SQLite

}
static void cfShmBarrier(sqlite3_file *pFile){
  sqlite3OsShmBarrier(((CrashFile*)pFile)->pRealFile);
}
static int cfShmClose(sqlite3_file *pFile, int delFlag){
  return sqlite3OsShmClose(((CrashFile*)pFile)->pRealFile, delFlag);
}
static int cfShmPage(
  sqlite3_file *pFile,            /* Handle open on database file */
  int iPage,                      /* Page to retrieve */
  int pgsz,                       /* Size of pages */
  int w,                          /* True to extend file if necessary */
  void volatile **pp              /* OUT: Mapped memory */
){
  return sqlite3OsShmPage(((CrashFile*)pFile)->pRealFile, iPage, pgsz, w, pp);
}


static const sqlite3_io_methods CrashFileVtab = {
  2,                            /* iVersion */
  cfClose,                      /* xClose */
  cfRead,                       /* xRead */
  cfWrite,                      /* xWrite */

  cfDeviceCharacteristics,      /* xDeviceCharacteristics */
  cfShmOpen,                    /* xShmOpen */
  cfShmSize,                    /* xShmSize */
  cfShmGet,                     /* xShmGet */
  cfShmRelease,                 /* xShmRelease */
  cfShmLock,                    /* xShmLock */
  cfShmBarrier,                 /* xShmBarrier */
  cfShmClose,                   /* xShmClose */
  cfShmPage                     /* xShmPage */
};

/*
** Application data for the crash VFS
*/
struct crashAppData {
  sqlite3_vfs *pOrig;                   /* Wrapped vfs structure */

  char *zWalName;            /* Name of WAL file */
  u32 nCkpt;                 /* Checkpoint sequence counter in the wal-header */
#ifdef SQLITE_DEBUG
  u8 lockError;              /* True if a locking error has occurred */
#endif
};

/*
** Each page of the wal-index mapping contains a hash-table made up of
** an array of HASHTABLE_NSLOT elements of the following type.
*/
typedef u16 ht_slot;

/*
** Define the parameters of the hash tables in the wal-index file. There
** is a hash-table following every HASHTABLE_NPAGE page numbers in the
** wal-index.
**
** Changing any of these constants will alter the wal-index format and
** create incompatibilities.
*/

#define HASHTABLE_NPAGE      4096                 /* Must be power of 2 */
#define HASHTABLE_HASH_1     383                  /* Should be prime */
#define HASHTABLE_NSLOT      (HASHTABLE_NPAGE*2)  /* Must be a power of 2 */


/* The block of page numbers associated with the first hash-table in a
** wal-index is smaller than usual. This is so that there is a complete
** hash-table on each aligned 32KB page of the wal-index.
*/
#define HASHTABLE_NPAGE_ONE  (HASHTABLE_NPAGE - (WALINDEX_HDR_SIZE/sizeof(u32)))

/* The wal-index is divided into pages of WALINDEX_PGSZ bytes each. */
#define WALINDEX_PGSZ   (                                         \
    sizeof(ht_slot)*HASHTABLE_NSLOT + HASHTABLE_NPAGE*sizeof(u32) \
)

/*
** Obtain a pointer to the iPage'th page of the wal-index. The wal-index
** is broken into pages of WALINDEX_PGSZ bytes. Wal-index pages are
** numbered from zero.
**
** If this call is successful, *ppPage is set to point to the wal-index
** page and SQLITE_OK is returned. If an error (an OOM or VFS error) occurs,
** then an SQLite error code is returned and *ppPage is set to 0.
*/
static int walIndexPage(Wal *pWal, int iPage, volatile u32 **ppPage){

    memset(&apNew[pWal->nWiData], 0, sizeof(u32 *)*(iPage+1-pWal->nWiData));
    pWal->apWiData = apNew;
    pWal->nWiData = iPage+1;
  }

  /* Request a pointer to the required page from the VFS */
  if( pWal->apWiData[iPage]==0 ){
    rc = sqlite3OsShmPage(pWal->pDbFd, iPage, WALINDEX_PGSZ, 
        pWal->writeLock, (void volatile **)&pWal->apWiData[iPage]
    );
  }

  *ppPage = pWal->apWiData[iPage];
  assert( iPage==0 || *ppPage || rc!=SQLITE_OK );
  return rc;

**   walIteratorInit() - Create a new iterator,
**   walIteratorNext() - Step an iterator,
**   walIteratorFree() - Free an iterator.
**
** This functionality is used by the checkpoint code (see walCheckpoint()).
*/
struct WalIterator {
  int iPrior;                     /* Last result returned from the iterator */
  int nSegment;                   /* Size of the aSegment[] array */
  struct WalSegment {
    int iNext;                    /* Next slot in aIndex[] not yet returned */
    ht_slot *aIndex;              /* i0, i1, i2... such that aPgno[iN] ascend */
    u32 *aPgno;                   /* Array of page numbers. */
    int nEntry;                   /* Max size of aPgno[] and aIndex[] arrays */
    int iZero;                    /* Frame number associated with aPgno[0] */
  } aSegment[1];                  /* One for every 32KB page in the WAL */
};

/*
** The argument to this macro must be of type u32. On a little-endian
** architecture, it returns the u32 value that results from interpreting
** the 4 bytes as a big-endian value. On a big-endian architecture, it
** returns the value that would be produced by intepreting the 4 bytes

** Finally, set *paPgno such that for all frames F between (*piZero+1) and 
** (*piZero+HASHTABLE_NPAGE), (*paPgno)[F] is the database page number 
** associated with frame F.
*/
static int walHashGet(
  Wal *pWal,                      /* WAL handle */
  int iHash,                      /* Find the iHash'th table */
  volatile ht_slot **paHash,      /* OUT: Pointer to hash index */
  volatile u32 **paPgno,          /* OUT: Pointer to page number array */
  u32 *piZero                     /* OUT: Frame associated with *paPgno[0] */
){
  int rc;                         /* Return code */
  volatile u32 *aPgno;

  rc = walIndexPage(pWal, iHash, &aPgno);
  assert( rc==SQLITE_OK || iHash>0 );

  if( rc==SQLITE_OK ){
    u32 iZero;
    volatile ht_slot *aHash;

    aHash = (volatile ht_slot *)&aPgno[HASHTABLE_NPAGE];
    if( iHash==0 ){
      aPgno = &aPgno[WALINDEX_HDR_SIZE/sizeof(u32)-1];
      iZero = 0;
    }else{
      iZero = HASHTABLE_NPAGE_ONE + (iHash-1)*HASHTABLE_NPAGE;
      aPgno = &aPgno[-1*iZero-1];
    }

**
** At most only the hash table containing pWal->hdr.mxFrame needs to be
** updated.  Any later hash tables will be automatically cleared when
** pWal->hdr.mxFrame advances to the point where those hash tables are
** actually needed.
*/
static void walCleanupHash(Wal *pWal){
  volatile ht_slot *aHash;        /* Pointer to hash table to clear */
  volatile u32 *aPgno;            /* Page number array for hash table */
  u32 iZero;                      /* frame == (aHash[x]+iZero) */
  int iLimit = 0;                 /* Zero values greater than this */
  int nByte;                      /* Number of bytes to zero in aPgno[] */
  int i;                          /* Used to iterate through aHash[] */

  assert( pWal->writeLock );
  testcase( pWal->hdr.mxFrame==HASHTABLE_NPAGE-1 );
  testcase( pWal->hdr.mxFrame==HASHTABLE_NPAGE );
  testcase( pWal->hdr.mxFrame==HASHTABLE_NPAGE+1 );

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

** Set an entry in the wal-index that will map database page number
** pPage into WAL frame iFrame.
*/
static int walIndexAppend(Wal *pWal, u32 iFrame, u32 iPage){
  int rc;                         /* Return code */
  u32 iZero;                      /* One less than frame number of aPgno[1] */
  volatile u32 *aPgno;            /* Page number array */
  volatile ht_slot *aHash;        /* Hash table */

  rc = walHashGet(pWal, walFramePage(iFrame), &aHash, &aPgno, &iZero);

  /* Assuming the wal-index file was successfully mapped, populate the
  ** page number array and hash table entry.
  */
  if( rc==SQLITE_OK ){

  *piPage = p->iPrior = iRet;
  return (iRet==0xFFFFFFFF);
}


static void walMergesort(
  u32 *aContent,                  /* Pages in wal */
  ht_slot *aBuffer,               /* Buffer of at least *pnList items to use */
  ht_slot *aList,                 /* IN/OUT: List to sort */
  int *pnList                     /* IN/OUT: Number of elements in aList[] */
){
  int nList = *pnList;
  if( nList>1 ){
    int nLeft = nList / 2;        /* Elements in left list */
    int nRight = nList - nLeft;   /* Elements in right list */
    int iLeft = 0;                /* Current index in aLeft */
    int iRight = 0;               /* Current index in aright */
    int iOut = 0;                 /* Current index in output buffer */
    ht_slot *aLeft = aList;       /* Left list */
    ht_slot *aRight = aList+nLeft;/* Right list */

    /* TODO: Change to non-recursive version. */
    walMergesort(aContent, aBuffer, aLeft, &nLeft);
    walMergesort(aContent, aBuffer, aRight, &nRight);

    while( iRight<nRight || iLeft<nLeft ){
      ht_slot logpage;
      Pgno dbpage;

      if( (iLeft<nLeft) 
       && (iRight>=nRight || aContent[aLeft[iLeft]]<aContent[aRight[iRight]])
      ){
        logpage = aLeft[iLeft++];
      }else{

**
** The calling routine should invoke walIteratorFree() to destroy the
** WalIterator object when it has finished with it.  The caller must
** also unmap the wal-index.  But the wal-index must not be unmapped
** prior to the WalIterator object being destroyed.
*/
static int walIteratorInit(Wal *pWal, WalIterator **pp){
  WalIterator *p;                 /* Return value */
  int nSegment;                   /* Number of segments to merge */
  u32 iLast;                      /* Last frame in log */
  int nByte;                      /* Number of bytes to allocate */
  int i;                          /* Iterator variable */
  ht_slot *aTmp;                  /* Temp space used by merge-sort */
  ht_slot *aSpace;                /* Space at the end of the allocation */

  /* This routine only runs while holding SQLITE_SHM_CHECKPOINT.  No other
  ** thread is able to write to shared memory while this routine is
  ** running (or, indeed, while the WalIterator object exists).  Hence,
  ** we can cast off the volatile qualification from shared memory
  */
  assert( pWal->ckptLock );
  iLast = pWal->hdr.mxFrame;

  /* Allocate space for the WalIterator object */
  nSegment = walFramePage(iLast) + 1;
  nByte = sizeof(WalIterator) 
        + nSegment*(sizeof(struct WalSegment))
        + (nSegment+1)*(HASHTABLE_NPAGE * sizeof(ht_slot));
  p = (WalIterator *)sqlite3_malloc(nByte);
  if( !p ){
    return SQLITE_NOMEM;
  }
  memset(p, 0, nByte);

  /* Allocate space for the WalIterator object */
  p->nSegment = nSegment;
  aSpace = (ht_slot *)&p->aSegment[nSegment];
  aTmp = &aSpace[HASHTABLE_NPAGE*nSegment];
  for(i=0; i<nSegment; i++){
    volatile ht_slot *aHash;
    int j;
    u32 iZero;
    int nEntry;
    volatile u32 *aPgno;
    int rc;

    rc = walHashGet(pWal, i, &aHash, &aPgno, &iZero);

  **     This condition filters out normal hash-table collisions.
  **
  **   (iFrame<=iLast): 
  **     This condition filters out entries that were added to the hash
  **     table after the current read-transaction had started.
  */
  for(iHash=walFramePage(iLast); iHash>=0 && iRead==0; iHash--){
    volatile ht_slot *aHash;      /* Pointer to hash table */
    volatile u32 *aPgno;          /* Pointer to array of page numbers */
    u32 iZero;                    /* Frame number corresponding to aPgno[0] */
    int iKey;                     /* Hash slot index */
    int rc;

    rc = walHashGet(pWal, iHash, &aHash, &aPgno, &iZero);
    if( rc!=SQLITE_OK ){
      return rc;

**
** Otherwise, if the callback function does not return an error, this
** function returns SQLITE_OK.
*/
int sqlite3WalUndo(Wal *pWal, int (*xUndo)(void *, Pgno), void *pUndoCtx){
  int rc = SQLITE_OK;
  if( pWal->writeLock ){

    Pgno iMax = pWal->hdr.mxFrame;
    Pgno iFrame;
  
    /* Restore the clients cache of the wal-index header to the state it
    ** was in before the client began writing to the database. 
    */
    memcpy(&pWal->hdr, (void *)walIndexHdr(pWal), sizeof(WalIndexHdr));

    for(iFrame=pWal->hdr.mxFrame+1; 
        ALWAYS(rc==SQLITE_OK) && iFrame<=iMax; 
        iFrame++
    ){
      /* This call cannot fail. Unless the page for which the page number
      ** is passed as the second argument is (a) in the cache and 
      ** (b) has an outstanding reference, then xUndo is either a no-op
      ** (if (a) is false) or simply expels the page from the cache (if (b)
      ** is false).
      **
      ** If the upper layer is doing a rollback, it is guaranteed that there
      ** are no outstanding references to any page other than page 1. And
      ** page 1 is never written to the log until the transaction is
      ** committed. As a result, the call to xUndo may not fail.
      */

      assert( walFramePgno(pWal, iFrame)!=1 );
      rc = xUndo(pUndoCtx, walFramePgno(pWal, iFrame));
    }
    walCleanupHash(pWal);
  }
  assert( rc==SQLITE_OK );
  return rc;