btree.c

来自「最新的sqlite3.6.2源代码」· C语言 代码 · 共 2,132 行 · 第 1/5 页

      assert( frag<=data[pPage->hdrOffset+7] );
      data[pPage->hdrOffset+7] -= frag;
      put2byte(&data[pbegin], get2byte(&data[pnext]));
      put2byte(&data[pbegin+2], pnext+get2byte(&data[pnext+2])-pbegin);
    }else{
      addr = pbegin;
    }
  }

  /* If the cell content area begins with a freeblock, remove it. */
  if( data[hdr+1]==data[hdr+5] && data[hdr+2]==data[hdr+6] ){
    int top;
    pbegin = get2byte(&data[hdr+1]);
    memcpy(&data[hdr+1], &data[pbegin], 2);
    top = get2byte(&data[hdr+5]);
    put2byte(&data[hdr+5], top + get2byte(&data[pbegin+2]));
  }
}

/*
** Decode the flags byte (the first byte of the header) for a page
** and initialize fields of the MemPage structure accordingly.
**
** Only the following combinations are supported.  Anything different
** indicates a corrupt database files:
**
**         PTF_ZERODATA
**         PTF_ZERODATA | PTF_LEAF
**         PTF_LEAFDATA | PTF_INTKEY
**         PTF_LEAFDATA | PTF_INTKEY | PTF_LEAF
*/
static int decodeFlags(MemPage *pPage, int flagByte){
  BtShared *pBt;     /* A copy of pPage->pBt */

  assert( pPage->hdrOffset==(pPage->pgno==1 ? 100 : 0) );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  pPage->leaf = flagByte>>3;  assert( PTF_LEAF == 1<<3 );
  flagByte &= ~PTF_LEAF;
  pPage->childPtrSize = 4-4*pPage->leaf;
  pBt = pPage->pBt;
  if( flagByte==(PTF_LEAFDATA | PTF_INTKEY) ){
    pPage->intKey = 1;
    pPage->hasData = pPage->leaf;
    pPage->maxLocal = pBt->maxLeaf;
    pPage->minLocal = pBt->minLeaf;
  }else if( flagByte==PTF_ZERODATA ){
    pPage->intKey = 0;
    pPage->hasData = 0;
    pPage->maxLocal = pBt->maxLocal;
    pPage->minLocal = pBt->minLocal;
  }else{
    return SQLITE_CORRUPT_BKPT;
  }
  return SQLITE_OK;
}

/*
** Initialize the auxiliary information for a disk block.
**
** The pParent parameter must be a pointer to the MemPage which
** is the parent of the page being initialized.  The root of a
** BTree has no parent and so for that page, pParent==NULL.
**
** Return SQLITE_OK on success.  If we see that the page does
** not contain a well-formed database page, then return 
** SQLITE_CORRUPT.  Note that a return of SQLITE_OK does not
** guarantee that the page is well-formed.  It only shows that
** we failed to detect any corruption.
*/
int sqlite3BtreeInitPage(
  MemPage *pPage,        /* The page to be initialized */
  MemPage *pParent       /* The parent.  Might be NULL */
){
  int pc;            /* Address of a freeblock within pPage->aData[] */
  int 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 */

  pBt = pPage->pBt;
  assert( pBt!=0 );
  assert( pParent==0 || pParent->pBt==pBt );
  assert( sqlite3_mutex_held(pBt->mutex) );
  assert( pPage->pgno==sqlite3PagerPagenumber(pPage->pDbPage) );
  assert( pPage == sqlite3PagerGetExtra(pPage->pDbPage) );
  assert( pPage->aData == sqlite3PagerGetData(pPage->pDbPage) );
  if( pPage->pParent!=pParent && (pPage->pParent!=0 || pPage->isInit) ){
    /* The parent page should never change unless the file is corrupt */
    return SQLITE_CORRUPT_BKPT;
  }
  if( pPage->isInit ) return SQLITE_OK;
  if( pPage->pParent==0 && pParent!=0 ){
    pPage->pParent = pParent;
    sqlite3PagerRef(pParent->pDbPage);
  }
  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;
  pPage->idxShift = 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;
  }
  if( pPage->nCell==0 && pParent!=0 && pParent->pgno!=1 ){
    /* All pages must have at least one cell, except for root pages */
    return SQLITE_CORRUPT_BKPT;
  }

  /* Compute the total free space on the page */
  pc = get2byte(&data[hdr+1]);
  nFree = data[hdr+7] + top - (cellOffset + 2*pPage->nCell);
  while( pc>0 ){
    int 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 += size;
    pc = next;
  }
  pPage->nFree = nFree;
  if( nFree>=usableSize ){
    /* Free space cannot exceed total page size */
    return SQLITE_CORRUPT_BKPT; 
  }

#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
** no entries.
*/
static void zeroPage(MemPage *pPage, int flags){
  unsigned char *data = pPage->aData;
  BtShared *pBt = pPage->pBt;
  int hdr = pPage->hdrOffset;
  int first;

  assert( sqlite3PagerPagenumber(pPage->pDbPage)==pPage->pgno );
  assert( sqlite3PagerGetExtra(pPage->pDbPage) == (void*)pPage );
  assert( sqlite3PagerGetData(pPage->pDbPage) == data );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( sqlite3_mutex_held(pBt->mutex) );
  /*memset(&data[hdr], 0, pBt->usableSize - hdr);*/
  data[hdr] = flags;
  first = hdr + 8 + 4*((flags&PTF_LEAF)==0);
  memset(&data[hdr+1], 0, 4);
  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->idxShift = 0;
  pPage->nCell = 0;
  pPage->isInit = 1;
}

/*
** Get a page from the pager.  Initialize the MemPage.pBt and
** MemPage.aData elements if needed.
**
** If the noContent flag is set, it means that we do not care about
** the content of the page at this time.  So do not go to the disk
** to fetch the content.  Just fill in the content with zeros for now.
** If in the future we call sqlite3PagerWrite() on this page, that
** means we have started to be concerned about content and the disk
** read should occur at that point.
*/
int sqlite3BtreeGetPage(
  BtShared *pBt,       /* The btree */
  Pgno pgno,           /* Number of the page to fetch */
  MemPage **ppPage,    /* Return the page in this parameter */
  int noContent        /* Do not load page content if true */
){
  int rc;
  MemPage *pPage;
  DbPage *pDbPage;

  assert( sqlite3_mutex_held(pBt->mutex) );
  rc = sqlite3PagerAcquire(pBt->pPager, pgno, (DbPage**)&pDbPage, noContent);
  if( rc ) return rc;
  pPage = (MemPage *)sqlite3PagerGetExtra(pDbPage);
  pPage->aData = sqlite3PagerGetData(pDbPage);
  pPage->pDbPage = pDbPage;
  pPage->pBt = pBt;
  pPage->pgno = pgno;
  pPage->hdrOffset = pPage->pgno==1 ? 100 : 0;
  *ppPage = pPage;
  return SQLITE_OK;
}

/*
** Get a page from the pager and initialize it.  This routine
** is just a convenience wrapper around separate calls to
** sqlite3BtreeGetPage() and sqlite3BtreeInitPage().
*/
static int getAndInitPage(
  BtShared *pBt,          /* The database file */
  Pgno pgno,           /* Number of the page to get */
  MemPage **ppPage,    /* Write the page pointer here */
  MemPage *pParent     /* Parent of the page */
){
  int rc;
  assert( sqlite3_mutex_held(pBt->mutex) );
  if( pgno==0 ){
    return SQLITE_CORRUPT_BKPT; 
  }
  rc = sqlite3BtreeGetPage(pBt, pgno, ppPage, 0);
  if( rc==SQLITE_OK && (*ppPage)->isInit==0 ){
    rc = sqlite3BtreeInitPage(*ppPage, pParent);
    if( rc!=SQLITE_OK ){
      releasePage(*ppPage);
      *ppPage = 0;
    }
  }
  return rc;
}

/*
** Release a MemPage.  This should be called once for each prior
** call to sqlite3BtreeGetPage.
*/
static void releasePage(MemPage *pPage){
  if( pPage ){
    assert( pPage->aData );
    assert( pPage->pBt );
    assert( sqlite3PagerGetExtra(pPage->pDbPage) == (void*)pPage );
    assert( sqlite3PagerGetData(pPage->pDbPage)==pPage->aData );
    assert( sqlite3_mutex_held(pPage->pBt->mutex) );
    sqlite3PagerUnref(pPage->pDbPage);
  }
}

/*
** This routine is called when the reference count for a page
** reaches zero.  We need to unref the pParent pointer when that
** happens.
*/
static void pageDestructor(DbPage *pData){
  MemPage *pPage;
  pPage = (MemPage *)sqlite3PagerGetExtra(pData);
  if( pPage ){
    assert( pPage->isInit==0 || sqlite3_mutex_held(pPage->pBt->mutex) );
    if( pPage->pParent ){
      MemPage *pParent = pPage->pParent;
      assert( pParent->pBt==pPage->pBt );
      pPage->pParent = 0;
      releasePage(pParent);
    }
    pPage->isInit = 0;
  }
}

/*
** During a rollback, when the pager reloads information into the cache
** so that the cache is restored to its original state at the start of
** the transaction, for each page restored this routine is called.
**
** This routine needs to reset the extra data section at the end of the
** page to agree with the restored data.
*/
static void pageReinit(DbPage *pData, int pageSize){
  MemPage *pPage;
  assert( (pageSize & 7)==0 );
  pPage = (MemPage *)sqlite3PagerGetExtra(pData);
  if( pPage->isInit ){
    assert( sqlite3_mutex_held(pPage->pBt->mutex) );
    pPage->isInit = 0;
    sqlite3BtreeInitPage(pPage, pPage->pParent);
  }
}

/*
** Invoke the busy handler for a btree.
*/
static int sqlite3BtreeInvokeBusyHandler(void *pArg, int n){
  BtShared *pBt = (BtShared*)pArg;
  assert( pBt->db );
  assert( sqlite3_mutex_held(pBt->db->mutex) );
  return sqlite3InvokeBusyHandler(&pBt->db->busyHandler);
}

/*
** Open a database file.
** 
** zFilename is the name of the database file.  If zFilename is NULL
** a new database with a random name is created.  This randomly named
** database file will be deleted when sqlite3BtreeClose() is called.
** If zFilename is ":memory:" then an in-memory database is created
** that is automatically destroyed when it is closed.
*/
int sqlite3BtreeOpen(
  const char *zFilename,  /* Name of the file containing the BTree database */
  sqlite3 *db,            /* Associated database handle */
  Btree **ppBtree,        /* Pointer to new Btree object written here */
  int flags,              /* Options */
  int vfsFlags            /* Flags passed through to sqlite3_vfs.xOpen() */
){
  sqlite3_vfs *pVfs;      /* The VFS to use for this btree */
  BtShared *pBt = 0;      /* Shared part of btree structure */
  Btree *p;               /* Handle to return */
  int rc = SQLITE_OK;
  int nReserve;
  unsigned char zDbHeader[100];

  /* Set the variable isMemdb to true for an in-memory database, or 
  ** false for a file-based database. This symbol is only required if
  ** either of the shared-data or autovacuum features are compiled 
  ** into the library.
  */
#if !defined(SQLITE_OMIT_SHARED_CACHE) || !defined(SQLITE_OMIT_AUTOVACUUM)
  #ifdef SQLITE_OMIT_MEMORYDB
    const int isMemdb = 0;
  #else
    const int isMemdb = zFilename && !strcmp(zFilename, ":memory:");
  #endif
#endif

  assert( db!=0 );
  assert( sqlite3_mutex_held(db->mutex) );

  pVfs = db->pVfs;
  p = sqlite3MallocZero(sizeof(Btree));
  if( !p ){
    return SQLITE_NOMEM;
  }
  p->inTrans = TRANS_NONE;
  p->db = db;

#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
  /*
  ** If this Btree is a candidate for shared cache, try to find an
  ** existing BtShared object that we can share with
  */
  if( isMemdb==0
   && (db->flags & SQLITE_Vtab)==0
   && zFilename && zFilename[0]
  ){
    if( sqlite3SharedCacheEnabled ){
      int nFullPathname = pVfs->mxPathname+1;
      char *zFullPathname = sqlite3Malloc(nFullPathname);
      sqlite3_mutex *mutexShared;
      p->sharable = 1;
      db->flags |= SQLITE_SharedCache;
      if( !zFullPathname ){
        sqlite3_free(p);
        return SQLITE_NOMEM;
      }
      sqlite3OsFullPathname(pVfs, zFilename, nFullPathname, zFullPathname);
      mutexShared = sqlite3MutexAlloc(SQLITE_MUTEX_STATIC_MASTER);
      sqlite3_mutex_enter(mutexShared);
      for(pBt=sqlite3SharedCacheList; pBt; pBt=pBt->pNext){
        assert( pBt->nRef>0 );
        if( 0==strcmp(zFullPathname, sqlite3PagerFilename(pBt->pPager))
                 && sqlite3PagerVfs(pBt->pPager)==pVfs ){
          p->pBt = pBt;
          pBt->nRef++;
          break;
        }
      }
      sqlite3_mutex_leave(mutexShared);
      sqlite3_free(zFullPathname);
    }
#ifdef SQLITE_DEBUG
    else{
      /* In debug mode, we mark all persistent databases as sharable
      ** even when they are not.  This exercises the locking code and
      ** gives more opportunity for asserts(sqlite3_mutex_held())
      ** statements to find locking problems.
      */
      p->sharable = 1;
    }
#endif
  }
#endif
  if( pBt==0 ){
    /*
    ** The following asserts make sure that structures used by the btree are
    ** the right size.  This is to guard against size changes that result
    ** when compiling on a different architecture.
    */
    assert( sizeof(i64)==8 || sizeof(i64)==4 );
    assert( sizeof(u64)==8 || sizeof(u64)==4 );
    assert( sizeof(u32)==4 );
    assert( sizeof(u16)==2 );