SQLite

#define FILEHANDLEID(fd) ((int)fd)

/*
** The Pager.eState variable stores the current 'state' of a pager. A
** pager may be in any one of the following six states:
**
**  NONE:

**    The pager starts up in this state. Nothing is guaranteed in this
**    state - the file may or may not be locked and the database size is
**    unknown. The database may not be read or written.
**
**    * No read or write transaction is active.
**    * Any lock, or no lock at all, may be held on the database file.
**    * The dbSize, dbOrigSize and dbFileSize variables may not be trusted.
**
**  READER:
**    In this state all the requirements for reading the database in 
**    rollback (non-WAL) mode are met. Unless the pager is (or recently
**    was) in exclusive-locking mode, a user-level read transaction is 
**    open. The database size is known in this state.
** 
**    * A read transaction may be active.
**    * A SHARED or greater lock is held on the database file.
**    * The dbSize variable may be trusted (even if a user-level read 
**      transaction is not active).

**
**  WRITER_INITIAL:
**    * A write transaction is active.
**    * A RESERVED or greater lock is held on the database file.
**    * The dbSize, dbOrigSize and dbFileSize variables are all valid.
**    * The contents of the pager cache have not been modified.
**

**    * A write transaction is active.
**    * An EXCLUSIVE or greater lock is held on the database file.
**    * All writing and syncing of journal and database data has finished.
**      If no error occured, all that remains is to finalize the journal to
**      commit the transaction. If an error did occur, the caller will need
**      to rollback the transaction. 
**




















** Allowable transitions and the [function] that performs each:
** 
**   NONE              -> READER              [PagerSharedLock]
**   READER            -> WRITER_INITIAL      [PagerBegin]
**   WRITER_INITIAL    -> WRITER_CACHEMOD     [pager_open_journal]
**   WRITER_CACHEMOD   -> WRITER_DBMOD        [syncJournal]
**   WRITER_DBMOD      -> WRITER_FINISHED     [PagerCommitPhaseOne]
** 

**   or SQLITE_FULL. Once one of the first three errors occurs, it persists
**   and is returned as the result of every major pager API call.  The
**   SQLITE_FULL return code is slightly different. It persists only until the
**   next successful rollback is performed on the pager cache. Also,
**   SQLITE_FULL does not affect the sqlite3PagerGet() and sqlite3PagerLookup()
**   APIs, they may still be used successfully.
**
** dbSizeValid, dbSize, dbOrigSize, dbFileSize
**
**   Managing the size of the database file in pages is a little complicated.
**   The variable Pager.dbSize contains the number of pages that the database
**   image currently contains. As the database image grows or shrinks this
**   variable is updated. The variable Pager.dbFileSize contains the number
**   of pages in the database file. This may be different from Pager.dbSize
**   if some pages have been appended to the database image but not yet written

  ** operates.
  **
  ** The 'state' variable is described in more detail along with the
  ** descriptions of the values it may take - PAGER_UNLOCK etc. Many of the
  ** other variables in this block are described in the comment directly 
  ** above this class definition.
  */
#if 0
  u8 state;                   /* PAGER_UNLOCK, _SHARED, _RESERVED, etc. */
  u8 dbModified;              /* True if there are any changes to the Db */
  u8 journalStarted;          /* True if header of journal is synced */
  u8 dbSizeValid;             /* Set when dbSize is correct */
#endif
  u8 eState;                  /* Pager state (NONE, READER, WRITER_INITIAL..) */
  u8 eLock;                   /* Current lock held on database file */

  u8 changeCountDone;         /* Set after incrementing the change-counter */
  u8 setMaster;               /* True if a m-j name has been written to jrnl */
  u8 doNotSpill;              /* Do not spill the cache when non-zero */
  u8 doNotSyncSpill;          /* Do not do a spill that requires jrnl sync */
  u8 subjInMemory;            /* True to use in-memory sub-journals */
  Pgno dbSize;                /* Number of pages in the database */
  Pgno dbOrigSize;            /* dbSize before the current transaction */

      assert( p->eLock>=SHARED_LOCK || p->noReadlock );
      break;

    case PAGER_WRITER_INITIAL:
      if( !pagerUseWal(pPager) ){
        assert( p->eLock>=RESERVED_LOCK );
      }


      break;

    case PAGER_WRITER_CACHEMOD:
      if( !pagerUseWal(pPager) ){
        /* It is possible that if journal_mode=wal here that neither the
        ** journal file nor the WAL file are open. This happens during
        ** a rollback transaction that switches from journal_mode=off
        ** to journal_mode=wal.
        */
        assert( p->eLock>=RESERVED_LOCK );
        assert( isOpen(p->jfd) 
             || p->journalMode==PAGER_JOURNALMODE_OFF 
             || p->journalMode==PAGER_JOURNALMODE_WAL 
        );
      }

      break;

    case PAGER_WRITER_DBMOD:
      assert( !pagerUseWal(pPager) );
      assert( p->eLock>=EXCLUSIVE_LOCK || pagerUseWal(pPager) );
      assert( isOpen(p->jfd) 
           || p->journalMode==PAGER_JOURNALMODE_OFF 

/*
** (gdb) printf "%s", print_pager_state(pPager)
*/
static char *print_pager_state(Pager *p){
  static char zRet[1024];

  sqlite3_snprintf(1024, zRet,
      "State: %s\n"
      "Lock:  %s\n"
      "Locking mode:  locking_mode=%s\n"

      "Backing store: tempFile=%d memDb=%d\n"
      , p->eState==PAGER_NONE            ? "NONE" :
        p->eState==PAGER_READER          ? "READER" :
        p->eState==PAGER_WRITER_INITIAL  ? "WRITER_INITIAL" :
        p->eState==PAGER_WRITER_CACHEMOD ? "WRITER_CACHEMOD" :
        p->eState==PAGER_WRITER_DBMOD    ? "WRITER_DBMOD" :
        p->eState==PAGER_WRITER_FINISHED ? "WRITER_FINISHED" : "?error?"
      , p->eLock==NO_LOCK         ? "NONE" :
        p->eLock==RESERVED_LOCK   ? "RESERVED" :
        p->eLock==EXCLUSIVE_LOCK  ? "EXCLUSIVE" :
        p->eLock==SHARED_LOCK     ? "SHARED" : "?error?"
      , p->exclusiveMode ? "exclusive" : "normal"






      , (int)p->tempFile, (int)p->memDb
  );

  return zRet;
}
#endif

/*

      }
    }
    nPage = (Pgno)(n / pPager->pageSize);
    if( nPage==0 && n>0 ){
      nPage = 1;
    }
  }









  *pnPage = nPage;
  return SQLITE_OK;
}


/*
** Check if the *-wal file that corresponds to the database opened by pPager

** Attempt to set the maximum database page count if mxPage is positive. 
** Make no changes if mxPage is zero or negative.  And never reduce the
** maximum page count below the current size of the database.
**
** Regardless of mxPage, return the current maximum page count.
*/
int sqlite3PagerMaxPageCount(Pager *pPager, int mxPage){
  int nPage;
  if( mxPage>0 ){
    pPager->mxPgno = mxPage;
  }
  if( pPager->eState!=PAGER_NONE ){
    sqlite3PagerPagecount(pPager, &nPage);
    assert( (int)pPager->mxPgno>=nPage );
  }
  return pPager->mxPgno;
}

/*
** The following set of routines are used to disable the simulated
** I/O error mechanism.  These routines are used to avoid simulated

      rc = SQLITE_OK;
    }
  }
  return rc;
}

/*

** Return the total number of pages in the database file associated 
** with pPager. Normally, this is calculated as (<db file size>/<page-size>).

** However, if the file is between 1 and <page-size> bytes in size, then 
** this is considered a 1 page file.
**
** If the pager is in error state when this function is called, then the
** error state error code is returned and *pnPage left unchanged. Or,
** if the file system has to be queried for the size of the file and
** the query attempt returns an IO error, the IO error code is returned
** and *pnPage is left unchanged.
**
** Otherwise, if everything is successful, then SQLITE_OK is returned
** and *pnPage is set to the number of pages in the database.
*/
int sqlite3PagerPagecount(Pager *pPager, int *pnPage){
  Pgno nPage = 0;           /* Value to return via *pnPage */

  assert( pPager->eState>=PAGER_SHARED );
  assert( pPager->eState!=PAGER_WRITER_FINISHED );

  /* Determine the number of pages in the file. Store this in nPage. */
  if( pPager->eState>PAGER_NONE ){
    nPage = pPager->dbSize;
  }else{
    int rc;                 /* Error returned by OsFileSize() */
    i64 n = 0;              /* File size in bytes returned by OsFileSize() */

    if( pagerUseWal(pPager) && pPager->eState!=PAGER_NONE ){
      nPage = sqlite3WalDbsize(pPager->pWal);
    }

    if( nPage==0 ){
      assert( isOpen(pPager->fd) || pPager->tempFile );
      if( isOpen(pPager->fd) ){
        if( SQLITE_OK!=(rc = sqlite3OsFileSize(pPager->fd, &n)) ){
          pager_error(pPager, rc);
          return rc;
        }
      }
      if( n>0 && n<pPager->pageSize ){
        nPage = 1;
      }else{
        nPage = (Pgno)(n / pPager->pageSize);
      }
    }
    if( pPager->eState!=PAGER_NONE ){
      pPager->dbSize = nPage;
      pPager->dbFileSize = nPage;
    }
  }

  /* If the current number of pages in the file is greater than the 
  ** configured maximum pager number, increase the allowed limit so
  ** that the file can be read.
  */
  if( nPage>pPager->mxPgno ){
    pPager->mxPgno = (Pgno)nPage;
  }

  /* Set the output variable and return SQLITE_OK */
  *pnPage = nPage;
  return SQLITE_OK;
}


static int pagerLock(Pager *pPager, int eLock){
  int rc;
  assert( eLock==SHARED_LOCK || eLock==RESERVED_LOCK || eLock==EXCLUSIVE_LOCK );

}

/*
** Sync the journal. In other words, make sure all the pages that have
** been written to the journal have actually reached the surface of the
** disk and can be restored in the event of a hot-journal rollback.
**
** If the Pager.noSync flag is set, then this function is a no-op. 
** Otherwise, the actions required depend on the journal-mode and the 
** device characteristics of the the file-system, as follows:
**
**   * If the journal file is an in-memory journal file, no action need
**     be taken.
**
**   * Otherwise, if the device does not support the SAFE_APPEND property,

**     if( NOT SEQUENTIAL ) xSync(<journal file>);
**   }
**
** If successful, this routine clears the PGHDR_NEED_SYNC flag of every 
** page currently held in memory before returning SQLITE_OK. If an IO
** error is encountered, then the IO error code is returned to the caller.
*/
static int syncJournal(Pager *pPager){
  int rc;                         /* Return code */

  assert( pPager->eState==PAGER_WRITER_CACHEMOD
       || pPager->eState==PAGER_WRITER_DBMOD
  );
  assert( assert_pager_state(pPager) );


  rc = sqlite3PagerExclusiveLock(pPager);
  if( rc!=SQLITE_OK ) return rc;

  if( !pPager->noSync ){
    assert( !pPager->tempFile );
    if( isOpen(pPager->jfd) && pPager->journalMode!=PAGER_JOURNALMODE_MEMORY ){

        PAGERTRACE(("SYNC journal of %d\n", PAGERID(pPager)));
        IOTRACE(("JSYNC %p\n", pPager))
        rc = sqlite3OsSync(pPager->jfd, pPager->sync_flags| 
          (pPager->sync_flags==SQLITE_SYNC_FULL?SQLITE_SYNC_DATAONLY:0)
        );
        if( rc!=SQLITE_OK ) return rc;
      }
    }






    pPager->journalHdr = pPager->journalOff;

  }

  /* Unless the pager is in noSync mode, the journal file was just 
  ** successfully synced. Either way, clear the PGHDR_NEED_SYNC flag on 
  ** all pages.
  */
  sqlite3PcacheClearSyncFlags(pPager->pPCache);

  ** However it may be called in WRITER_CACHEMOD state if the page being
  ** written (and all other pages that reside on the same disk sector) was
  ** a free-list leaf page at the start of the transaction. In that case
  ** the database file is not really being modified, so it is Ok to write
  ** to it in CACHEMOD state.
  */
  assert( !pagerUseWal(pPager) );
  assert( pPager->eState==PAGER_WRITER_CACHEMOD
       || pPager->eState==PAGER_WRITER_DBMOD 
  );
  assert( pPager->eState==PAGER_WRITER_DBMOD || pList->pDirty==0 );



  rc = pager_wait_on_lock(pPager, EXCLUSIVE_LOCK);

  /* If the file is a temp-file has not yet been opened, open it now. It
  ** is not possible for rc to be other than SQLITE_OK if this branch
  ** is taken, as pager_wait_on_lock() is a no-op for temp-files.
  */

    if( rc==SQLITE_OK ){
      rc = pagerWalFrames(pPager, pPg, 0, 0, 0);
    }
  }else{
  
    /* Sync the journal file if required. */
    if( pPg->flags&PGHDR_NEED_SYNC ){
      rc = syncJournal(pPager);
      if( rc==SQLITE_OK && 
        !pPager->noSync &&
        !(pPager->journalMode==PAGER_JOURNALMODE_MEMORY) &&
        !(sqlite3OsDeviceCharacteristics(pPager->fd)&SQLITE_IOCAP_SAFE_APPEND)
      ){
        pPager->nRec = 0;
        rc = writeJournalHdr(pPager);
      }
    }
  
    /* If the page number of this page is larger than the current size of
    ** the database image, it may need to be written to the sub-journal.
    ** This is because the call to pager_write_pagelist() below will not
    ** actually write data to the file in this case.
    **

    assert( pgno<=PAGER_MAX_PGNO && pgno!=PAGER_MJ_PGNO(pPager) );
    PAGER_INCR(pPager->nHit);
    return SQLITE_OK;

  }else{
    /* The pager cache has created a new page. Its content needs to 
    ** be initialized.  */
    int nMax;

    PAGER_INCR(pPager->nMiss);
    pPg = *ppPage;
    pPg->pPager = pPager;

    /* The maximum page number is 2^31. Return SQLITE_CORRUPT if a page
    ** number greater than this, or the unused locking-page, is requested. */
    if( pgno>PAGER_MAX_PGNO || pgno==PAGER_MJ_PGNO(pPager) ){
      rc = SQLITE_CORRUPT_BKPT;
      goto pager_acquire_err;
    }

    rc = sqlite3PagerPagecount(pPager, &nMax);
    if( rc!=SQLITE_OK ){
      goto pager_acquire_err;
    }

    if( MEMDB || nMax<(int)pgno || noContent || !isOpen(pPager->fd) ){
      if( pgno>pPager->mxPgno ){
        rc = SQLITE_FULL;
        goto pager_acquire_err;
      }
      if( noContent ){
        /* Failure to set the bits in the InJournal bit-vectors is benign.
        ** It merely means that we might do some extra work to journal a 

**
** Return SQLITE_OK if everything is successful. Otherwise, return 
** SQLITE_NOMEM if the attempt to allocate Pager.pInJournal fails, or 
** an IO error code if opening or writing the journal file fails.
*/
static int pager_open_journal(Pager *pPager){
  int rc = SQLITE_OK;                        /* Return code */
  int nPage;                                 /* Size of database file */
  sqlite3_vfs * const pVfs = pPager->pVfs;   /* Local cache of vfs pointer */

  assert( pPager->eState==PAGER_WRITER_INITIAL );
  assert( assert_pager_state(pPager) );
  assert( pPager->pInJournal==0 );
  
  /* If already in the error state, this function is a no-op.  But on
  ** the other hand, this routine is never called if we are already in
  ** an error state. */
  if( NEVER(pPager->errCode) ) return pPager->errCode;

  if( !pagerUseWal(pPager) && pPager->journalMode!=PAGER_JOURNALMODE_OFF ){
    rc = sqlite3PagerPagecount(pPager, &nPage);
    if( rc ) return rc;
    pPager->pInJournal = sqlite3BitvecCreate(nPage);
    if( pPager->pInJournal==0 ){
      return SQLITE_NOMEM;
    }
  
    /* Open the journal file if it is not already open. */
    if( !isOpen(pPager->jfd) ){
      if( pPager->journalMode==PAGER_JOURNALMODE_MEMORY ){

  
  
    /* Write the first journal header to the journal file and open 
    ** the sub-journal if necessary.
    */
    if( rc==SQLITE_OK ){
      /* TODO: Check if all of these are really required. */
      pPager->dbOrigSize = pPager->dbSize;
      pPager->nRec = 0;
      pPager->journalOff = 0;
      pPager->setMaster = 0;
      pPager->journalHdr = 0;
      rc = writeJournalHdr(pPager);
    }
  }

  if( rc!=SQLITE_OK ){
    sqlite3BitvecDestroy(pPager->pInJournal);
    pPager->pInJournal = 0;
  }else{

    pPager->eState = PAGER_WRITER_CACHEMOD;
  }

  return rc;
}

/*

      ** when it has an open transaction, but never to DBMOD or FINISHED.
      ** This is because in those states the code to roll back savepoint 
      ** transactions may copy data from the sub-journal into the database 
      ** file as well as into the page cache. Which would be incorrect in 
      ** WAL mode.
      */
      pPager->eState = PAGER_WRITER_INITIAL;
      pPager->dbOrigSize = pPager->dbSize;
      pPager->journalOff = 0;
    }else{
      /* Ignore any IO error that occurs within pager_end_transaction(). The
      ** purpose of this call is to reset the internal state of the pager
      ** sub-system. It doesn't matter if the journal-file is not properly
      ** finalized at this point (since it is not a valid journal file anyway).
      */

    ** yet be open. Open it now if this is the case.
    */
    if( pPager->eState==PAGER_WRITER_INITIAL ){
      rc = pager_open_journal(pPager);
      if( rc!=SQLITE_OK ) return rc;
    }
    assert( pPager->eState>=PAGER_WRITER_CACHEMOD );

  
    /* The transaction journal now exists and we have a RESERVED or an
    ** EXCLUSIVE lock on the main database file.  Write the current page to
    ** the transaction journal if it is not there already.
    */
    if( !pageInJournal(pPg) && isOpen(pPager->jfd) ){
      assert( !pagerUseWal(pPager) );
      if( pPg->pgno<=pPager->dbOrigSize ){
        u32 cksum;
        char *pData2;

        /* We should never write to the journal file the page that
        ** contains the database locks.  The following assert verifies
        ** that we do not. */
        assert( pPg->pgno!=PAGER_MJ_PGNO(pPager) );

        /* Even if an IO or diskfull error occurred while journalling the
        ** page in the block above, set the need-sync flag for the page.
        ** Otherwise, when the transaction is rolled back, the logic in
        ** playback_one_page() will think that the page needs to be restored
        ** in the database file. And if an IO error occurs while doing so,
        ** then corruption may follow.
        */
        if( 1 || !pPager->noSync ){
          pPg->flags |= PGHDR_NEED_SYNC;
        }

        /* An error has occurred writing to the journal file. The 
        ** transaction will be rolled back by the layer above.
        */
        if( rc!=SQLITE_OK ){
          return rc;
        }

        pPager->nRec++;
        assert( pPager->pInJournal!=0 );
        rc = sqlite3BitvecSet(pPager->pInJournal, pPg->pgno);
        testcase( rc==SQLITE_NOMEM );
        assert( rc==SQLITE_OK || rc==SQLITE_NOMEM );
        rc |= addToSavepointBitvecs(pPager, pPg->pgno);
        if( rc!=SQLITE_OK ){
          assert( rc==SQLITE_NOMEM );
          return rc;
        }
      }else{
        if( pPager->eState!=PAGER_WRITER_DBMOD && (!pPager->noSync || 1)){
          pPg->flags |= PGHDR_NEED_SYNC;
        }
        PAGERTRACE(("APPEND %d page %d needSync=%d\n",
                PAGERID(pPager), pPg->pgno,
               ((pPg->flags&PGHDR_NEED_SYNC)?1:0)));
      }
    }

int sqlite3PagerWrite(DbPage *pDbPage){
  int rc = SQLITE_OK;

  PgHdr *pPg = pDbPage;
  Pager *pPager = pPg->pPager;
  Pgno nPagePerSector = (pPager->sectorSize/pPager->pageSize);




  if( nPagePerSector>1 ){
    Pgno nPageCount;          /* Total number of pages in database file */
    Pgno pg1;                 /* First page of the sector pPg is located on. */
    int nPage = 0;            /* Number of pages starting at pg1 to journal */
    int ii;                   /* Loop counter */
    int needSync = 0;         /* True if any page has PGHDR_NEED_SYNC */

    /* This trick assumes that both the page-size and sector-size are
    ** an integer power of 2. It sets variable pg1 to the identifier
    ** of the first page of the sector pPg is located on.
    */
    pg1 = ((pPg->pgno-1) & ~(nPagePerSector-1)) + 1;

    rc = sqlite3PagerPagecount(pPager, (int *)&nPageCount);
    if( rc==SQLITE_OK ){
      if( pPg->pgno>nPageCount ){
        nPage = (pPg->pgno - pg1)+1;
      }else if( (pg1+nPagePerSector-1)>nPageCount ){
        nPage = nPageCount+1-pg1;
      }else{
        nPage = nPagePerSector;
      }
      assert(nPage>0);
      assert(pg1<=pPg->pgno);
      assert((pg1+nPage)>pPg->pgno);
    }

    for(ii=0; ii<nPage && rc==SQLITE_OK; ii++){
      Pgno pg = pg1+ii;
      PgHdr *pPage;
      if( pg==pPg->pgno || !sqlite3BitvecTest(pPager->pInJournal, pg) ){
        if( pg!=PAGER_MJ_PGNO(pPager) ){
          rc = sqlite3PagerGet(pPager, pg, &pPage);

      ** Because the change-counter page was just modified, unless the
      ** atomic-update optimization is used it is almost certain that the
      ** journal requires a sync here. However, in locking_mode=exclusive
      ** on a system under memory pressure it is just possible that this is 
      ** not the case. In this case it is likely enough that the redundant
      ** xSync() call will be changed to a no-op by the OS anyhow. 
      */
      rc = syncJournal(pPager);
      if( rc!=SQLITE_OK ) goto commit_phase_one_exit;

      rc = pager_write_pagelist(pPager,sqlite3PcacheDirtyList(pPager->pPCache));
      if( rc!=SQLITE_OK ){
        assert( rc!=SQLITE_IOERR_BLOCKED );
        goto commit_phase_one_exit;
      }

** If a memory allocation fails, SQLITE_NOMEM is returned. If an error 
** occurs while opening the sub-journal file, then an IO error code is
** returned. Otherwise, SQLITE_OK.
*/
int sqlite3PagerOpenSavepoint(Pager *pPager, int nSavepoint){
  int rc = SQLITE_OK;                       /* Return code */
  int nCurrent = pPager->nSavepoint;        /* Current number of savepoints */




  if( nSavepoint>nCurrent && pPager->useJournal ){
    int ii;                                 /* Iterator variable */
    PagerSavepoint *aNew;                   /* New Pager.aSavepoint array */
    int nPage;                              /* Size of database file */

    rc = sqlite3PagerPagecount(pPager, &nPage);
    if( rc ) return rc;

    /* Grow the Pager.aSavepoint array using realloc(). Return SQLITE_NOMEM
    ** if the allocation fails. Otherwise, zero the new portion in case a 
    ** malloc failure occurs while populating it in the for(...) loop below.
    */
    aNew = (PagerSavepoint *)sqlite3Realloc(
        pPager->aSavepoint, sizeof(PagerSavepoint)*nSavepoint
    );
    if( !aNew ){
      return SQLITE_NOMEM;
    }
    memset(&aNew[nCurrent], 0, (nSavepoint-nCurrent) * sizeof(PagerSavepoint));
    pPager->aSavepoint = aNew;

    /* Populate the PagerSavepoint structures just allocated. */
    for(ii=nCurrent; ii<nSavepoint; ii++){
      aNew[ii].nOrig = nPage;
      if( isOpen(pPager->jfd) && pPager->journalOff>0 ){
        aNew[ii].iOffset = pPager->journalOff;
      }else{
        aNew[ii].iOffset = JOURNAL_HDR_SZ(pPager);
      }
      aNew[ii].iSubRec = pPager->nSubRec;
      aNew[ii].pInSavepoint = sqlite3BitvecCreate(nPage);
      if( !aNew[ii].pInSavepoint ){
        return SQLITE_NOMEM;
      }
      if( pagerUseWal(pPager) ){
        sqlite3WalSavepoint(pPager->pWal, aNew[ii].aWalData);
      }
      pPager->nSavepoint = ii+1;