SQLite

Check-in [aab82a229a]
Login

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

Overview
Comment:Simplifications to sqlite3BtreeInsert() and allocateSpace(). Added many testcase() macros to verify boundary conditions in btree.c. (CVS 6858)
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: aab82a229a984bdd37bda2d140cf4279ab54a741
User & Date: drh 2009-07-08 01:49:12.000
Context
2009-07-08
08:05
Remove an ALWAYS clause that could be false if an IO error within a statement executed by a virtual table caused an emergency rollback. (CVS 6859) (check-in: 0cc705c2c4 user: danielk1977 tags: trunk)
01:49
Simplifications to sqlite3BtreeInsert() and allocateSpace(). Added many testcase() macros to verify boundary conditions in btree.c. (CVS 6858) (check-in: aab82a229a user: drh tags: trunk)
2009-07-07
17:38
Improvements to corrupt database detection in defragmentPage(). (CVS 6857) (check-in: 87bbc8d6b6 user: drh tags: trunk)
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/btree.c.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
/*
** 2004 April 6
**
** The author disclaims copyright to this source code.  In place of
** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** $Id: btree.c,v 1.657 2009/07/07 17:38:39 drh Exp $
**
** This file implements a external (disk-based) database using BTrees.
** See the header comment on "btreeInt.h" for additional information.
** Including a description of file format and an overview of operation.
*/
#include "btreeInt.h"












|







1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
/*
** 2004 April 6
**
** The author disclaims copyright to this source code.  In place of
** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** $Id: btree.c,v 1.658 2009/07/08 01:49:12 drh Exp $
**
** This file implements a external (disk-based) database using BTrees.
** See the header comment on "btreeInt.h" for additional information.
** Including a description of file format and an overview of operation.
*/
#include "btreeInt.h"

806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
** This routine works only for pages that do not contain overflow cells.
*/
#define findCell(P,I) \
  ((P)->aData + ((P)->maskPage & get2byte(&(P)->aData[(P)->cellOffset+2*(I)])))

/*
** This a more complex version of findCell() that works for
** pages that do contain overflow cells.  See insert
*/
static u8 *findOverflowCell(MemPage *pPage, int iCell){
  int i;
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  for(i=pPage->nOverflow-1; i>=0; i--){
    int k;
    struct _OvflCell *pOvfl;







|







806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
** This routine works only for pages that do not contain overflow cells.
*/
#define findCell(P,I) \
  ((P)->aData + ((P)->maskPage & get2byte(&(P)->aData[(P)->cellOffset+2*(I)])))

/*
** This a more complex version of findCell() that works for
** pages that do contain overflow cells.
*/
static u8 *findOverflowCell(MemPage *pPage, int iCell){
  int i;
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  for(i=pPage->nOverflow-1; i>=0; i--){
    int k;
    struct _OvflCell *pOvfl;
864
865
866
867
868
869
870


871
872
873
874
875
876
877
  }else{
    pInfo->nData = 0;
    n += getVarint32(&pCell[n], nPayload);
    pInfo->nKey = nPayload;
  }
  pInfo->nPayload = nPayload;
  pInfo->nHeader = n;


  if( likely(nPayload<=pPage->maxLocal) ){
    /* This is the (easy) common case where the entire payload fits
    ** on the local page.  No overflow is required.
    */
    int nSize;          /* Total size of cell content in bytes */
    nSize = nPayload + n;
    pInfo->nLocal = (u16)nPayload;







>
>







864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
  }else{
    pInfo->nData = 0;
    n += getVarint32(&pCell[n], nPayload);
    pInfo->nKey = nPayload;
  }
  pInfo->nPayload = nPayload;
  pInfo->nHeader = n;
  testcase( nPayload==pPage->maxLocal );
  testcase( nPayload==pPage->maxLocal+1 );
  if( likely(nPayload<=pPage->maxLocal) ){
    /* This is the (easy) common case where the entire payload fits
    ** on the local page.  No overflow is required.
    */
    int nSize;          /* Total size of cell content in bytes */
    nSize = nPayload + n;
    pInfo->nLocal = (u16)nPayload;
893
894
895
896
897
898
899


900
901
902
903
904
905
906
    int minLocal;  /* Minimum amount of payload held locally */
    int maxLocal;  /* Maximum amount of payload held locally */
    int surplus;   /* Overflow payload available for local storage */

    minLocal = pPage->minLocal;
    maxLocal = pPage->maxLocal;
    surplus = minLocal + (nPayload - minLocal)%(pPage->pBt->usableSize - 4);


    if( surplus <= maxLocal ){
      pInfo->nLocal = (u16)surplus;
    }else{
      pInfo->nLocal = (u16)minLocal;
    }
    pInfo->iOverflow = (u16)(pInfo->nLocal + n);
    pInfo->nSize = pInfo->iOverflow + 4;







>
>







895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
    int minLocal;  /* Minimum amount of payload held locally */
    int maxLocal;  /* Maximum amount of payload held locally */
    int surplus;   /* Overflow payload available for local storage */

    minLocal = pPage->minLocal;
    maxLocal = pPage->maxLocal;
    surplus = minLocal + (nPayload - minLocal)%(pPage->pBt->usableSize - 4);
    testcase( surplus==maxLocal );
    testcase( surplus==maxLocal+1 );
    if( surplus <= maxLocal ){
      pInfo->nLocal = (u16)surplus;
    }else{
      pInfo->nLocal = (u16)minLocal;
    }
    pInfo->iOverflow = (u16)(pInfo->nLocal + n);
    pInfo->nSize = pInfo->iOverflow + 4;
948
949
950
951
952
953
954


955
956
957


958
959
960
961
962
963
964
    ** past the end of the key value. */
    pEnd = &pIter[9];
    while( (*pIter++)&0x80 && pIter<pEnd );
  }else{
    pIter += getVarint32(pIter, nSize);
  }



  if( nSize>pPage->maxLocal ){
    int minLocal = pPage->minLocal;
    nSize = minLocal + (nSize - minLocal) % (pPage->pBt->usableSize - 4);


    if( nSize>pPage->maxLocal ){
      nSize = minLocal;
    }
    nSize += 4;
  }
  nSize += (u32)(pIter - pCell);








>
>



>
>







952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
    ** past the end of the key value. */
    pEnd = &pIter[9];
    while( (*pIter++)&0x80 && pIter<pEnd );
  }else{
    pIter += getVarint32(pIter, nSize);
  }

  testcase( nSize==pPage->maxLocal );
  testcase( nSize==pPage->maxLocal+1 );
  if( nSize>pPage->maxLocal ){
    int minLocal = pPage->minLocal;
    nSize = minLocal + (nSize - minLocal) % (pPage->pBt->usableSize - 4);
    testcase( nSize==pPage->maxLocal );
    testcase( nSize==pPage->maxLocal+1 );
    if( nSize>pPage->maxLocal ){
      nSize = minLocal;
    }
    nSize += 4;
  }
  nSize += (u32)(pIter - pCell);

1034
1035
1036
1037
1038
1039
1040


1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061



1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081

1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097


1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109

1110

1111


1112
1113
1114

1115


1116
1117
1118
1119
1120
1121
1122
1123
1124
1125


1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136

1137
1138
1139












1140
1141
1142
1143
1144
1145

1146
1147
1148
1149
1150
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

1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
  cbrk = usableSize;
  iCellFirst = cellOffset + 2*nCell;
  iCellLast = usableSize - 4;
  for(i=0; i<nCell; i++){
    u8 *pAddr;     /* The i-th cell pointer */
    pAddr = &data[cellOffset + i*2];
    pc = get2byte(pAddr);


#if !defined(SQLITE_ENABLE_OVERSIZE_CELL_CHECK)
    /* These conditions have already been verified in sqlite3BtreeInitPage()
    ** if SQLITE_ENABLE_OVERSIZE_CELL_CHECK is defined 
    */
    if( pc<iCellFirst || pc>iCellLast ){
      return SQLITE_CORRUPT_BKPT;
    }
#endif
    assert( pc>=iCellFirst && pc<=iCellLast );
    size = cellSizePtr(pPage, &temp[pc]);
    cbrk -= size;
#if defined(SQLITE_ENABLE_OVERSIZE_CELL_CHECK)
    if( cbrk<iCellFirst ){
      return SQLITE_CORRUPT_BKPT;
    }
#else
    if( cbrk<iCellFirst || pc+size>usableSize ){
      return SQLITE_CORRUPT_BKPT;
    }
#endif
    assert( cbrk+size<=usableSize && cbrk>iCellFirst );



    memcpy(&data[cbrk], &temp[pc], size);
    put2byte(pAddr, cbrk);
  }
  assert( cbrk>=iCellFirst );
  put2byte(&data[hdr+5], cbrk);
  data[hdr+1] = 0;
  data[hdr+2] = 0;
  data[hdr+7] = 0;
  memset(&data[iCellFirst], 0, cbrk-iCellFirst);
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  if( cbrk-iCellFirst!=pPage->nFree ){
    return SQLITE_CORRUPT_BKPT;
  }
  return SQLITE_OK;
}

/*
** Allocate nByte bytes of space from within the B-Tree page passed
** as the first argument. Return the index into pPage->aData[] of the 
** first byte of allocated space. 

**
** The caller guarantees that the space between the end of the cell-offset 
** array and the start of the cell-content area is at least nByte bytes
** in size. So this routine can never fail.
**
** If there are already 60 or more bytes of fragments within the page,
** the page is defragmented before returning. If this were not done there
** is a chance that the number of fragmented bytes could eventually 
** overflow the single-byte field of the page-header in which this value
** is stored.
*/
static int allocateSpace(MemPage *pPage, int nByte){
  const int hdr = pPage->hdrOffset;    /* Local cache of pPage->hdrOffset */
  u8 * const data = pPage->aData;      /* Local cache of pPage->aData */
  int nFrag;                           /* Number of fragmented bytes on pPage */
  int top;


  
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( pPage->pBt );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( nByte>=0 );  /* Minimum cell size is 4 */
  assert( pPage->nFree>=nByte );
  assert( pPage->nOverflow==0 );

  /* Assert that the space between the cell-offset array and the 
  ** cell-content area is greater than nByte bytes.
  */
  assert( nByte <= (

      get2byte(&data[hdr+5])-(hdr+8+(pPage->leaf?0:4)+2*get2byte(&data[hdr+3]))

  ));



  nFrag = data[hdr+7];
  if( nFrag>=60 ){

    defragmentPage(pPage);


  }else{
    /* 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){
      int size = get2byte(&data[pc+2]);     /* Size of free slot */
      if( size>=nByte ){
        int x = size - nByte;


        if( x<4 ){
          /* Remove the slot from the free-list. Update the number of
          ** fragmented bytes within the page. */
          memcpy(&data[addr], &data[pc], 2);
          data[hdr+7] = (u8)(nFrag + x);
        }else{
          /* The slot remains on the free-list. Reduce its size to account
          ** for the portion used by the new allocation. */
          put2byte(&data[pc+2], x);
        }
        return pc + x;

      }
    }
  }













  /* Allocate memory from the gap in between the cell pointer array
  ** and the cell content area.
  */
  top = get2byte(&data[hdr+5]) - nByte;
  put2byte(&data[hdr+5], top);

  return top;
}

/*
** Return a section of the pPage->aData to the freelist.
** The first byte of the new free block is pPage->aDisk[start]
** and the size of the block is "size" bytes.
**
** Most of the effort here is involved in coalesing adjacent
** free blocks into a single big free block.
*/
static int freeSpace(MemPage *pPage, int start, int size){
  int addr, pbegin, hdr;

  unsigned char *data = pPage->aData;

  assert( pPage->pBt!=0 );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( start>=pPage->hdrOffset+6+(pPage->leaf?0:4) );
  assert( (start + size)<=pPage->pBt->usableSize );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( size>=0 );   /* Minimum cell size is 4 */

#ifdef SQLITE_SECURE_DELETE
  /* Overwrite deleted information with zeros when the SECURE_DELETE 
  ** option is enabled at compile-time */
  memset(&data[start], 0, size);
#endif

  /* Add the space back into the linked list of freeblocks */






  hdr = pPage->hdrOffset;
  addr = hdr + 1;

  while( (pbegin = get2byte(&data[addr]))<start && pbegin>0 ){
    assert( pbegin<=pPage->pBt->usableSize-4 );
    if( pbegin<=addr ) {
      return SQLITE_CORRUPT_BKPT;
    }
    addr = pbegin;
  }
  if ( pbegin>pPage->pBt->usableSize-4 ) {
    return SQLITE_CORRUPT_BKPT;
  }
  assert( pbegin>addr || pbegin==0 );
  put2byte(&data[addr], start);
  put2byte(&data[start], pbegin);
  put2byte(&data[start+2], size);
  pPage->nFree = pPage->nFree + (u16)size;

  /* Coalesce adjacent free blocks */
  addr = pPage->hdrOffset + 1;
  while( (pbegin = get2byte(&data[addr]))>0 ){
    int pnext, psize, x;
    assert( pbegin>addr );
    assert( pbegin<=pPage->pBt->usableSize-4 );
    pnext = get2byte(&data[pbegin]);
    psize = get2byte(&data[pbegin+2]);
    if( pbegin + psize + 3 >= pnext && pnext>0 ){
      int frag = pnext - (pbegin+psize);
      if( (frag<0) || (frag>(int)data[pPage->hdrOffset+7]) ){
        return SQLITE_CORRUPT_BKPT;
      }
      data[pPage->hdrOffset+7] -= (u8)frag;
      x = get2byte(&data[pnext]);
      put2byte(&data[pbegin], x);
      x = pnext + get2byte(&data[pnext+2]) - pbegin;
      put2byte(&data[pbegin+2], x);
    }else{
      addr = pbegin;
    }







>
>




















|
>
>
>


















|
|
>

|
<
|
|
|
|
<
<
|

|



|
>
>








|
<
<
|
>
|
>
|
>
>

<

>
|
>
>
|









>
>










|
>



>
>
>
>
>
>
>
>
>
>
>
>




|

>
|












>















|
>
>
>
>
>
>


>

<
|




|









|








|


|







1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097

1098
1099
1100
1101


1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119


1120
1121
1122
1123
1124
1125
1126
1127

1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
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
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218

1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
  cbrk = usableSize;
  iCellFirst = cellOffset + 2*nCell;
  iCellLast = usableSize - 4;
  for(i=0; i<nCell; i++){
    u8 *pAddr;     /* The i-th cell pointer */
    pAddr = &data[cellOffset + i*2];
    pc = get2byte(pAddr);
    testcase( pc==iCellFirst );
    testcase( pc==iCellLast );
#if !defined(SQLITE_ENABLE_OVERSIZE_CELL_CHECK)
    /* These conditions have already been verified in sqlite3BtreeInitPage()
    ** if SQLITE_ENABLE_OVERSIZE_CELL_CHECK is defined 
    */
    if( pc<iCellFirst || pc>iCellLast ){
      return SQLITE_CORRUPT_BKPT;
    }
#endif
    assert( pc>=iCellFirst && pc<=iCellLast );
    size = cellSizePtr(pPage, &temp[pc]);
    cbrk -= size;
#if defined(SQLITE_ENABLE_OVERSIZE_CELL_CHECK)
    if( cbrk<iCellFirst ){
      return SQLITE_CORRUPT_BKPT;
    }
#else
    if( cbrk<iCellFirst || pc+size>usableSize ){
      return SQLITE_CORRUPT_BKPT;
    }
#endif
    assert( cbrk+size<=usableSize && cbrk>=iCellFirst );
    testcase( cbrk+size==usableSize );
    testcase( cbrk==iCellFirst );
    testcase( pc+size==usableSize );
    memcpy(&data[cbrk], &temp[pc], size);
    put2byte(pAddr, cbrk);
  }
  assert( cbrk>=iCellFirst );
  put2byte(&data[hdr+5], cbrk);
  data[hdr+1] = 0;
  data[hdr+2] = 0;
  data[hdr+7] = 0;
  memset(&data[iCellFirst], 0, cbrk-iCellFirst);
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  if( cbrk-iCellFirst!=pPage->nFree ){
    return SQLITE_CORRUPT_BKPT;
  }
  return SQLITE_OK;
}

/*
** Allocate nByte bytes of space from within the B-Tree page passed
** as the first argument. Write into *pIdx the index into pPage->aData[]
** of the first byte of allocated space. Return either SQLITE_OK or
** an error code (usually SQLITE_CORRUPT).
**
** The caller guarantees that there is sufficient space to make the

** allocation.  This routine might need to defragment in order to bring
** all the space together, however.  This routine will avoid using
** the first two bytes past the cell pointer area since presumably this
** allocation is being made in order to insert a new cell, so we will


** also end up needing a new cell pointer.
*/
static int allocateSpace(MemPage *pPage, int nByte, int *pIdx){
  const int hdr = pPage->hdrOffset;    /* Local cache of pPage->hdrOffset */
  u8 * const data = pPage->aData;      /* Local cache of pPage->aData */
  int nFrag;                           /* Number of fragmented bytes on pPage */
  int top;                             /* First byte of cell content area */
  int gap;        /* First byte of gap between cell pointers and cell content */
  int rc;         /* Integer return code */
  
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( pPage->pBt );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( nByte>=0 );  /* Minimum cell size is 4 */
  assert( pPage->nFree>=nByte );
  assert( pPage->nOverflow==0 );

  nFrag = data[hdr+7];


  assert( pPage->cellOffset == hdr + 12 - 4*pPage->leaf );
  gap = pPage->cellOffset + 2*pPage->nCell;
  top = get2byte(&data[hdr+5]);
  assert( gap<=top );
  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){
      int size = get2byte(&data[pc+2]);     /* Size of free slot */
      if( size>=nByte ){
        int x = size - nByte;
        testcase( x==4 );
        testcase( x==3 );
        if( x<4 ){
          /* Remove the slot from the free-list. Update the number of
          ** fragmented bytes within the page. */
          memcpy(&data[addr], &data[pc], 2);
          data[hdr+7] = (u8)(nFrag + x);
        }else{
          /* The slot remains on the free-list. Reduce its size to account
          ** for the portion used by the new allocation. */
          put2byte(&data[pc+2], x);
        }
        *pIdx = pc + x;
        return SQLITE_OK;
      }
    }
  }

  /* Check to make sure there is enough space in the gap to satisfy
  ** 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.
  */
  top -= nByte;
  put2byte(&data[hdr+5], top);
  *pIdx = top;
  return SQLITE_OK;
}

/*
** Return a section of the pPage->aData to the freelist.
** The first byte of the new free block is pPage->aDisk[start]
** and the size of the block is "size" bytes.
**
** Most of the effort here is involved in coalesing adjacent
** free blocks into a single big free block.
*/
static int freeSpace(MemPage *pPage, int start, int size){
  int addr, pbegin, hdr;
  int iLast;                        /* Largest possible freeblock offset */
  unsigned char *data = pPage->aData;

  assert( pPage->pBt!=0 );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( start>=pPage->hdrOffset+6+(pPage->leaf?0:4) );
  assert( (start + size)<=pPage->pBt->usableSize );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( size>=0 );   /* Minimum cell size is 4 */

#ifdef SQLITE_SECURE_DELETE
  /* Overwrite deleted information with zeros when the SECURE_DELETE 
  ** option is enabled at compile-time */
  memset(&data[start], 0, size);
#endif

  /* Add the space back into the linked list of freeblocks.  Note that
  ** even though the freeblock list was checked by sqlite3BtreeInitPage(),
  ** sqlite3BtreeInitPage() did not detect overlapping freeblocks or
  ** freeblocks that overlapped cells.  If there was overlap then
  ** subsequent insert operations might have corrupted the freelist.
  ** So we do need to check for corruption while scanning the freelist.
  */
  hdr = pPage->hdrOffset;
  addr = hdr + 1;
  iLast = pPage->pBt->usableSize - 4;
  while( (pbegin = get2byte(&data[addr]))<start && pbegin>0 ){

    if( pbegin>iLast || pbegin<addr+4 ){
      return SQLITE_CORRUPT_BKPT;
    }
    addr = pbegin;
  }
  if( pbegin>iLast ){
    return SQLITE_CORRUPT_BKPT;
  }
  assert( pbegin>addr || pbegin==0 );
  put2byte(&data[addr], start);
  put2byte(&data[start], pbegin);
  put2byte(&data[start+2], size);
  pPage->nFree = pPage->nFree + (u16)size;

  /* Coalesce adjacent free blocks */
  addr = hdr + 1;
  while( (pbegin = get2byte(&data[addr]))>0 ){
    int pnext, psize, x;
    assert( pbegin>addr );
    assert( pbegin<=pPage->pBt->usableSize-4 );
    pnext = get2byte(&data[pbegin]);
    psize = get2byte(&data[pbegin+2]);
    if( pbegin + psize + 3 >= pnext && pnext>0 ){
      int frag = pnext - (pbegin+psize);
      if( (frag<0) || (frag>(int)data[hdr+7]) ){
        return SQLITE_CORRUPT_BKPT;
      }
      data[hdr+7] -= (u8)frag;
      x = get2byte(&data[pnext]);
      put2byte(&data[pbegin], x);
      x = pnext + get2byte(&data[pnext+2]) - pbegin;
      put2byte(&data[pbegin+2], x);
    }else{
      addr = pbegin;
    }
1284
1285
1286
1287
1288
1289
1290


1291
1292
1293
1294
1295
1296
1297
    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 */



    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 );







>
>







1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
    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 );
1309
1310
1311
1312
1313
1314
1315


1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327


1328
1329
1330
1331

1332
1333
1334
1335

1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
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
    /* A malformed database page might cause use to read past the end
    ** of page when parsing a cell.  
    **
    ** The following block of code checks early to see if a cell extends
    ** past the end of a page boundary and causes SQLITE_CORRUPT to be 
    ** returned if it does.
    */


#if defined(SQLITE_ENABLE_OVERSIZE_CELL_CHECK)
    {
      int iCellFirst;   /* First allowable cell index */
      int iCellLast;    /* Last possible cell index */
      int i;            /* Index into the cell pointer array */
      int sz;           /* Size of a cell */

      iCellFirst = cellOffset + 2*pPage->nCell;
      iCellLast = usableSize - 4;
      if( !pPage->leaf ) iCellLast--;
      for(i=0; i<pPage->nCell; i++){
        pc = get2byte(&data[cellOffset+i*2]);


        if( pc<iCellFirst || pc>iCellLast ){
          return SQLITE_CORRUPT_BKPT;
        }
        sz = cellSizePtr(pPage, &data[pc]);

        if( pc+sz>usableSize ){
          return SQLITE_CORRUPT_BKPT;
        }
      }

    }  
#endif

    /* Compute the total free space on the page */
    pc = get2byte(&data[hdr+1]);
    nFree = data[hdr+7] + top;
    while( pc>0 ){
      u16 next, size;
      if( pc>usableSize-4 ){
        /* Free block is off the page */
        return SQLITE_CORRUPT_BKPT; 
      }
      next = get2byte(&data[pc]);
      size = get2byte(&data[pc+2]);
      if( next>0 && next<=pc+size+3 ){
        /* Free blocks must be in accending order */
        return SQLITE_CORRUPT_BKPT; 
      }
      nFree = nFree + size;
      pc = next;
    }

    /* At this point, nFree contains the sum of the offset to the start
    ** of the cell-content area plus the number of free bytes within
    ** the cell-content area. If this is greater than the usable-size
    ** of the page, then the page must be corrupted. This check also
    ** serves to verify that the offset to the start of the cell-content
    ** area, according to the page header, lies within the page.
    */
    if( nFree>usableSize ){
      return SQLITE_CORRUPT_BKPT; 
    }
    pPage->nFree = nFree - (cellOffset + 2*pPage->nCell);

#if 0
  /* Check that all the offsets in the cell offset array are within range. 
  ** 
  ** Omitting this consistency check and using the pPage->maskPage mask
  ** to prevent overrunning the page buffer in findCell() results in a
  ** 2.5% performance gain.
  */
  {
    u8 *pOff;        /* Iterator used to check all cell offsets are in range */
    u8 *pEnd;        /* Pointer to end of cell offset array */
    u8 mask;         /* Mask of bits that must be zero in MSB of cell offsets */
    mask = ~(((u8)(pBt->pageSize>>8))-1);
    pEnd = &data[cellOffset + pPage->nCell*2];
    for(pOff=&data[cellOffset]; pOff!=pEnd && !((*pOff)&mask); pOff+=2);
    if( pOff!=pEnd ){
      return SQLITE_CORRUPT_BKPT;
    }
  }
#endif

    pPage->isInit = 1;
  }
  return SQLITE_OK;
}

/*
** Set up a raw page so that it looks like a database page holding







>
>


<
<



<
<



>
>




>




>








|






|
















|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361


1362
1363
1364


1365
1366
1367
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
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412





















1413
1414
1415
1416
1417
1418
1419
    /* A malformed database page might cause use to read past the end
    ** of page when parsing a cell.  
    **
    ** The following block of code checks early to see if a cell extends
    ** past the end of a page boundary and causes SQLITE_CORRUPT to be 
    ** returned if it does.
    */
    iCellFirst = cellOffset + 2*pPage->nCell;
    iCellLast = usableSize - 4;
#if defined(SQLITE_ENABLE_OVERSIZE_CELL_CHECK)
    {


      int i;            /* Index into the cell pointer array */
      int sz;           /* Size of a cell */



      if( !pPage->leaf ) iCellLast--;
      for(i=0; i<pPage->nCell; i++){
        pc = get2byte(&data[cellOffset+i*2]);
        testcase( pc==iCellFirst );
        testcase( pc==iCellLast );
        if( pc<iCellFirst || pc>iCellLast ){
          return SQLITE_CORRUPT_BKPT;
        }
        sz = cellSizePtr(pPage, &data[pc]);
        testcase( pc+sz==usableSize );
        if( pc+sz>usableSize ){
          return SQLITE_CORRUPT_BKPT;
        }
      }
      if( !pPage->leaf ) iCellLast++;
    }  
#endif

    /* Compute the total free space on the page */
    pc = get2byte(&data[hdr+1]);
    nFree = data[hdr+7] + top;
    while( pc>0 ){
      u16 next, size;
      if( pc<iCellFirst || pc>iCellLast ){
        /* Free block is off the page */
        return SQLITE_CORRUPT_BKPT; 
      }
      next = get2byte(&data[pc]);
      size = get2byte(&data[pc+2]);
      if( next>0 && next<=pc+size+3 ){
        /* Free blocks must be in ascending order */
        return SQLITE_CORRUPT_BKPT; 
      }
      nFree = nFree + size;
      pc = next;
    }

    /* At this point, nFree contains the sum of the offset to the start
    ** of the cell-content area plus the number of free bytes within
    ** the cell-content area. If this is greater than the usable-size
    ** of the page, then the page must be corrupted. This check also
    ** serves to verify that the offset to the start of the cell-content
    ** area, according to the page header, lies within the page.
    */
    if( nFree>usableSize ){
      return SQLITE_CORRUPT_BKPT; 
    }
    pPage->nFree = nFree - iCellFirst;





















    pPage->isInit = 1;
  }
  return SQLITE_OK;
}

/*
** Set up a raw page so that it looks like a database page holding
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
static int btreeCursor(
  Btree *p,                              /* The btree */
  int iTable,                            /* Root page of table to open */
  int wrFlag,                            /* 1 to write. 0 read-only */
  struct KeyInfo *pKeyInfo,              /* First arg to comparison function */
  BtCursor *pCur                         /* Space for new cursor */
){
  int rc;                                /* Return code */
  BtShared *pBt = p->pBt;                /* Shared b-tree handle */

  assert( sqlite3BtreeHoldsMutex(p) );
  assert( wrFlag==0 || wrFlag==1 );

  /* The following assert statements verify that if this is a sharable 
  ** b-tree database, the connection is holding the required table locks, 







<







3247
3248
3249
3250
3251
3252
3253

3254
3255
3256
3257
3258
3259
3260
static int btreeCursor(
  Btree *p,                              /* The btree */
  int iTable,                            /* Root page of table to open */
  int wrFlag,                            /* 1 to write. 0 read-only */
  struct KeyInfo *pKeyInfo,              /* First arg to comparison function */
  BtCursor *pCur                         /* Space for new cursor */
){

  BtShared *pBt = p->pBt;                /* Shared b-tree handle */

  assert( sqlite3BtreeHoldsMutex(p) );
  assert( wrFlag==0 || wrFlag==1 );

  /* The following assert statements verify that if this is a sharable 
  ** b-tree database, the connection is holding the required table locks, 
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
  u8 *pCell,        /* Content of the new cell */
  int sz,           /* Bytes of content in pCell */
  u8 *pTemp,        /* Temp storage space for pCell, if needed */
  Pgno iChild       /* If non-zero, replace first 4 bytes with this value */
){
  int idx;          /* Where to write new cell content in data[] */
  int j;            /* Loop counter */
  int top;          /* First byte of content for any cell in data[] */
  int end;          /* First byte past the last cell pointer in data[] */
  int ins;          /* Index in data[] where new cell pointer is inserted */
  int hdr;          /* Offset into data[] of the page header */
  int cellOffset;   /* Address of first cell pointer in data[] */
  u8 *data;         /* The content of the whole page */
  u8 *ptr;          /* Used for moving information around in data[] */

  int nSkip = (iChild ? 4 : 0);

  assert( i>=0 && i<=pPage->nCell+pPage->nOverflow );







<


<







5214
5215
5216
5217
5218
5219
5220

5221
5222

5223
5224
5225
5226
5227
5228
5229
  u8 *pCell,        /* Content of the new cell */
  int sz,           /* Bytes of content in pCell */
  u8 *pTemp,        /* Temp storage space for pCell, if needed */
  Pgno iChild       /* If non-zero, replace first 4 bytes with this value */
){
  int idx;          /* Where to write new cell content in data[] */
  int j;            /* Loop counter */

  int end;          /* First byte past the last cell pointer in data[] */
  int ins;          /* Index in data[] where new cell pointer is inserted */

  int cellOffset;   /* Address of first cell pointer in data[] */
  u8 *data;         /* The content of the whole page */
  u8 *ptr;          /* Used for moving information around in data[] */

  int nSkip = (iChild ? 4 : 0);

  assert( i>=0 && i<=pPage->nCell+pPage->nOverflow );
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
  }else{
    int rc = sqlite3PagerWrite(pPage->pDbPage);
    if( rc!=SQLITE_OK ){
      return rc;
    }
    assert( sqlite3PagerIswriteable(pPage->pDbPage) );
    data = pPage->aData;
    hdr = pPage->hdrOffset;
    top = get2byte(&data[hdr+5]);
    cellOffset = pPage->cellOffset;
    end = cellOffset + 2*pPage->nCell + 2;
    ins = cellOffset + 2*i;
    if( end > top - sz ){
      rc = defragmentPage(pPage);
      if( rc!=SQLITE_OK ){
        return rc;
      }
      top = get2byte(&data[hdr+5]);
      assert( end + sz <= top );
    }
    idx = allocateSpace(pPage, sz);
    assert( idx>0 );
    assert( end <= get2byte(&data[hdr+5]) );
    if (idx+sz > pPage->pBt->usableSize) {
      return SQLITE_CORRUPT_BKPT;
    }
    pPage->nCell++;
    pPage->nFree = pPage->nFree - (u16)(2 + sz);
    memcpy(&data[idx+nSkip], pCell+nSkip, sz-nSkip);
    if( iChild ){
      put4byte(&data[idx], iChild);
    }
    for(j=end-2, ptr=&data[j]; j>ins; j-=2, ptr-=2){
      ptr[0] = ptr[-2];
      ptr[1] = ptr[-1];
    }
    put2byte(&data[ins], idx);
    put2byte(&data[hdr+3], pPage->nCell);
#ifndef SQLITE_OMIT_AUTOVACUUM
    if( pPage->pBt->autoVacuum ){
      /* The cell may contain a pointer to an overflow page. If so, write
      ** the entry for the overflow page into the pointer map.
      */
      return ptrmapPutOvflPtr(pPage, pCell);
    }







<
<

|

<
|
<
|
<
<
<
<
<
|
<
|



|




|




|







5246
5247
5248
5249
5250
5251
5252


5253
5254
5255

5256

5257





5258

5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
  }else{
    int rc = sqlite3PagerWrite(pPage->pDbPage);
    if( rc!=SQLITE_OK ){
      return rc;
    }
    assert( sqlite3PagerIswriteable(pPage->pDbPage) );
    data = pPage->aData;


    cellOffset = pPage->cellOffset;
    end = cellOffset + 2*pPage->nCell;
    ins = cellOffset + 2*i;

    rc = allocateSpace(pPage, sz, &idx);

    if( rc ) return rc;





    assert( idx>=end+2 );

    if( idx+sz > pPage->pBt->usableSize ){
      return SQLITE_CORRUPT_BKPT;
    }
    pPage->nCell++;
    pPage->nFree -= (u16)(2 + sz);
    memcpy(&data[idx+nSkip], pCell+nSkip, sz-nSkip);
    if( iChild ){
      put4byte(&data[idx], iChild);
    }
    for(j=end, ptr=&data[j]; j>ins; j-=2, ptr-=2){
      ptr[0] = ptr[-2];
      ptr[1] = ptr[-1];
    }
    put2byte(&data[ins], idx);
    put2byte(&data[pPage->hdrOffset+3], pPage->nCell);
#ifndef SQLITE_OMIT_AUTOVACUUM
    if( pPage->pBt->autoVacuum ){
      /* The cell may contain a pointer to an overflow page. If so, write
      ** the entry for the overflow page into the pointer map.
      */
      return ptrmapPutOvflPtr(pPage, pCell);
    }