数据库系统

开发平台：

C/C++

btree.c.svn-base：源码内容

/*
** 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 1.451 2008/04/03 21:46:57 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"
/*
** The header string that appears at the beginning of every
** SQLite database.
*/
static const char zMagicHeader[] = SQLITE_FILE_HEADER;
/*
** Set this global variable to 1 to enable tracing using the TRACE
** macro.
*/
#if SQLITE_TEST
int sqlite3BtreeTrace=0; /* True to enable tracing */
#endif
#ifndef SQLITE_OMIT_SHARED_CACHE
/*
** A flag to indicate whether or not shared cache is enabled. Also,
** a list of BtShared objects that are eligible for participation
** in shared cache. The variables have file scope during normal builds,
** but the test harness needs to access these variables so we make them
** global for test builds.
*/
#ifdef SQLITE_TEST
BtShared *sqlite3SharedCacheList = 0;
int sqlite3SharedCacheEnabled = 0;
#else
static BtShared *sqlite3SharedCacheList = 0;
static int sqlite3SharedCacheEnabled = 0;
#endif
#endif /* SQLITE_OMIT_SHARED_CACHE */
#ifndef SQLITE_OMIT_SHARED_CACHE
/*
** Enable or disable the shared pager and schema features.
**
** This routine has no effect on existing database connections.
** The shared cache setting effects only future calls to
** sqlite3_open(), sqlite3_open16(), or sqlite3_open_v2().
*/
int sqlite3_enable_shared_cache(int enable){
sqlite3SharedCacheEnabled = enable;
return SQLITE_OK;
}
#endif
/*
** Forward declaration
*/
static int checkReadLocks(Btree*,Pgno,BtCursor*);
#ifdef SQLITE_OMIT_SHARED_CACHE
/*
** The functions queryTableLock(), lockTable() and unlockAllTables()
** manipulate entries in the BtShared.pLock linked list used to store
** shared-cache table level locks. If the library is compiled with the
** shared-cache feature disabled, then there is only ever one user
** of each BtShared structure and so this locking is not necessary.
** So define the lock related functions as no-ops.
*/
#define queryTableLock(a,b,c) SQLITE_OK
#define lockTable(a,b,c) SQLITE_OK
#define unlockAllTables(a)
#endif
#ifndef SQLITE_OMIT_SHARED_CACHE
/*
** Query to see if btree handle p may obtain a lock of type eLock
** (READ_LOCK or WRITE_LOCK) on the table with root-page iTab. Return
** SQLITE_OK if the lock may be obtained (by calling lockTable()), or
** SQLITE_LOCKED if not.
*/
static int queryTableLock(Btree *p, Pgno iTab, u8 eLock){
BtShared *pBt = p->pBt;
BtLock *pIter;
assert( sqlite3BtreeHoldsMutex(p) );
/* This is a no-op if the shared-cache is not enabled */
if( !p->sharable ){
return SQLITE_OK;
}
/* If some other connection is holding an exclusive lock, the
** requested lock may not be obtained.
*/
if( pBt->pExclusive && pBt->pExclusive!=p ){
return SQLITE_LOCKED;
}
/* This (along with lockTable()) is where the ReadUncommitted flag is
** dealt with. If the caller is querying for a read-lock and the flag is
** set, it is unconditionally granted - even if there are write-locks
** on the table. If a write-lock is requested, the ReadUncommitted flag
** is not considered.
**
** In function lockTable(), if a read-lock is demanded and the
** ReadUncommitted flag is set, no entry is added to the locks list
** (BtShared.pLock).
**
** To summarize: If the ReadUncommitted flag is set, then read cursors do
** not create or respect table locks. The locking procedure for a
** write-cursor does not change.
*/
if(
!p->db ||
0==(p->db->flags&SQLITE_ReadUncommitted) ||
eLock==WRITE_LOCK ||
iTab==MASTER_ROOT
){
for(pIter=pBt->pLock; pIter; pIter=pIter->pNext){
if( pIter->pBtree!=p && pIter->iTable==iTab &&
(pIter->eLock!=eLock || eLock!=READ_LOCK) ){
return SQLITE_LOCKED;
}
}
}
return SQLITE_OK;
}
#endif /* !SQLITE_OMIT_SHARED_CACHE */
#ifndef SQLITE_OMIT_SHARED_CACHE
/*
** Add a lock on the table with root-page iTable to the shared-btree used
** by Btree handle p. Parameter eLock must be either READ_LOCK or
** WRITE_LOCK.
**
** SQLITE_OK is returned if the lock is added successfully. SQLITE_BUSY and
** SQLITE_NOMEM may also be returned.
*/
static int lockTable(Btree *p, Pgno iTable, u8 eLock){
BtShared *pBt = p->pBt;
BtLock *pLock = 0;
BtLock *pIter;
assert( sqlite3BtreeHoldsMutex(p) );
/* This is a no-op if the shared-cache is not enabled */
if( !p->sharable ){
return SQLITE_OK;
}
assert( SQLITE_OK==queryTableLock(p, iTable, eLock) );
/* If the read-uncommitted flag is set and a read-lock is requested,
** return early without adding an entry to the BtShared.pLock list. See
** comment in function queryTableLock() for more info on handling
** the ReadUncommitted flag.
*/
if(
(p->db) &&
(p->db->flags&SQLITE_ReadUncommitted) &&
(eLock==READ_LOCK) &&
iTable!=MASTER_ROOT
){
return SQLITE_OK;
}
/* First search the list for an existing lock on this table. */
for(pIter=pBt->pLock; pIter; pIter=pIter->pNext){
if( pIter->iTable==iTable && pIter->pBtree==p ){
pLock = pIter;
break;
}
}
/* If the above search did not find a BtLock struct associating Btree p
** with table iTable, allocate one and link it into the list.
*/
if( !pLock ){
pLock = (BtLock *)sqlite3MallocZero(sizeof(BtLock));
if( !pLock ){
return SQLITE_NOMEM;
}
pLock->iTable = iTable;
pLock->pBtree = p;
pLock->pNext = pBt->pLock;
pBt->pLock = pLock;
}
/* Set the BtLock.eLock variable to the maximum of the current lock
** and the requested lock. This means if a write-lock was already held
** and a read-lock requested, we don't incorrectly downgrade the lock.
*/
assert( WRITE_LOCK>READ_LOCK );
if( eLock>pLock->eLock ){
pLock->eLock = eLock;
}
return SQLITE_OK;
}
#endif /* !SQLITE_OMIT_SHARED_CACHE */
#ifndef SQLITE_OMIT_SHARED_CACHE
/*
** Release all the table locks (locks obtained via calls to the lockTable()
** procedure) held by Btree handle p.
*/
static void unlockAllTables(Btree *p){
BtShared *pBt = p->pBt;
BtLock **ppIter = &pBt->pLock;
assert( sqlite3BtreeHoldsMutex(p) );
assert( p->sharable || 0==*ppIter );
while( *ppIter ){
BtLock *pLock = *ppIter;
assert( pBt->pExclusive==0 || pBt->pExclusive==pLock->pBtree );
if( pLock->pBtree==p ){
*ppIter = pLock->pNext;
sqlite3_free(pLock);
}else{
ppIter = &pLock->pNext;
}
}
if( pBt->pExclusive==p ){
pBt->pExclusive = 0;
}
}
#endif /* SQLITE_OMIT_SHARED_CACHE */
static void releasePage(MemPage *pPage); /* Forward reference */
/*
** Verify that the cursor holds a mutex on the BtShared
*/
#ifndef NDEBUG
static int cursorHoldsMutex(BtCursor *p){
return sqlite3_mutex_held(p->pBt->mutex);
}
#endif
#ifndef SQLITE_OMIT_INCRBLOB
/*
** Invalidate the overflow page-list cache for cursor pCur, if any.
*/
static void invalidateOverflowCache(BtCursor *pCur){
assert( cursorHoldsMutex(pCur) );
sqlite3_free(pCur->aOverflow);
pCur->aOverflow = 0;
}
/*
** Invalidate the overflow page-list cache for all cursors opened
** on the shared btree structure pBt.
*/
static void invalidateAllOverflowCache(BtShared *pBt){
BtCursor *p;
assert( sqlite3_mutex_held(pBt->mutex) );
for(p=pBt->pCursor; p; p=p->pNext){
invalidateOverflowCache(p);
}
}
#else
#define invalidateOverflowCache(x)
#define invalidateAllOverflowCache(x)
#endif
/*
** Save the current cursor position in the variables BtCursor.nKey
** and BtCursor.pKey. The cursor's state is set to CURSOR_REQUIRESEEK.
*/
static int saveCursorPosition(BtCursor *pCur){
int rc;
assert( CURSOR_VALID==pCur->eState );
assert( 0==pCur->pKey );
assert( cursorHoldsMutex(pCur) );
rc = sqlite3BtreeKeySize(pCur, &pCur->nKey);
/* If this is an intKey table, then the above call to BtreeKeySize()
** stores the integer key in pCur->nKey. In this case this value is
** all that is required. Otherwise, if pCur is not open on an intKey
** table, then malloc space for and store the pCur->nKey bytes of key
** data.
*/
if( rc==SQLITE_OK && 0==pCur->pPage->intKey){
void *pKey = sqlite3_malloc(pCur->nKey);
if( pKey ){
rc = sqlite3BtreeKey(pCur, 0, pCur->nKey, pKey);
if( rc==SQLITE_OK ){
pCur->pKey = pKey;
}else{
sqlite3_free(pKey);
}
}else{
rc = SQLITE_NOMEM;
}
}
assert( !pCur->pPage->intKey || !pCur->pKey );
if( rc==SQLITE_OK ){
releasePage(pCur->pPage);
pCur->pPage = 0;
pCur->eState = CURSOR_REQUIRESEEK;
}
invalidateOverflowCache(pCur);
return rc;
}
/*
** Save the positions of all cursors except pExcept open on the table
** with root-page iRoot. Usually, this is called just before cursor
** pExcept is used to modify the table (BtreeDelete() or BtreeInsert()).
*/
static int saveAllCursors(BtShared *pBt, Pgno iRoot, BtCursor *pExcept){
BtCursor *p;
assert( sqlite3_mutex_held(pBt->mutex) );
assert( pExcept==0 || pExcept->pBt==pBt );
for(p=pBt->pCursor; p; p=p->pNext){
if( p!=pExcept && (0==iRoot || p->pgnoRoot==iRoot) &&
p->eState==CURSOR_VALID ){
int rc = saveCursorPosition(p);
if( SQLITE_OK!=rc ){
return rc;
}
}
}
return SQLITE_OK;
}
/*
** Clear the current cursor position.
*/
static void clearCursorPosition(BtCursor *pCur){
assert( cursorHoldsMutex(pCur) );
sqlite3_free(pCur->pKey);
pCur->pKey = 0;
pCur->eState = CURSOR_INVALID;
}
/*
** Restore the cursor to the position it was in (or as close to as possible)
** when saveCursorPosition() was called. Note that this call deletes the
** saved position info stored by saveCursorPosition(), so there can be
** at most one effective restoreOrClearCursorPosition() call after each
** saveCursorPosition().
**
** If the second argument argument - doSeek - is false, then instead of
** returning the cursor to its saved position, any saved position is deleted
** and the cursor state set to CURSOR_INVALID.
*/
int sqlite3BtreeRestoreOrClearCursorPosition(BtCursor *pCur){
int rc;
assert( cursorHoldsMutex(pCur) );
assert( pCur->eState>=CURSOR_REQUIRESEEK );
if( pCur->eState==CURSOR_FAULT ){
return pCur->skip;
}
#ifndef SQLITE_OMIT_INCRBLOB
if( pCur->isIncrblobHandle ){
return SQLITE_ABORT;
}
#endif
pCur->eState = CURSOR_INVALID;
rc = sqlite3BtreeMoveto(pCur, pCur->pKey, 0, pCur->nKey, 0, &pCur->skip);
if( rc==SQLITE_OK ){
sqlite3_free(pCur->pKey);
pCur->pKey = 0;
assert( pCur->eState==CURSOR_VALID || pCur->eState==CURSOR_INVALID );
}
return rc;
}
#define restoreOrClearCursorPosition(p)
(p->eState>=CURSOR_REQUIRESEEK ?
sqlite3BtreeRestoreOrClearCursorPosition(p) :
SQLITE_OK)
#ifndef SQLITE_OMIT_AUTOVACUUM
/*
** Given a page number of a regular database page, return the page
** number for the pointer-map page that contains the entry for the
** input page number.
*/
static Pgno ptrmapPageno(BtShared *pBt, Pgno pgno){
int nPagesPerMapPage, iPtrMap, ret;
assert( sqlite3_mutex_held(pBt->mutex) );
nPagesPerMapPage = (pBt->usableSize/5)+1;
iPtrMap = (pgno-2)/nPagesPerMapPage;
ret = (iPtrMap*nPagesPerMapPage) + 2;
if( ret==PENDING_BYTE_PAGE(pBt) ){
ret++;
}
return ret;
}
/*
** Write an entry into the pointer map.
**
** This routine updates the pointer map entry for page number 'key'
** so that it maps to type 'eType' and parent page number 'pgno'.
** An error code is returned if something goes wrong, otherwise SQLITE_OK.
*/
static int ptrmapPut(BtShared *pBt, Pgno key, u8 eType, Pgno parent){
DbPage *pDbPage; /* The pointer map page */
u8 *pPtrmap; /* The pointer map data */
Pgno iPtrmap; /* The pointer map page number */
int offset; /* Offset in pointer map page */
int rc;
assert( sqlite3_mutex_held(pBt->mutex) );
/* The master-journal page number must never be used as a pointer map page */
assert( 0==PTRMAP_ISPAGE(pBt, PENDING_BYTE_PAGE(pBt)) );
assert( pBt->autoVacuum );
if( key==0 ){
return SQLITE_CORRUPT_BKPT;
}
iPtrmap = PTRMAP_PAGENO(pBt, key);
rc = sqlite3PagerGet(pBt->pPager, iPtrmap, &pDbPage);
if( rc!=SQLITE_OK ){
return rc;
}
offset = PTRMAP_PTROFFSET(pBt, key);
pPtrmap = (u8 *)sqlite3PagerGetData(pDbPage);
if( eType!=pPtrmap[offset] || get4byte(&pPtrmap[offset+1])!=parent ){
TRACE(("PTRMAP_UPDATE: %d->(%d,%d)n", key, eType, parent));
rc = sqlite3PagerWrite(pDbPage);
if( rc==SQLITE_OK ){
pPtrmap[offset] = eType;
put4byte(&pPtrmap[offset+1], parent);
}
}
sqlite3PagerUnref(pDbPage);
return rc;
}
/*
** Read an entry from the pointer map.
**
** This routine retrieves the pointer map entry for page 'key', writing
** the type and parent page number to *pEType and *pPgno respectively.
** An error code is returned if something goes wrong, otherwise SQLITE_OK.
*/
static int ptrmapGet(BtShared *pBt, Pgno key, u8 *pEType, Pgno *pPgno){
DbPage *pDbPage; /* The pointer map page */
int iPtrmap; /* Pointer map page index */
u8 *pPtrmap; /* Pointer map page data */
int offset; /* Offset of entry in pointer map */
int rc;
assert( sqlite3_mutex_held(pBt->mutex) );
iPtrmap = PTRMAP_PAGENO(pBt, key);
rc = sqlite3PagerGet(pBt->pPager, iPtrmap, &pDbPage);
if( rc!=0 ){
return rc;
}
pPtrmap = (u8 *)sqlite3PagerGetData(pDbPage);
offset = PTRMAP_PTROFFSET(pBt, key);
assert( pEType!=0 );
*pEType = pPtrmap[offset];
if( pPgno ) *pPgno = get4byte(&pPtrmap[offset+1]);
sqlite3PagerUnref(pDbPage);
if( *pEType<1 || *pEType>5 ) return SQLITE_CORRUPT_BKPT;
return SQLITE_OK;
}
#endif /* SQLITE_OMIT_AUTOVACUUM */
/*
** Given a btree page and a cell index (0 means the first cell on
** the page, 1 means the second cell, and so forth) return a pointer
** to the cell content.
**
** This routine works only for pages that do not contain overflow cells.
*/
#define findCell(pPage, iCell)
((pPage)->aData + get2byte(&(pPage)->aData[(pPage)->cellOffset+2*(iCell)]))
#ifdef SQLITE_TEST
u8 *sqlite3BtreeFindCell(MemPage *pPage, int iCell){
assert( iCell>=0 );
assert( iCell<get2byte(&pPage->aData[pPage->hdrOffset+3]) );
return findCell(pPage, iCell);
}
#endif
/*
** This a more complex version of sqlite3BtreeFindCell() 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;
pOvfl = &pPage->aOvfl[i];
k = pOvfl->idx;
if( k<=iCell ){
if( k==iCell ){
return pOvfl->pCell;
}
iCell--;
}
}
return findCell(pPage, iCell);
}
/*
** Parse a cell content block and fill in the CellInfo structure. There
** are two versions of this function. sqlite3BtreeParseCell() takes a
** cell index as the second argument and sqlite3BtreeParseCellPtr()
** takes a pointer to the body of the cell as its second argument.
**
** Within this file, the parseCell() macro can be called instead of
** sqlite3BtreeParseCellPtr(). Using some compilers, this will be faster.
*/
void sqlite3BtreeParseCellPtr(
MemPage *pPage, /* Page containing the cell */
u8 *pCell, /* Pointer to the cell text. */
CellInfo *pInfo /* Fill in this structure */
){
int n; /* Number bytes in cell content header */
u32 nPayload; /* Number of bytes of cell payload */
assert( sqlite3_mutex_held(pPage->pBt->mutex) );
pInfo->pCell = pCell;
assert( pPage->leaf==0 || pPage->leaf==1 );
n = pPage->childPtrSize;
assert( n==4-4*pPage->leaf );
if( pPage->hasData ){
n += getVarint32(&pCell[n], &nPayload);
}else{
nPayload = 0;
}
pInfo->nData = nPayload;
if( pPage->intKey ){
n += getVarint(&pCell[n], (u64 *)&pInfo->nKey);
}else{
u32 x;
n += getVarint32(&pCell[n], &x);
pInfo->nKey = x;
nPayload += x;
}
pInfo->nPayload = nPayload;
pInfo->nHeader = n;
if( 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 */
pInfo->nLocal = nPayload;
pInfo->iOverflow = 0;
nSize = nPayload + n;
if( nSize<4 ){
nSize = 4; /* Minimum cell size is 4 */
}
pInfo->nSize = nSize;
}else{
/* If the payload will not fit completely on the local page, we have
** to decide how much to store locally and how much to spill onto
** overflow pages. The strategy is to minimize the amount of unused
** space on overflow pages while keeping the amount of local storage
** in between minLocal and maxLocal.
**
** Warning: changing the way overflow payload is distributed in any
** way will result in an incompatible file format.
*/
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 = surplus;
}else{
pInfo->nLocal = minLocal;
}
pInfo->iOverflow = pInfo->nLocal + n;
pInfo->nSize = pInfo->iOverflow + 4;
}
}
#define parseCell(pPage, iCell, pInfo)
sqlite3BtreeParseCellPtr((pPage), findCell((pPage), (iCell)), (pInfo))
void sqlite3BtreeParseCell(
MemPage *pPage, /* Page containing the cell */
int iCell, /* The cell index. First cell is 0 */
CellInfo *pInfo /* Fill in this structure */
){
parseCell(pPage, iCell, pInfo);
}
/*
** Compute the total number of bytes that a Cell needs in the cell
** data area of the btree-page. The return number includes the cell
** data header and the local payload, but not any overflow page or
** the space used by the cell pointer.
*/
#ifndef NDEBUG
static u16 cellSize(MemPage *pPage, int iCell){
CellInfo info;
sqlite3BtreeParseCell(pPage, iCell, &info);
return info.nSize;
}
#endif
static u16 cellSizePtr(MemPage *pPage, u8 *pCell){
CellInfo info;
sqlite3BtreeParseCellPtr(pPage, pCell, &info);
return info.nSize;
}
#ifndef SQLITE_OMIT_AUTOVACUUM
/*
** If the cell pCell, part of page pPage contains a pointer
** to an overflow page, insert an entry into the pointer-map
** for the overflow page.
*/
static int ptrmapPutOvflPtr(MemPage *pPage, u8 *pCell){
if( pCell ){
CellInfo info;
sqlite3BtreeParseCellPtr(pPage, pCell, &info);
assert( (info.nData+(pPage->intKey?0:info.nKey))==info.nPayload );
if( (info.nData+(pPage->intKey?0:info.nKey))>info.nLocal ){
Pgno ovfl = get4byte(&pCell[info.iOverflow]);
return ptrmapPut(pPage->pBt, ovfl, PTRMAP_OVERFLOW1, pPage->pgno);
}
}
return SQLITE_OK;
}
/*
** If the cell with index iCell on page pPage contains a pointer
** to an overflow page, insert an entry into the pointer-map
** for the overflow page.
*/
static int ptrmapPutOvfl(MemPage *pPage, int iCell){
u8 *pCell;
assert( sqlite3_mutex_held(pPage->pBt->mutex) );
pCell = findOverflowCell(pPage, iCell);
return ptrmapPutOvflPtr(pPage, pCell);
}
#endif
/*
** Defragment the page given. All Cells are moved to the
** end of the page and all free space is collected into one
** big FreeBlk that occurs in between the header and cell
** pointer array and the cell content area.
*/
static int defragmentPage(MemPage *pPage){
int i; /* Loop counter */
int pc; /* Address of a i-th cell */
int addr; /* Offset of first byte after cell pointer array */
int hdr; /* Offset to the page header */
int size; /* Size of a cell */
int usableSize; /* Number of usable bytes on a page */
int cellOffset; /* Offset to the cell pointer array */
int brk; /* Offset to the cell content area */
int nCell; /* Number of cells on the page */
unsigned char *data; /* The page data */
unsigned char *temp; /* Temp area for cell content */
assert( sqlite3PagerIswriteable(pPage->pDbPage) );
assert( pPage->pBt!=0 );
assert( pPage->pBt->usableSize <= SQLITE_MAX_PAGE_SIZE );
assert( pPage->nOverflow==0 );
assert( sqlite3_mutex_held(pPage->pBt->mutex) );
temp = sqlite3PagerTempSpace(pPage->pBt->pPager);
data = pPage->aData;
hdr = pPage->hdrOffset;
cellOffset = pPage->cellOffset;
nCell = pPage->nCell;
assert( nCell==get2byte(&data[hdr+3]) );
usableSize = pPage->pBt->usableSize;
brk = get2byte(&data[hdr+5]);
memcpy(&temp[brk], &data[brk], usableSize - brk);
brk = usableSize;
for(i=0; i<nCell; i++){
u8 *pAddr; /* The i-th cell pointer */
pAddr = &data[cellOffset + i*2];
pc = get2byte(pAddr);
assert( pc<pPage->pBt->usableSize );
size = cellSizePtr(pPage, &temp[pc]);
brk -= size;
memcpy(&data[brk], &temp[pc], size);
put2byte(pAddr, brk);
}
assert( brk>=cellOffset+2*nCell );
put2byte(&data[hdr+5], brk);
data[hdr+1] = 0;
data[hdr+2] = 0;
data[hdr+7] = 0;
addr = cellOffset+2*nCell;
memset(&data[addr], 0, brk-addr);
return SQLITE_OK;
}
/*
** Allocate nByte bytes of space on a page.
**
** Return the index into pPage->aData[] of the first byte of
** the new allocation. Or return 0 if there is not enough free
** space on the page to satisfy the allocation request.
**
** If the page contains nBytes of free space but does not contain
** nBytes of contiguous free space, then this routine automatically
** calls defragementPage() to consolidate all free space before
** allocating the new chunk.
*/
static int allocateSpace(MemPage *pPage, int nByte){
int addr, pc, hdr;
int size;
int nFrag;
int top;
int nCell;
int cellOffset;
unsigned char *data;
data = pPage->aData;
assert( sqlite3PagerIswriteable(pPage->pDbPage) );
assert( pPage->pBt );
assert( sqlite3_mutex_held(pPage->pBt->mutex) );
if( nByte<4 ) nByte = 4;
if( pPage->nFree<nByte || pPage->nOverflow>0 ) return 0;
pPage->nFree -= nByte;
hdr = pPage->hdrOffset;
nFrag = data[hdr+7];
if( nFrag<60 ){
/* Search the freelist looking for a slot big enough to satisfy the
** space request. */
addr = hdr+1;
while( (pc = get2byte(&data[addr]))>0 ){
size = get2byte(&data[pc+2]);
if( size>=nByte ){
if( size<nByte+4 ){
memcpy(&data[addr], &data[pc], 2);
data[hdr+7] = nFrag + size - nByte;
return pc;
}else{
put2byte(&data[pc+2], size-nByte);
return pc + size - nByte;
}
}
addr = pc;
}
}
/* Allocate memory from the gap in between the cell pointer array
** and the cell content area.
*/
top = get2byte(&data[hdr+5]);
nCell = get2byte(&data[hdr+3]);
cellOffset = pPage->cellOffset;
if( nFrag>=60 || cellOffset + 2*nCell > top - nByte ){
if( defragmentPage(pPage) ) return 0;
top = get2byte(&data[hdr+5]);
}
top -= nByte;
assert( cellOffset + 2*nCell <= top );
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 void 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) );
if( size<4 ) size = 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 );
assert( pbegin>addr );
addr = pbegin;
}
assert( pbegin<=pPage->pBt->usableSize-4 );
assert( pbegin>addr || pbegin==0 );
put2byte(&data[addr], start);
put2byte(&data[start], pbegin);
put2byte(&data[start+2], size);
pPage->nFree += size;
/* Coalesce adjacent free blocks */
addr = pPage->hdrOffset + 1;
while( (pbegin = get2byte(&data[addr]))>0 ){
int pnext, psize;
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);
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.
*/
static void 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->intKey = (flagByte & (PTF_INTKEY|PTF_LEAFDATA))!=0;
pPage->zeroData = (flagByte & PTF_ZERODATA)!=0;
pPage->leaf = (flagByte & PTF_LEAF)!=0;
pPage->childPtrSize = 4*(pPage->leaf==0);
pBt = pPage->pBt;
if( flagByte & PTF_LEAFDATA ){
pPage->leafData = 1;
pPage->maxLocal = pBt->maxLeaf;
pPage->minLocal = pBt->minLeaf;
}else{
pPage->leafData = 0;
pPage->maxLocal = pBt->maxLocal;
pPage->minLocal = pBt->minLocal;
}
pPage->hasData = !(pPage->zeroData || (!pPage->leaf && pPage->leafData));
}
/*
** 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;
decodeFlags(pPage, data[hdr]);
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;
}
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;
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);
}
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, int pageSize){
MemPage *pPage;
assert( (pageSize & 7)==0 );
pPage = (MemPage *)sqlite3PagerGetExtra(pData);
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( (flags & BTREE_PRIVATE)==0
&& isMemdb==0
&& (db->flags & SQLITE_Vtab)==0
&& zFilename && zFilename[0]
){
if( sqlite3SharedCacheEnabled ){
int nFullPathname = pVfs->mxPathname+1;
char *zFullPathname = (char *)sqlite3_malloc(nFullPathname);
sqlite3_mutex *mutexShared;
p->sharable = 1;
if( db ){
db->flags |= SQLITE_SharedCache;
}
if( !zFullPathname ){
sqlite3_free(p);
return SQLITE_NOMEM;
}
sqlite3OsFullPathname(pVfs, zFilename, nFullPathname, zFullPathname);
mutexShared = sqlite3_mutex_alloc(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 );
assert( sizeof(Pgno)==4 );
pBt = sqlite3MallocZero( sizeof(*pBt) );
if( pBt==0 ){
rc = SQLITE_NOMEM;
goto btree_open_out;
}
pBt->busyHdr.xFunc = sqlite3BtreeInvokeBusyHandler;
pBt->busyHdr.pArg = pBt;
rc = sqlite3PagerOpen(pVfs, &pBt->pPager, zFilename,
EXTRA_SIZE, flags, vfsFlags);
if( rc==SQLITE_OK ){
rc = sqlite3PagerReadFileheader(pBt->pPager,sizeof(zDbHeader),zDbHeader);
}
if( rc!=SQLITE_OK ){
goto btree_open_out;
}
sqlite3PagerSetBusyhandler(pBt->pPager, &pBt->busyHdr);
p->pBt = pBt;
sqlite3PagerSetDestructor(pBt->pPager, pageDestructor);
sqlite3PagerSetReiniter(pBt->pPager, pageReinit);
pBt->pCursor = 0;
pBt->pPage1 = 0;
pBt->readOnly = sqlite3PagerIsreadonly(pBt->pPager);
pBt->pageSize = get2byte(&zDbHeader[16]);
if( pBt->pageSize<512 || pBt->pageSize>SQLITE_MAX_PAGE_SIZE
|| ((pBt->pageSize-1)&pBt->pageSize)!=0 ){
pBt->pageSize = 0;
sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize);
pBt->maxEmbedFrac = 64; /* 25% */
pBt->minEmbedFrac = 32; /* 12.5% */
pBt->minLeafFrac = 32; /* 12.5% */
#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
** SQLITE_OMIT_MEMORYDB has been defined, then ":memory:" is just a
** regular file-name. In this case the auto-vacuum applies as per normal.
*/
if( zFilename && !isMemdb ){
pBt->autoVacuum = (SQLITE_DEFAULT_AUTOVACUUM ? 1 : 0);
pBt->incrVacuum = (SQLITE_DEFAULT_AUTOVACUUM==2 ? 1 : 0);
}
#endif
nReserve = 0;
}else{
nReserve = zDbHeader[20];
pBt->maxEmbedFrac = zDbHeader[21];
pBt->minEmbedFrac = zDbHeader[22];
pBt->minLeafFrac = zDbHeader[23];
pBt->pageSizeFixed = 1;
#ifndef SQLITE_OMIT_AUTOVACUUM
pBt->autoVacuum = (get4byte(&zDbHeader[36 + 4*4])?1:0);
pBt->incrVacuum = (get4byte(&zDbHeader[36 + 7*4])?1:0);
#endif
}
pBt->usableSize = pBt->pageSize - nReserve;
assert( (pBt->pageSize & 7)==0 ); /* 8-byte alignment of pageSize */
sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize);
#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
/* Add the new BtShared object to the linked list sharable BtShareds.
*/
if( p->sharable ){
sqlite3_mutex *mutexShared;
pBt->nRef = 1;
mutexShared = sqlite3_mutex_alloc(SQLITE_MUTEX_STATIC_MASTER);
if( SQLITE_THREADSAFE ){
pBt->mutex = sqlite3_mutex_alloc(SQLITE_MUTEX_FAST);
if( pBt->mutex==0 ){
rc = SQLITE_NOMEM;
db->mallocFailed = 0;
goto btree_open_out;
}
}
sqlite3_mutex_enter(mutexShared);
pBt->pNext = sqlite3SharedCacheList;
sqlite3SharedCacheList = pBt;
sqlite3_mutex_leave(mutexShared);
}
#endif
}
#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
/* If the new Btree uses a sharable pBtShared, then link the new
** Btree into the list of all sharable Btrees for the same connection.
** The list is kept in ascending order by pBt address.
*/
if( p->sharable ){
int i;
Btree *pSib;
for(i=0; i<db->nDb; i++){
if( (pSib = db->aDb[i].pBt)!=0 && pSib->sharable ){
while( pSib->pPrev ){ pSib = pSib->pPrev; }
if( p->pBt<pSib->pBt ){
p->pNext = pSib;
p->pPrev = 0;
pSib->pPrev = p;
}else{
while( pSib->pNext && pSib->pNext->pBt<p->pBt ){
pSib = pSib->pNext;
}
p->pNext = pSib->pNext;
p->pPrev = pSib;
if( p->pNext ){
p->pNext->pPrev = p;
}
pSib->pNext = p;
}
break;
}
}
}
#endif
*ppBtree = p;
btree_open_out:
if( rc!=SQLITE_OK ){
if( pBt && pBt->pPager ){
sqlite3PagerClose(pBt->pPager);
}
sqlite3_free(pBt);
sqlite3_free(p);
*ppBtree = 0;
}
return rc;
}
/*
** Decrement the BtShared.nRef counter. When it reaches zero,
** remove the BtShared structure from the sharing list. Return
** true if the BtShared.nRef counter reaches zero and return
** false if it is still positive.
*/
static int removeFromSharingList(BtShared *pBt){
#ifndef SQLITE_OMIT_SHARED_CACHE
sqlite3_mutex *pMaster;
BtShared *pList;
int removed = 0;
assert( sqlite3_mutex_notheld(pBt->mutex) );
pMaster = sqlite3_mutex_alloc(SQLITE_MUTEX_STATIC_MASTER);
sqlite3_mutex_enter(pMaster);
pBt->nRef--;
if( pBt->nRef<=0 ){
if( sqlite3SharedCacheList==pBt ){
sqlite3SharedCacheList = pBt->pNext;
}else{
pList = sqlite3SharedCacheList;
while( pList && pList->pNext!=pBt ){
pList=pList->pNext;
}
if( pList ){
pList->pNext = pBt->pNext;
}
}
if( SQLITE_THREADSAFE ){
sqlite3_mutex_free(pBt->mutex);
}
removed = 1;
}
sqlite3_mutex_leave(pMaster);
return removed;
#else
return 1;
#endif
}
/*
** Close an open database and invalidate all cursors.
*/
int sqlite3BtreeClose(Btree *p){
BtShared *pBt = p->pBt;
BtCursor *pCur;
/* Close all cursors opened via this handle. */
assert( sqlite3_mutex_held(p->db->mutex) );
sqlite3BtreeEnter(p);
pBt->db = p->db;
pCur = pBt->pCursor;
while( pCur ){
BtCursor *pTmp = pCur;
pCur = pCur->pNext;
if( pTmp->pBtree==p ){
sqlite3BtreeCloseCursor(pTmp);
}
}
/* Rollback any active transaction and free the handle structure.
** The call to sqlite3BtreeRollback() drops any table-locks held by
** this handle.
*/
sqlite3BtreeRollback(p);
sqlite3BtreeLeave(p);
/* If there are still other outstanding references to the shared-btree
** structure, return now. The remainder of this procedure cleans
** up the shared-btree.
*/
assert( p->wantToLock==0 && p->locked==0 );
if( !p->sharable || removeFromSharingList(pBt) ){
/* The pBt is no longer on the sharing list, so we can access
** it without having to hold the mutex.
**
** Clean out and delete the BtShared object.
*/
assert( !pBt->pCursor );
sqlite3PagerClose(pBt->pPager);
if( pBt->xFreeSchema && pBt->pSchema ){
pBt->xFreeSchema(pBt->pSchema);
}
sqlite3_free(pBt->pSchema);
sqlite3_free(pBt->pTmpSpace);
sqlite3_free(pBt);
}
#ifndef SQLITE_OMIT_SHARED_CACHE
assert( p->wantToLock==0 );
assert( p->locked==0 );
if( p->pPrev ) p->pPrev->pNext = p->pNext;
if( p->pNext ) p->pNext->pPrev = p->pPrev;
#endif
sqlite3_free(p);
return SQLITE_OK;
}
/*
** Change the limit on the number of pages allowed in the cache.
**
** The maximum number of cache pages is set to the absolute
** value of mxPage. If mxPage is negative, the pager will
** operate asynchronously - it will not stop to do fsync()s
** to insure data is written to the disk surface before
** continuing. Transactions still work if synchronous is off,
** and the database cannot be corrupted if this program
** crashes. But if the operating system crashes or there is
** an abrupt power failure when synchronous is off, the database
** could be left in an inconsistent and unrecoverable state.
** Synchronous is on by default so database corruption is not
** normally a worry.
*/
int sqlite3BtreeSetCacheSize(Btree *p, int mxPage){
BtShared *pBt = p->pBt;
assert( sqlite3_mutex_held(p->db->mutex) );
sqlite3BtreeEnter(p);
sqlite3PagerSetCachesize(pBt->pPager, mxPage);
sqlite3BtreeLeave(p);
return SQLITE_OK;
}
/*
** Change the way data is synced to disk in order to increase or decrease
** how well the database resists damage due to OS crashes and power
** failures. Level 1 is the same as asynchronous (no syncs() occur and
** there is a high probability of damage) Level 2 is the default. There
** is a very low but non-zero probability of damage. Level 3 reduces the
** probability of damage to near zero but with a write performance reduction.
*/
#ifndef SQLITE_OMIT_PAGER_PRAGMAS
int sqlite3BtreeSetSafetyLevel(Btree *p, int level, int fullSync){
BtShared *pBt = p->pBt;
assert( sqlite3_mutex_held(p->db->mutex) );
sqlite3BtreeEnter(p);
sqlite3PagerSetSafetyLevel(pBt->pPager, level, fullSync);
sqlite3BtreeLeave(p);
return SQLITE_OK;
}
#endif
/*
** Return TRUE if the given btree is set to safety level 1. In other
** words, return TRUE if no sync() occurs on the disk files.
*/
int sqlite3BtreeSyncDisabled(Btree *p){
BtShared *pBt = p->pBt;
int rc;
assert( sqlite3_mutex_held(p->db->mutex) );
sqlite3BtreeEnter(p);
assert( pBt && pBt->pPager );
rc = sqlite3PagerNosync(pBt->pPager);
sqlite3BtreeLeave(p);
return rc;
}
#if !defined(SQLITE_OMIT_PAGER_PRAGMAS) || !defined(SQLITE_OMIT_VACUUM)
/*
** Change the default pages size and the number of reserved bytes per page.
**
** The page size must be a power of 2 between 512 and 65536. If the page
** size supplied does not meet this constraint then the page size is not
** changed.
**
** Page sizes are constrained to be a power of two so that the region
** of the database file used for locking (beginning at PENDING_BYTE,
** the first byte past the 1GB boundary, 0x40000000) needs to occur
** at the beginning of a page.
**
** If parameter nReserve is less than zero, then the number of reserved
** bytes per page is left unchanged.
*/
int sqlite3BtreeSetPageSize(Btree *p, int pageSize, int nReserve){
int rc = SQLITE_OK;
BtShared *pBt = p->pBt;
sqlite3BtreeEnter(p);
if( pBt->pageSizeFixed ){
sqlite3BtreeLeave(p);
return SQLITE_READONLY;
}
if( nReserve<0 ){
nReserve = pBt->pageSize - pBt->usableSize;
}
if( pageSize>=512 && pageSize<=SQLITE_MAX_PAGE_SIZE &&
((pageSize-1)&pageSize)==0 ){
assert( (pageSize & 7)==0 );
assert( !pBt->pPage1 && !pBt->pCursor );
pBt->pageSize = pageSize;
sqlite3_free(pBt->pTmpSpace);
pBt->pTmpSpace = 0;
rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize);
}
pBt->usableSize = pBt->pageSize - nReserve;
sqlite3BtreeLeave(p);
return rc;
}
/*
** Return the currently defined page size
*/
int sqlite3BtreeGetPageSize(Btree *p){
return p->pBt->pageSize;
}
int sqlite3BtreeGetReserve(Btree *p){
int n;
sqlite3BtreeEnter(p);
n = p->pBt->pageSize - p->pBt->usableSize;
sqlite3BtreeLeave(p);
return n;
}
/*
** Set the maximum page count for a database if mxPage is positive.
** No changes are made if mxPage is 0 or negative.
** Regardless of the value of mxPage, return the maximum page count.
*/
int sqlite3BtreeMaxPageCount(Btree *p, int mxPage){
int n;
sqlite3BtreeEnter(p);
n = sqlite3PagerMaxPageCount(p->pBt->pPager, mxPage);
sqlite3BtreeLeave(p);
return n;
}
#endif /* !defined(SQLITE_OMIT_PAGER_PRAGMAS) || !defined(SQLITE_OMIT_VACUUM) */
/*
** Change the 'auto-vacuum' property of the database. If the 'autoVacuum'
** parameter is non-zero, then auto-vacuum mode is enabled. If zero, it
** is disabled. The default value for the auto-vacuum property is
** determined by the SQLITE_DEFAULT_AUTOVACUUM macro.
*/
int sqlite3BtreeSetAutoVacuum(Btree *p, int autoVacuum){
#ifdef SQLITE_OMIT_AUTOVACUUM
return SQLITE_READONLY;
#else
BtShared *pBt = p->pBt;
int rc = SQLITE_OK;
int av = (autoVacuum?1:0);
sqlite3BtreeEnter(p);
if( pBt->pageSizeFixed && av!=pBt->autoVacuum ){
rc = SQLITE_READONLY;
}else{
pBt->autoVacuum = av;
}
sqlite3BtreeLeave(p);
return rc;
#endif
}
/*
** Return the value of the 'auto-vacuum' property. If auto-vacuum is
** enabled 1 is returned. Otherwise 0.
*/
int sqlite3BtreeGetAutoVacuum(Btree *p){
#ifdef SQLITE_OMIT_AUTOVACUUM
return BTREE_AUTOVACUUM_NONE;
#else
int rc;
sqlite3BtreeEnter(p);
rc = (
(!p->pBt->autoVacuum)?BTREE_AUTOVACUUM_NONE:
(!p->pBt->incrVacuum)?BTREE_AUTOVACUUM_FULL:
BTREE_AUTOVACUUM_INCR
);
sqlite3BtreeLeave(p);
return rc;
#endif
}
/*
** Get a reference to pPage1 of the database file. This will
** also acquire a readlock on that file.
**
** SQLITE_OK is returned on success. If the file is not a
** well-formed database file, then SQLITE_CORRUPT is returned.
** SQLITE_BUSY is returned if the database is locked. SQLITE_NOMEM
** is returned if we run out of memory.
*/
static int lockBtree(BtShared *pBt){
int rc;
MemPage *pPage1;
assert( sqlite3_mutex_held(pBt->mutex) );
if( pBt->pPage1 ) return SQLITE_OK;
rc = sqlite3BtreeGetPage(pBt, 1, &pPage1, 0);
if( rc!=SQLITE_OK ) return rc;
/* Do some checking to help insure the file we opened really is
** a valid database file.
*/
rc = SQLITE_NOTADB;
if( sqlite3PagerPagecount(pBt->pPager)>0 ){
int pageSize;
int usableSize;
u8 *page1 = pPage1->aData;
if( memcmp(page1, zMagicHeader, 16)!=0 ){
goto page1_init_failed;
}
if( page1[18]>1 ){
pBt->readOnly = 1;
}
if( page1[19]>1 ){
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 = usableSize;
pBt->pageSize = pageSize;
sqlite3_free(pBt->pTmpSpace);
pBt->pTmpSpace = 0;
sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize);
return SQLITE_OK;
}
if( usableSize<500 ){
goto page1_init_failed;
}
pBt->pageSize = pageSize;
pBt->usableSize = usableSize;
pBt->maxEmbedFrac = page1[21];
pBt->minEmbedFrac = page1[22];
pBt->minLeafFrac = page1[23];
#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
** a cell. Make sure it is small enough so that at least minFanout
** cells can will fit on one page. We assume a 10-byte page header.
** Besides the payload, the cell must store:
** 2-byte pointer to the cell
** 4-byte child pointer
** 9-byte nKey value
** 4-byte nData value
** 4-byte overflow page pointer
** So a cell consists of a 2-byte poiner, a header which is as much as
** 17 bytes long, 0 to N bytes of payload, and an optional 4 byte overflow
** page pointer.
*/
pBt->maxLocal = (pBt->usableSize-12)*pBt->maxEmbedFrac/255 - 23;
pBt->minLocal = (pBt->usableSize-12)*pBt->minEmbedFrac/255 - 23;
pBt->maxLeaf = pBt->usableSize - 35;
pBt->minLeaf = (pBt->usableSize-12)*pBt->minLeafFrac/255 - 23;
if( pBt->minLocal>pBt->maxLocal || pBt->maxLocal<0 ){
goto page1_init_failed;
}
assert( pBt->maxLeaf + 23 <= MX_CELL_SIZE(pBt) );
pBt->pPage1 = pPage1;
return SQLITE_OK;
page1_init_failed:
releasePage(pPage1);
pBt->pPage1 = 0;
return rc;
}
/*
** This routine works like lockBtree() except that it also invokes the
** busy callback if there is lock contention.
*/
static int lockBtreeWithRetry(Btree *pRef){
int rc = SQLITE_OK;
assert( sqlite3BtreeHoldsMutex(pRef) );
if( pRef->inTrans==TRANS_NONE ){
u8 inTransaction = pRef->pBt->inTransaction;
btreeIntegrity(pRef);
rc = sqlite3BtreeBeginTrans(pRef, 0);
pRef->pBt->inTransaction = inTransaction;
pRef->inTrans = TRANS_NONE;
if( rc==SQLITE_OK ){
pRef->pBt->nTransaction--;
}
btreeIntegrity(pRef);
}
return rc;
}
/*
** If there are no outstanding cursors and we are not in the middle
** of a transaction but there is a read lock on the database, then
** this routine unrefs the first page of the database file which
** has the effect of releasing the read lock.
**
** If there are any outstanding cursors, this routine is a no-op.
**
** If there is a transaction in progress, this routine is a no-op.
*/
static void unlockBtreeIfUnused(BtShared *pBt){
assert( sqlite3_mutex_held(pBt->mutex) );
if( pBt->inTransaction==TRANS_NONE && pBt->pCursor==0 && pBt->pPage1!=0 ){
if( sqlite3PagerRefcount(pBt->pPager)>=1 ){
assert( pBt->pPage1->aData );
#if 0
if( pBt->pPage1->aData==0 ){
MemPage *pPage = pBt->pPage1;
pPage->aData = sqlite3PagerGetData(pPage->pDbPage);
pPage->pBt = pBt;
pPage->pgno = 1;
}
#endif
releasePage(pBt->pPage1);
}
pBt->pPage1 = 0;
pBt->inStmt = 0;
}
}
/*
** Create a new database by initializing the first page of the
** file.
*/
static int newDatabase(BtShared *pBt){
MemPage *pP1;
unsigned char *data;
int rc;
assert( sqlite3_mutex_held(pBt->mutex) );
if( sqlite3PagerPagecount(pBt->pPager)>0 ) return SQLITE_OK;
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;
data[20] = pBt->pageSize - pBt->usableSize;
data[21] = pBt->maxEmbedFrac;
data[22] = pBt->minEmbedFrac;
data[23] = pBt->minLeafFrac;
memset(&data[24], 0, 100-24);
zeroPage(pP1, PTF_INTKEY|PTF_LEAF|PTF_LEAFDATA );
pBt->pageSizeFixed = 1;
#ifndef SQLITE_OMIT_AUTOVACUUM
assert( pBt->autoVacuum==1 || pBt->autoVacuum==0 );
assert( pBt->incrVacuum==1 || pBt->incrVacuum==0 );
put4byte(&data[36 + 4*4], pBt->autoVacuum);
put4byte(&data[36 + 7*4], pBt->incrVacuum);
#endif
return SQLITE_OK;
}
/*
** Attempt to start a new transaction. A write-transaction
** is started if the second argument is nonzero, otherwise a read-
** transaction. If the second argument is 2 or more and exclusive
** transaction is started, meaning that no other process is allowed
** to access the database. A preexisting transaction may not be
** upgraded to exclusive by calling this routine a second time - the
** exclusivity flag only works for a new transaction.
**
** A write-transaction must be started before attempting any
** changes to the database. None of the following routines
** will work unless a transaction is started first:
**
** sqlite3BtreeCreateTable()
** sqlite3BtreeCreateIndex()
** sqlite3BtreeClearTable()
** sqlite3BtreeDropTable()
** sqlite3BtreeInsert()
** sqlite3BtreeDelete()
** sqlite3BtreeUpdateMeta()
**
** If an initial attempt to acquire the lock fails because of lock contention
** and the database was previously unlocked, then invoke the busy handler
** if there is one. But if there was previously a read-lock, do not
** invoke the busy handler - just return SQLITE_BUSY. SQLITE_BUSY is
** returned when there is already a read-lock in order to avoid a deadlock.
**
** Suppose there are two processes A and B. A has a read lock and B has
** a reserved lock. B tries to promote to exclusive but is blocked because
** of A's read lock. A tries to promote to reserved but is blocked by B.
** One or the other of the two processes must give way or there can be
** no progress. By returning SQLITE_BUSY and not invoking the busy callback
** when A already has a read lock, we encourage A to give up and let B
** proceed.
*/
int sqlite3BtreeBeginTrans(Btree *p, int wrflag){
BtShared *pBt = p->pBt;
int rc = SQLITE_OK;
sqlite3BtreeEnter(p);
pBt->db = p->db;
btreeIntegrity(p);
/* If the btree is already in a write-transaction, or it
** is already in a read-transaction and a read-transaction
** is requested, this is a no-op.
*/
if( p->inTrans==TRANS_WRITE || (p->inTrans==TRANS_READ && !wrflag) ){
goto trans_begun;
}
/* Write transactions are not possible on a read-only database */
if( pBt->readOnly && wrflag ){
rc = SQLITE_READONLY;
goto trans_begun;
}
/* If another database handle has already opened a write transaction
** on this shared-btree structure and a second write transaction is
** requested, return SQLITE_BUSY.
*/
if( pBt->inTransaction==TRANS_WRITE && wrflag ){
rc = SQLITE_BUSY;
goto trans_begun;
}
#ifndef SQLITE_OMIT_SHARED_CACHE
if( wrflag>1 ){
BtLock *pIter;
for(pIter=pBt->pLock; pIter; pIter=pIter->pNext){
if( pIter->pBtree!=p ){
rc = SQLITE_BUSY;
goto trans_begun;
}
}
}
#endif
do {
while( rc==SQLITE_OK && pBt->pPage1==0 ){
rc = lockBtree(pBt);
}
if( rc==SQLITE_OK && wrflag ){
if( pBt->readOnly ){
rc = SQLITE_READONLY;
}else{
rc = sqlite3PagerBegin(pBt->pPage1->pDbPage, wrflag>1);
if( rc==SQLITE_OK ){
rc = newDatabase(pBt);
}
}
}
if( rc==SQLITE_OK ){
if( wrflag ) pBt->inStmt = 0;
}else{
unlockBtreeIfUnused(pBt);
}
}while( rc==SQLITE_BUSY && pBt->inTransaction==TRANS_NONE &&
sqlite3BtreeInvokeBusyHandler(pBt, 0) );
if( rc==SQLITE_OK ){
if( p->inTrans==TRANS_NONE ){
pBt->nTransaction++;
}
p->inTrans = (wrflag?TRANS_WRITE:TRANS_READ);
if( p->inTrans>pBt->inTransaction ){
pBt->inTransaction = p->inTrans;
}
#ifndef SQLITE_OMIT_SHARED_CACHE
if( wrflag>1 ){
assert( !pBt->pExclusive );
pBt->pExclusive = p;
}
#endif
}
trans_begun:
btreeIntegrity(p);
sqlite3BtreeLeave(p);
return rc;
}
#ifndef SQLITE_OMIT_AUTOVACUUM
/*
** Set the pointer-map entries for all children of page pPage. Also, if
** pPage contains cells that point to overflow pages, set the pointer
** map entries for the overflow pages as well.
*/
static int setChildPtrmaps(MemPage *pPage){
int i; /* Counter variable */
int nCell; /* Number of cells in page pPage */
int rc; /* Return code */
BtShared *pBt = pPage->pBt;
int isInitOrig = pPage->isInit;
Pgno pgno = pPage->pgno;
assert( sqlite3_mutex_held(pPage->pBt->mutex) );
rc = sqlite3BtreeInitPage(pPage, pPage->pParent);
if( rc!=SQLITE_OK ){
goto set_child_ptrmaps_out;
}
nCell = pPage->nCell;
for(i=0; i<nCell; i++){
u8 *pCell = findCell(pPage, i);
rc = ptrmapPutOvflPtr(pPage, pCell);
if( rc!=SQLITE_OK ){
goto set_child_ptrmaps_out;
}
if( !pPage->leaf ){
Pgno childPgno = get4byte(pCell);
rc = ptrmapPut(pBt, childPgno, PTRMAP_BTREE, pgno);
if( rc!=SQLITE_OK ) goto set_child_ptrmaps_out;
}
}
if( !pPage->leaf ){
Pgno childPgno = get4byte(&pPage->aData[pPage->hdrOffset+8]);
rc = ptrmapPut(pBt, childPgno, PTRMAP_BTREE, pgno);
}
set_child_ptrmaps_out:
pPage->isInit = isInitOrig;
return rc;
}
/*
** Somewhere on pPage, which is guarenteed to be a btree page, not an overflow
** page, is a pointer to page iFrom. Modify this pointer so that it points to
** iTo. Parameter eType describes the type of pointer to be modified, as
** follows:
**
** PTRMAP_BTREE: pPage is a btree-page. The pointer points at a child
** page of pPage.
**
** PTRMAP_OVERFLOW1: pPage is a btree-page. The pointer points at an overflow
** page pointed to by one of the cells on pPage.
**
** PTRMAP_OVERFLOW2: pPage is an overflow-page. The pointer points at the next
** overflow page in the list.
*/
static int modifyPagePointer(MemPage *pPage, Pgno iFrom, Pgno iTo, u8 eType){
assert( sqlite3_mutex_held(pPage->pBt->mutex) );
if( eType==PTRMAP_OVERFLOW2 ){
/* The pointer is always the first 4 bytes of the page in this case. */
if( get4byte(pPage->aData)!=iFrom ){
return SQLITE_CORRUPT_BKPT;
}
put4byte(pPage->aData, iTo);
}else{
int isInitOrig = pPage->isInit;
int i;
int nCell;
sqlite3BtreeInitPage(pPage, 0);
nCell = pPage->nCell;
for(i=0; i<nCell; i++){
u8 *pCell = findCell(pPage, i);
if( eType==PTRMAP_OVERFLOW1 ){
CellInfo info;
sqlite3BtreeParseCellPtr(pPage, pCell, &info);
if( info.iOverflow ){
if( iFrom==get4byte(&pCell[info.iOverflow]) ){
put4byte(&pCell[info.iOverflow], iTo);
break;
}
}
}else{
if( get4byte(pCell)==iFrom ){
put4byte(pCell, iTo);
break;
}
}
}
if( i==nCell ){
if( eType!=PTRMAP_BTREE ||
get4byte(&pPage->aData[pPage->hdrOffset+8])!=iFrom ){
return SQLITE_CORRUPT_BKPT;
}
put4byte(&pPage->aData[pPage->hdrOffset+8], iTo);
}
pPage->isInit = isInitOrig;
}
return SQLITE_OK;
}
/*
** Move the open database page pDbPage to location iFreePage in the
** database. The pDbPage reference remains valid.
*/
static int relocatePage(
BtShared *pBt, /* Btree */
MemPage *pDbPage, /* Open page to move */
u8 eType, /* Pointer map 'type' entry for pDbPage */
Pgno iPtrPage, /* Pointer map 'page-no' entry for pDbPage */
Pgno iFreePage /* The location to move pDbPage to */
){
MemPage *pPtrPage; /* The page that contains a pointer to pDbPage */
Pgno iDbPage = pDbPage->pgno;
Pager *pPager = pBt->pPager;
int rc;
assert( eType==PTRMAP_OVERFLOW2 || eType==PTRMAP_OVERFLOW1 ||
eType==PTRMAP_BTREE || eType==PTRMAP_ROOTPAGE );
assert( sqlite3_mutex_held(pBt->mutex) );
assert( pDbPage->pBt==pBt );
/* Move page iDbPage from its current location to page number iFreePage */
TRACE(("AUTOVACUUM: Moving %d to free page %d (ptr page %d type %d)n",
iDbPage, iFreePage, iPtrPage, eType));
rc = sqlite3PagerMovepage(pPager, pDbPage->pDbPage, iFreePage);
if( rc!=SQLITE_OK ){
return rc;
}
pDbPage->pgno = iFreePage;
/* If pDbPage was a btree-page, then it may have child pages and/or cells
** that point to overflow pages. The pointer map entries for all these
** pages need to be changed.
**
** If pDbPage is an overflow page, then the first 4 bytes may store a
** pointer to a subsequent overflow page. If this is the case, then
** the pointer map needs to be updated for the subsequent overflow page.
*/
if( eType==PTRMAP_BTREE || eType==PTRMAP_ROOTPAGE ){
rc = setChildPtrmaps(pDbPage);
if( rc!=SQLITE_OK ){
return rc;
}
}else{
Pgno nextOvfl = get4byte(pDbPage->aData);
if( nextOvfl!=0 ){
rc = ptrmapPut(pBt, nextOvfl, PTRMAP_OVERFLOW2, iFreePage);
if( rc!=SQLITE_OK ){
return rc;
}
}
}
/* Fix the database pointer on page iPtrPage that pointed at iDbPage so
** that it points at iFreePage. Also fix the pointer map entry for
** iPtrPage.
*/
if( eType!=PTRMAP_ROOTPAGE ){
rc = sqlite3BtreeGetPage(pBt, iPtrPage, &pPtrPage, 0);
if( rc!=SQLITE_OK ){
return rc;
}
rc = sqlite3PagerWrite(pPtrPage->pDbPage);
if( rc!=SQLITE_OK ){
releasePage(pPtrPage);
return rc;
}
rc = modifyPagePointer(pPtrPage, iDbPage, iFreePage, eType);
releasePage(pPtrPage);
if( rc==SQLITE_OK ){
rc = ptrmapPut(pBt, iFreePage, eType, iPtrPage);
}
}
return rc;
}
/* Forward declaration required by incrVacuumStep(). */
static int allocateBtreePage(BtShared *, MemPage **, Pgno *, Pgno, u8);
/*
** Perform a single step of an incremental-vacuum. If successful,
** return SQLITE_OK. If there is no work to do (and therefore no
** point in calling this function again), return SQLITE_DONE.
**
** More specificly, this function attempts to re-organize the
** database so that the last page of the file currently in use
** is no longer in use.
**
** If the nFin parameter is non-zero, the implementation assumes
** that the caller will keep calling incrVacuumStep() until
** it returns SQLITE_DONE or an error, and that nFin is the
** number of pages the database file will contain after this
** process is complete.
*/
static int incrVacuumStep(BtShared *pBt, Pgno nFin){
Pgno iLastPg; /* Last page in the database */
Pgno nFreeList; /* Number of pages still on the free-list */
assert( sqlite3_mutex_held(pBt->mutex) );
iLastPg = pBt->nTrunc;
if( iLastPg==0 ){
iLastPg = sqlite3PagerPagecount(pBt->pPager);
}
if( !PTRMAP_ISPAGE(pBt, iLastPg) && iLastPg!=PENDING_BYTE_PAGE(pBt) ){
int rc;
u8 eType;
Pgno iPtrPage;
nFreeList = get4byte(&pBt->pPage1->aData[36]);
if( nFreeList==0 || nFin==iLastPg ){
return SQLITE_DONE;
}
rc = ptrmapGet(pBt, iLastPg, &eType, &iPtrPage);
if( rc!=SQLITE_OK ){
return rc;
}
if( eType==PTRMAP_ROOTPAGE ){
return SQLITE_CORRUPT_BKPT;
}
if( eType==PTRMAP_FREEPAGE ){
if( nFin==0 ){
/* Remove the page from the files free-list. This is not required
** if nFin is non-zero. In that case, the free-list will be
** truncated to zero after this function returns, so it doesn't
** matter if it still contains some garbage entries.
*/
Pgno iFreePg;
MemPage *pFreePg;
rc = allocateBtreePage(pBt, &pFreePg, &iFreePg, iLastPg, 1);
if( rc!=SQLITE_OK ){
return rc;
}
assert( iFreePg==iLastPg );
releasePage(pFreePg);
}
} else {
Pgno iFreePg; /* Index of free page to move pLastPg to */
MemPage *pLastPg;
rc = sqlite3BtreeGetPage(pBt, iLastPg, &pLastPg, 0);
if( rc!=SQLITE_OK ){
return rc;
}
/* If nFin is zero, this loop runs exactly once and page pLastPg
** is swapped with the first free page pulled off the free list.
**
** On the other hand, if nFin is greater than zero, then keep
** looping until a free-page located within the first nFin pages
** of the file is found.
*/
do {
MemPage *pFreePg;
rc = allocateBtreePage(pBt, &pFreePg, &iFreePg, 0, 0);
if( rc!=SQLITE_OK ){
releasePage(pLastPg);
return rc;
}
releasePage(pFreePg);
}while( nFin!=0 && iFreePg>nFin );
assert( iFreePg<iLastPg );
rc = sqlite3PagerWrite(pLastPg->pDbPage);
if( rc==SQLITE_OK ){
rc = relocatePage(pBt, pLastPg, eType, iPtrPage, iFreePg);
}
releasePage(pLastPg);
if( rc!=SQLITE_OK ){
return rc;
}
}
}
pBt->nTrunc = iLastPg - 1;
while( pBt->nTrunc==PENDING_BYTE_PAGE(pBt)||PTRMAP_ISPAGE(pBt, pBt->nTrunc) ){
pBt->nTrunc--;
}
return SQLITE_OK;
}
/*
** A write-transaction must be opened before calling this function.
** It performs a single unit of work towards an incremental vacuum.
**
** If the incremental vacuum is finished after this function has run,
** SQLITE_DONE is returned. If it is not finished, but no error occured,
** SQLITE_OK is returned. Otherwise an SQLite error code.
*/
int sqlite3BtreeIncrVacuum(Btree *p){
int rc;
BtShared *pBt = p->pBt;
sqlite3BtreeEnter(p);
pBt->db = p->db;
assert( pBt->inTransaction==TRANS_WRITE && p->inTrans==TRANS_WRITE );
if( !pBt->autoVacuum ){
rc = SQLITE_DONE;
}else{
invalidateAllOverflowCache(pBt);
rc = incrVacuumStep(pBt, 0);
}
sqlite3BtreeLeave(p);
return rc;
}
/*
** This routine is called prior to sqlite3PagerCommit when a transaction
** is commited for an auto-vacuum database.
**
** If SQLITE_OK is returned, then *pnTrunc is set to the number of pages
** the database file should be truncated to during the commit process.
** i.e. the database has been reorganized so that only the first *pnTrunc
** pages are in use.
*/
static int autoVacuumCommit(BtShared *pBt, Pgno *pnTrunc){
int rc = SQLITE_OK;
Pager *pPager = pBt->pPager;
#ifndef NDEBUG
int nRef = sqlite3PagerRefcount(pPager);
#endif
assert( sqlite3_mutex_held(pBt->mutex) );
invalidateAllOverflowCache(pBt);
assert(pBt->autoVacuum);
if( !pBt->incrVacuum ){
Pgno nFin = 0;
if( pBt->nTrunc==0 ){
Pgno nFree;
Pgno nPtrmap;
const int pgsz = pBt->pageSize;
Pgno nOrig = sqlite3PagerPagecount(pBt->pPager);
if( PTRMAP_ISPAGE(pBt, nOrig) ){
return SQLITE_CORRUPT_BKPT;
}
if( nOrig==PENDING_BYTE_PAGE(pBt) ){
nOrig--;
}
nFree = get4byte(&pBt->pPage1->aData[36]);
nPtrmap = (nFree-nOrig+PTRMAP_PAGENO(pBt, nOrig)+pgsz/5)/(pgsz/5);
nFin = nOrig - nFree - nPtrmap;
if( nOrig>PENDING_BYTE_PAGE(pBt) && nFin<=PENDING_BYTE_PAGE(pBt) ){
nFin--;
}
while( PTRMAP_ISPAGE(pBt, nFin) || nFin==PENDING_BYTE_PAGE(pBt) ){
nFin--;
}
}
while( rc==SQLITE_OK ){
rc = incrVacuumStep(pBt, nFin);
}
if( rc==SQLITE_DONE ){
assert(nFin==0 || pBt->nTrunc==0 || nFin<=pBt->nTrunc);
rc = SQLITE_OK;
if( pBt->nTrunc ){
rc = sqlite3PagerWrite(pBt->pPage1->pDbPage);
put4byte(&pBt->pPage1->aData[32], 0);
put4byte(&pBt->pPage1->aData[36], 0);
pBt->nTrunc = nFin;
}
}
if( rc!=SQLITE_OK ){
sqlite3PagerRollback(pPager);
}
}
if( rc==SQLITE_OK ){
*pnTrunc = pBt->nTrunc;
pBt->nTrunc = 0;
}
assert( nRef==sqlite3PagerRefcount(pPager) );
return rc;
}
#endif
/*
** This routine does the first phase of a two-phase commit. This routine
** causes a rollback journal to be created (if it does not already exist)
** and populated with enough information so that if a power loss occurs
** the database can be restored to its original state by playing back
** the journal. Then the contents of the journal are flushed out to
** the disk. After the journal is safely on oxide, the changes to the
** database are written into the database file and flushed to oxide.
** At the end of this call, the rollback journal still exists on the
** disk and we are still holding all locks, so the transaction has not
** committed. See sqlite3BtreeCommit() for the second phase of the
** commit process.
**
** This call is a no-op if no write-transaction is currently active on pBt.
**
** Otherwise, sync the database file for the btree pBt. zMaster points to
** the name of a master journal file that should be written into the
** individual journal file, or is NULL, indicating no master journal file
** (single database transaction).
**
** When this is called, the master journal should already have been
** created, populated with this journal pointer and synced to disk.
**
** Once this is routine has returned, the only thing required to commit
** the write-transaction for this database file is to delete the journal.
*/
int sqlite3BtreeCommitPhaseOne(Btree *p, const char *zMaster){
int rc = SQLITE_OK;
if( p->inTrans==TRANS_WRITE ){
BtShared *pBt = p->pBt;
Pgno nTrunc = 0;
sqlite3BtreeEnter(p);
pBt->db = p->db;
#ifndef SQLITE_OMIT_AUTOVACUUM
if( pBt->autoVacuum ){
rc = autoVacuumCommit(pBt, &nTrunc);
if( rc!=SQLITE_OK ){
sqlite3BtreeLeave(p);
return rc;
}
}
#endif
rc = sqlite3PagerCommitPhaseOne(pBt->pPager, zMaster, nTrunc, 0);
sqlite3BtreeLeave(p);
}
return rc;
}
/*
** Commit the transaction currently in progress.
**
** This routine implements the second phase of a 2-phase commit. The
** sqlite3BtreeSync() routine does the first phase and should be invoked
** prior to calling this routine. The sqlite3BtreeSync() routine did
** all the work of writing information out to disk and flushing the
** contents so that they are written onto the disk platter. All this
** routine has to do is delete or truncate the rollback journal
** (which causes the transaction to commit) and drop locks.
**
** This will release the write lock on the database file. If there
** are no active cursors, it also releases the read lock.
*/
int sqlite3BtreeCommitPhaseTwo(Btree *p){
BtShared *pBt = p->pBt;
sqlite3BtreeEnter(p);
pBt->db = p->db;
btreeIntegrity(p);
/* If the handle has a write-transaction open, commit the shared-btrees
** transaction and set the shared state to TRANS_READ.
*/
if( p->inTrans==TRANS_WRITE ){
int rc;
assert( pBt->inTransaction==TRANS_WRITE );
assert( pBt->nTransaction>0 );
rc = sqlite3PagerCommitPhaseTwo(pBt->pPager);
if( rc!=SQLITE_OK ){
sqlite3BtreeLeave(p);
return rc;
}
pBt->inTransaction = TRANS_READ;
pBt->inStmt = 0;
}
unlockAllTables(p);
/* If the handle has any kind of transaction open, decrement the transaction
** count of the shared btree. If the transaction count reaches 0, set
** the shared state to TRANS_NONE. The unlockBtreeIfUnused() call below
** will unlock the pager.
*/
if( p->inTrans!=TRANS_NONE ){
pBt->nTransaction--;
if( 0==pBt->nTransaction ){
pBt->inTransaction = TRANS_NONE;
}
}
/* Set the handles current transaction state to TRANS_NONE and unlock
** the pager if this call closed the only read or write transaction.
*/
p->inTrans = TRANS_NONE;
unlockBtreeIfUnused(pBt);
btreeIntegrity(p);
sqlite3BtreeLeave(p);
return SQLITE_OK;
}
/*
** Do both phases of a commit.
*/
int sqlite3BtreeCommit(Btree *p){
int rc;
sqlite3BtreeEnter(p);
rc = sqlite3BtreeCommitPhaseOne(p, 0);
if( rc==SQLITE_OK ){
rc = sqlite3BtreeCommitPhaseTwo(p);
}
sqlite3BtreeLeave(p);
return rc;
}
#ifndef NDEBUG
/*
** Return the number of write-cursors open on this handle. This is for use
** in assert() expressions, so it is only compiled if NDEBUG is not
** defined.
**
** For the purposes of this routine, a write-cursor is any cursor that
** is capable of writing to the databse. That means the cursor was
** originally opened for writing and the cursor has not be disabled
** by having its state changed to CURSOR_FAULT.
*/
static int countWriteCursors(BtShared *pBt){
BtCursor *pCur;
int r = 0;
for(pCur=pBt->pCursor; pCur; pCur=pCur->pNext){
if( pCur->wrFlag && pCur->eState!=CURSOR_FAULT ) r++;
}
return r;
}
#endif
/*
** This routine sets the state to CURSOR_FAULT and the error
** code to errCode for every cursor on BtShared that pBtree
** references.
**
** Every cursor is tripped, including cursors that belong
** to other database connections that happen to be sharing
** the cache with pBtree.
**
** This routine gets called when a rollback occurs.
** All cursors using the same cache must be tripped
** to prevent them from trying to use the btree after
** the rollback. The rollback may have deleted tables
** or moved root pages, so it is not sufficient to
** save the state of the cursor. The cursor must be
** invalidated.
*/
void sqlite3BtreeTripAllCursors(Btree *pBtree, int errCode){
BtCursor *p;
sqlite3BtreeEnter(pBtree);
for(p=pBtree->pBt->pCursor; p; p=p->pNext){
clearCursorPosition(p);
p->eState = CURSOR_FAULT;
p->skip = errCode;
}
sqlite3BtreeLeave(pBtree);
}
/*
** Rollback the transaction in progress. All cursors will be
** invalided by this operation. Any attempt to use a cursor
** that was open at the beginning of this operation will result
** in an error.
**
** This will release the write lock on the database file. If there
** are no active cursors, it also releases the read lock.
*/
int sqlite3BtreeRollback(Btree *p){
int rc;
BtShared *pBt = p->pBt;
MemPage *pPage1;
sqlite3BtreeEnter(p);
pBt->db = p->db;
rc = saveAllCursors(pBt, 0, 0);
#ifndef SQLITE_OMIT_SHARED_CACHE
if( rc!=SQLITE_OK ){
/* This is a horrible situation. An IO or malloc() error occured whilst
** trying to save cursor positions. If this is an automatic rollback (as
** the result of a constraint, malloc() failure or IO error) then
** the cache may be internally inconsistent (not contain valid trees) so
** we cannot simply return the error to the caller. Instead, abort
** all queries that may be using any of the cursors that failed to save.
*/
sqlite3BtreeTripAllCursors(p, rc);
}
#endif
btreeIntegrity(p);
unlockAllTables(p);
if( p->inTrans==TRANS_WRITE ){
int rc2;
#ifndef SQLITE_OMIT_AUTOVACUUM
pBt->nTrunc = 0;
#endif
assert( TRANS_WRITE==pBt->inTransaction );
rc2 = sqlite3PagerRollback(pBt->pPager);
if( rc2!=SQLITE_OK ){
rc = rc2;
}
/* The rollback may have destroyed the pPage1->aData value. So
** call sqlite3BtreeGetPage() on page 1 again to make
** sure pPage1->aData is set correctly. */
if( sqlite3BtreeGetPage(pBt, 1, &pPage1, 0)==SQLITE_OK ){
releasePage(pPage1);
}
assert( countWriteCursors(pBt)==0 );
pBt->inTransaction = TRANS_READ;
}
if( p->inTrans!=TRANS_NONE ){
assert( pBt->nTransaction>0 );
pBt->nTransaction--;
if( 0==pBt->nTransaction ){
pBt->inTransaction = TRANS_NONE;
}
}
p->inTrans = TRANS_NONE;
pBt->inStmt = 0;
unlockBtreeIfUnused(pBt);
btreeIntegrity(p);
sqlite3BtreeLeave(p);
return rc;
}
/*
** Start a statement subtransaction. The subtransaction can
** can be rolled back independently of the main transaction.
** You must start a transaction before starting a subtransaction.
** The subtransaction is ended automatically if the main transaction
** commits or rolls back.
**
** Only one subtransaction may be active at a time. It is an error to try
** to start a new subtransaction if another subtransaction is already active.
**
** Statement subtransactions are used around individual SQL statements
** that are contained within a BEGIN...COMMIT block. If a constraint
** error occurs within the statement, the effect of that one statement
** can be rolled back without having to rollback the entire transaction.
*/
int sqlite3BtreeBeginStmt(Btree *p){
int rc;
BtShared *pBt = p->pBt;
sqlite3BtreeEnter(p);
pBt->db = p->db;
if( (p->inTrans!=TRANS_WRITE) || pBt->inStmt ){
rc = pBt->readOnly ? SQLITE_READONLY : SQLITE_ERROR;
}else{
assert( pBt->inTransaction==TRANS_WRITE );
rc = pBt->readOnly ? SQLITE_OK : sqlite3PagerStmtBegin(pBt->pPager);
pBt->inStmt = 1;
}
sqlite3BtreeLeave(p);
return rc;
}
/*
** Commit the statment subtransaction currently in progress. If no
** subtransaction is active, this is a no-op.
*/
int sqlite3BtreeCommitStmt(Btree *p){
int rc;
BtShared *pBt = p->pBt;
sqlite3BtreeEnter(p);
pBt->db = p->db;
if( pBt->inStmt && !pBt->readOnly ){
rc = sqlite3PagerStmtCommit(pBt->pPager);
}else{
rc = SQLITE_OK;
}
pBt->inStmt = 0;
sqlite3BtreeLeave(p);
return rc;
}
/*
** Rollback the active statement subtransaction. If no subtransaction
** is active this routine is a no-op.
**
** All cursors will be invalidated by this operation. Any attempt
** to use a cursor that was open at the beginning of this operation
** will result in an error.
*/
int sqlite3BtreeRollbackStmt(Btree *p){
int rc = SQLITE_OK;
BtShared *pBt = p->pBt;
sqlite3BtreeEnter(p);
pBt->db = p->db;
if( pBt->inStmt && !pBt->readOnly ){
rc = sqlite3PagerStmtRollback(pBt->pPager);
assert( countWriteCursors(pBt)==0 );
pBt->inStmt = 0;
}
sqlite3BtreeLeave(p);
return rc;
}
/*
** Create a new cursor for the BTree whose root is on the page
** iTable. The act of acquiring a cursor gets a read lock on
** the database file.
**
** If wrFlag==0, then the cursor can only be used for reading.
** If wrFlag==1, then the cursor can be used for reading or for
** writing if other conditions for writing are also met. These
** are the conditions that must be met in order for writing to
** be allowed:
**
** 1: The cursor must have been opened with wrFlag==1
**
** 2: Other database connections that share the same pager cache
** but which are not in the READ_UNCOMMITTED state may not have
** cursors open with wrFlag==0 on the same table. Otherwise
** the changes made by this write cursor would be visible to
** the read cursors in the other database connection.
**
** 3: The database must be writable (not on read-only media)
**
** 4: There must be an active transaction.
**
** No checking is done to make sure that page iTable really is the
** root page of a b-tree. If it is not, then the cursor acquired
** will not work correctly.
*/
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;
BtShared *pBt = p->pBt;
assert( sqlite3BtreeHoldsMutex(p) );
if( wrFlag ){
if( pBt->readOnly ){
return SQLITE_READONLY;
}
if( checkReadLocks(p, iTable, 0) ){
return SQLITE_LOCKED;
}
}
if( pBt->pPage1==0 ){
rc = lockBtreeWithRetry(p);
if( rc!=SQLITE_OK ){
return rc;
}
if( pBt->readOnly && wrFlag ){
return SQLITE_READONLY;
}
}
pCur->pgnoRoot = (Pgno)iTable;
if( iTable==1 && sqlite3PagerPagecount(pBt->pPager)==0 ){
rc = SQLITE_EMPTY;
goto create_cursor_exception;
}
rc = getAndInitPage(pBt, pCur->pgnoRoot, &pCur->pPage, 0);
if( rc!=SQLITE_OK ){
goto create_cursor_exception;
}
/* Now that no other errors can occur, finish filling in the BtCursor
** variables, link the cursor into the BtShared list and set *ppCur (the
** output argument to this function).
*/
pCur->pKeyInfo = pKeyInfo;
pCur->pBtree = p;
pCur->pBt = pBt;
pCur->wrFlag = wrFlag;
pCur->pNext = pBt->pCursor;
if( pCur->pNext ){
pCur->pNext->pPrev = pCur;
}
pBt->pCursor = pCur;
pCur->eState = CURSOR_INVALID;
return SQLITE_OK;
create_cursor_exception:
if( pCur ){
releasePage(pCur->pPage);
}
unlockBtreeIfUnused(pBt);
return rc;
}
int sqlite3BtreeCursor(
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 xCompare() */
BtCursor *pCur /* Write new cursor here */
){
int rc;
sqlite3BtreeEnter(p);
p->pBt->db = p->db;
rc = btreeCursor(p, iTable, wrFlag, pKeyInfo, pCur);
sqlite3BtreeLeave(p);
return rc;
}
int sqlite3BtreeCursorSize(){
return sizeof(BtCursor);
}
/*
** Close a cursor. The read lock on the database file is released
** when the last cursor is closed.
*/
int sqlite3BtreeCloseCursor(BtCursor *pCur){
Btree *pBtree = pCur->pBtree;
if( pBtree ){
BtShared *pBt = pCur->pBt;
sqlite3BtreeEnter(pBtree);
pBt->db = pBtree->db;
clearCursorPosition(pCur);
if( pCur->pPrev ){
pCur->pPrev->pNext = pCur->pNext;
}else{
pBt->pCursor = pCur->pNext;
}
if( pCur->pNext ){
pCur->pNext->pPrev = pCur->pPrev;
}
releasePage(pCur->pPage);
unlockBtreeIfUnused(pBt);
invalidateOverflowCache(pCur);
/* sqlite3_free(pCur); */
sqlite3BtreeLeave(pBtree);
}
return SQLITE_OK;
}
/*
** Make a temporary cursor by filling in the fields of pTempCur.
** The temporary cursor is not on the cursor list for the Btree.
*/
void sqlite3BtreeGetTempCursor(BtCursor *pCur, BtCursor *pTempCur){
assert( cursorHoldsMutex(pCur) );
memcpy(pTempCur, pCur, sizeof(*pCur));
pTempCur->pNext = 0;
pTempCur->pPrev = 0;
if( pTempCur->pPage ){
sqlite3PagerRef(pTempCur->pPage->pDbPage);
}
}
/*
** Delete a temporary cursor such as was made by the CreateTemporaryCursor()
** function above.
*/
void sqlite3BtreeReleaseTempCursor(BtCursor *pCur){
assert( cursorHoldsMutex(pCur) );
if( pCur->pPage ){
sqlite3PagerUnref(pCur->pPage->pDbPage);
}
}
/*
** Make sure the BtCursor* given in the argument has a valid
** BtCursor.info structure. If it is not already valid, call
** sqlite3BtreeParseCell() to fill it in.
**
** BtCursor.info is a cache of the information in the current cell.
** Using this cache reduces the number of calls to sqlite3BtreeParseCell().
**
** 2007-06-25: There is a bug in some versions of MSVC that cause the
** compiler to crash when getCellInfo() is implemented as a macro.
** But there is a measureable speed advantage to using the macro on gcc
** (when less compiler optimizations like -Os or -O0 are used and the
** compiler is not doing agressive inlining.) So we use a real function
** for MSVC and a macro for everything else. Ticket #2457.
*/
#ifndef NDEBUG
static void assertCellInfo(BtCursor *pCur){
CellInfo info;
memset(&info, 0, sizeof(info));
sqlite3BtreeParseCell(pCur->pPage, pCur->idx, &info);
assert( memcmp(&info, &pCur->info, sizeof(info))==0 );
}
#else
#define assertCellInfo(x)
#endif
#ifdef _MSC_VER
/* Use a real function in MSVC to work around bugs in that compiler. */
static void getCellInfo(BtCursor *pCur){
if( pCur->info.nSize==0 ){
sqlite3BtreeParseCell(pCur->pPage, pCur->idx, &pCur->info);
pCur->validNKey = 1;
}else{
assertCellInfo(pCur);
}
}
#else /* if not _MSC_VER */
/* Use a macro in all other compilers so that the function is inlined */
#define getCellInfo(pCur)
if( pCur->info.nSize==0 ){
sqlite3BtreeParseCell(pCur->pPage, pCur->idx, &pCur->info);
pCur->validNKey = 1;
}else{
assertCellInfo(pCur);
}
#endif /* _MSC_VER */
/*
** Set *pSize to the size of the buffer needed to hold the value of
** the key for the current entry. If the cursor is not pointing
** to a valid entry, *pSize is set to 0.
**
** For a table with the INTKEY flag set, this routine returns the key
** itself, not the number of bytes in the key.
*/
int sqlite3BtreeKeySize(BtCursor *pCur, i64 *pSize){
int rc;
assert( cursorHoldsMutex(pCur) );
rc = restoreOrClearCursorPosition(pCur);
if( rc==SQLITE_OK ){
assert( pCur->eState==CURSOR_INVALID || pCur->eState==CURSOR_VALID );
if( pCur->eState==CURSOR_INVALID ){
*pSize = 0;
}else{
getCellInfo(pCur);
*pSize = pCur->info.nKey;
}
}
return rc;
}
/*
** Set *pSize to the number of bytes of data in the entry the
** cursor currently points to. Always return SQLITE_OK.
** Failure is not possible. If the cursor is not currently
** pointing to an entry (which can happen, for example, if
** the database is empty) then *pSize is set to 0.
*/
int sqlite3BtreeDataSize(BtCursor *pCur, u32 *pSize){
int rc;
assert( cursorHoldsMutex(pCur) );
rc = restoreOrClearCursorPosition(pCur);
if( rc==SQLITE_OK ){
assert( pCur->eState==CURSOR_INVALID || pCur->eState==CURSOR_VALID );
if( pCur->eState==CURSOR_INVALID ){
/* Not pointing at a valid entry - set *pSize to 0. */
*pSize = 0;
}else{
getCellInfo(pCur);
*pSize = pCur->info.nData;
}
}
return rc;
}
/*
** Given the page number of an overflow page in the database (parameter
** ovfl), this function finds the page number of the next page in the
** linked list of overflow pages. If possible, it uses the auto-vacuum
** pointer-map data instead of reading the content of page ovfl to do so.
**
** If an error occurs an SQLite error code is returned. Otherwise:
**
** Unless pPgnoNext is NULL, the page number of the next overflow
** page in the linked list is written to *pPgnoNext. If page ovfl
** is the last page in its linked list, *pPgnoNext is set to zero.
**
** If ppPage is not NULL, *ppPage is set to the MemPage* handle
** for page ovfl. The underlying pager page may have been requested
** with the noContent flag set, so the page data accessable via
** this handle may not be trusted.
*/
static int getOverflowPage(
BtShared *pBt,
Pgno ovfl, /* Overflow page */
MemPage **ppPage, /* OUT: MemPage handle */
Pgno *pPgnoNext /* OUT: Next overflow page number */
){
Pgno next = 0;
int rc;
assert( sqlite3_mutex_held(pBt->mutex) );
/* One of these must not be NULL. Otherwise, why call this function? */
assert(ppPage || pPgnoNext);
/* If pPgnoNext is NULL, then this function is being called to obtain
** a MemPage* reference only. No page-data is required in this case.
*/
if( !pPgnoNext ){
return sqlite3BtreeGetPage(pBt, ovfl, ppPage, 1);
}
#ifndef SQLITE_OMIT_AUTOVACUUM
/* Try to find the next page in the overflow list using the
** autovacuum pointer-map pages. Guess that the next page in
** the overflow list is page number (ovfl+1). If that guess turns
** out to be wrong, fall back to loading the data of page
** number ovfl to determine the next page number.
*/
if( pBt->autoVacuum ){
Pgno pgno;
Pgno iGuess = ovfl+1;
u8 eType;
while( PTRMAP_ISPAGE(pBt, iGuess) || iGuess==PENDING_BYTE_PAGE(pBt) ){
iGuess++;
}
if( iGuess<=sqlite3PagerPagecount(pBt->pPager) ){
rc = ptrmapGet(pBt, iGuess, &eType, &pgno);
if( rc!=SQLITE_OK ){
return rc;
}
if( eType==PTRMAP_OVERFLOW2 && pgno==ovfl ){
next = iGuess;
}
}
}
#endif
if( next==0 || ppPage ){
MemPage *pPage = 0;
rc = sqlite3BtreeGetPage(pBt, ovfl, &pPage, next!=0);
assert(rc==SQLITE_OK || pPage==0);
if( next==0 && rc==SQLITE_OK ){
next = get4byte(pPage->aData);
}
if( ppPage ){
*ppPage = pPage;
}else{
releasePage(pPage);
}
}
*pPgnoNext = next;
return rc;
}
/*
** Copy data from a buffer to a page, or from a page to a buffer.
**
** pPayload is a pointer to data stored on database page pDbPage.
** If argument eOp is false, then nByte bytes of data are copied
** from pPayload to the buffer pointed at by pBuf. If eOp is true,
** then sqlite3PagerWrite() is called on pDbPage and nByte bytes
** of data are copied from the buffer pBuf to pPayload.
**
** SQLITE_OK is returned on success, otherwise an error code.
*/
static int copyPayload(
void *pPayload, /* Pointer to page data */
void *pBuf, /* Pointer to buffer */
int nByte, /* Number of bytes to copy */
int eOp, /* 0 -> copy from page, 1 -> copy to page */
DbPage *pDbPage /* Page containing pPayload */
){
if( eOp ){
/* Copy data from buffer to page (a write operation) */
int rc = sqlite3PagerWrite(pDbPage);
if( rc!=SQLITE_OK ){
return rc;
}
memcpy(pPayload, pBuf, nByte);
}else{
/* Copy data from page to buffer (a read operation) */
memcpy(pBuf, pPayload, nByte);
}
return SQLITE_OK;
}
/*
** This function is used to read or overwrite payload information
** for the entry that the pCur cursor is pointing to. If the eOp
** parameter is 0, this is a read operation (data copied into
** buffer pBuf). If it is non-zero, a write (data copied from
** buffer pBuf).
**
** A total of "amt" bytes are read or written beginning at "offset".
** Data is read to or from the buffer pBuf.
**
** This routine does not make a distinction between key and data.
** It just reads or writes bytes from the payload area. Data might
** appear on the main page or be scattered out on multiple overflow
** pages.
**
** If the BtCursor.isIncrblobHandle flag is set, and the current
** cursor entry uses one or more overflow pages, this function
** allocates space for and lazily popluates the overflow page-list
** cache array (BtCursor.aOverflow). Subsequent calls use this
** cache to make seeking to the supplied offset more efficient.
**
** Once an overflow page-list cache has been allocated, it may be
** invalidated if some other cursor writes to the same table, or if
** the cursor is moved to a different row. Additionally, in auto-vacuum
** mode, the following events may invalidate an overflow page-list cache.
**
** * An incremental vacuum,
** * A commit in auto_vacuum="full" mode,
** * Creating a table (may require moving an overflow page).
*/
static int accessPayload(
BtCursor *pCur, /* Cursor pointing to entry to read from */
int offset, /* Begin reading this far into payload */
int amt, /* Read this many bytes */
unsigned char *pBuf, /* Write the bytes into this buffer */
int skipKey, /* offset begins at data if this is true */
int eOp /* zero to read. non-zero to write. */
){
unsigned char *aPayload;
int rc = SQLITE_OK;
u32 nKey;
int iIdx = 0;
MemPage *pPage = pCur->pPage; /* Btree page of current cursor entry */
BtShared *pBt; /* Btree this cursor belongs to */
assert( pPage );
assert( pCur->eState==CURSOR_VALID );
assert( pCur->idx>=0 && pCur->idx<pPage->nCell );
assert( offset>=0 );
assert( cursorHoldsMutex(pCur) );
getCellInfo(pCur);
aPayload = pCur->info.pCell + pCur->info.nHeader;
nKey = (pPage->intKey ? 0 : pCur->info.nKey);
if( skipKey ){
offset += nKey;
}
if( offset+amt > nKey+pCur->info.nData ){
/* Trying to read or write past the end of the data is an error */
return SQLITE_ERROR;
}
/* Check if data must be read/written to/from the btree page itself. */
if( offset<pCur->info.nLocal ){
int a = amt;
if( a+offset>pCur->info.nLocal ){
a = pCur->info.nLocal - offset;
}
rc = copyPayload(&aPayload[offset], pBuf, a, eOp, pPage->pDbPage);
offset = 0;
pBuf += a;
amt -= a;
}else{
offset -= pCur->info.nLocal;
}
pBt = pCur->pBt;
if( rc==SQLITE_OK && amt>0 ){
const int ovflSize = pBt->usableSize - 4; /* Bytes content per ovfl page */
Pgno nextPage;
nextPage = get4byte(&aPayload[pCur->info.nLocal]);
#ifndef SQLITE_OMIT_INCRBLOB
/* If the isIncrblobHandle flag is set and the BtCursor.aOverflow[]
** has not been allocated, allocate it now. The array is sized at
** one entry for each overflow page in the overflow chain. The
** page number of the first overflow page is stored in aOverflow[0],
** etc. A value of 0 in the aOverflow[] array means "not yet known"
** (the cache is lazily populated).
*/
if( pCur->isIncrblobHandle && !pCur->aOverflow ){
int nOvfl = (pCur->info.nPayload-pCur->info.nLocal+ovflSize-1)/ovflSize;
pCur->aOverflow = (Pgno *)sqlite3MallocZero(sizeof(Pgno)*nOvfl);
if( nOvfl && !pCur->aOverflow ){
rc = SQLITE_NOMEM;
}
}
/* If the overflow page-list cache has been allocated and the
** entry for the first required overflow page is valid, skip
** directly to it.
*/
if( pCur->aOverflow && pCur->aOverflow[offset/ovflSize] ){
iIdx = (offset/ovflSize);
nextPage = pCur->aOverflow[iIdx];
offset = (offset%ovflSize);
}
#endif
for( ; rc==SQLITE_OK && amt>0 && nextPage; iIdx++){
#ifndef SQLITE_OMIT_INCRBLOB
/* If required, populate the overflow page-list cache. */
if( pCur->aOverflow ){
assert(!pCur->aOverflow[iIdx] || pCur->aOverflow[iIdx]==nextPage);
pCur->aOverflow[iIdx] = nextPage;
}
#endif
if( offset>=ovflSize ){
/* The only reason to read this page is to obtain the page
** number for the next page in the overflow chain. The page
** data is not required. So first try to lookup the overflow
** page-list cache, if any, then fall back to the getOverflowPage()
** function.
*/
#ifndef SQLITE_OMIT_INCRBLOB
if( pCur->aOverflow && pCur->aOverflow[iIdx+1] ){
nextPage = pCur->aOverflow[iIdx+1];
} else
#endif
rc = getOverflowPage(pBt, nextPage, 0, &nextPage);
offset -= ovflSize;
}else{
/* Need to read this page properly. It contains some of the
** range of data that is being read (eOp==0) or written (eOp!=0).
*/
DbPage *pDbPage;
int a = amt;
rc = sqlite3PagerGet(pBt->pPager, nextPage, &pDbPage);
if( rc==SQLITE_OK ){
aPayload = sqlite3PagerGetData(pDbPage);
nextPage = get4byte(aPayload);
if( a + offset > ovflSize ){
a = ovflSize - offset;
}
rc = copyPayload(&aPayload[offset+4], pBuf, a, eOp, pDbPage);
sqlite3PagerUnref(pDbPage);
offset = 0;
amt -= a;
pBuf += a;
}
}
}
}
if( rc==SQLITE_OK && amt>0 ){
return SQLITE_CORRUPT_BKPT;
}
return rc;
}
/*
** Read part of the key associated with cursor pCur. Exactly
** "amt" bytes will be transfered into pBuf[]. The transfer
** begins at "offset".
**
** Return SQLITE_OK on success or an error code if anything goes
** wrong. An error is returned if "offset+amt" is larger than
** the available payload.
*/
int sqlite3BtreeKey(BtCursor *pCur, u32 offset, u32 amt, void *pBuf){
int rc;
assert( cursorHoldsMutex(pCur) );
rc = restoreOrClearCursorPosition(pCur);
if( rc==SQLITE_OK ){
assert( pCur->eState==CURSOR_VALID );
assert( pCur->pPage!=0 );
if( pCur->pPage->intKey ){
return SQLITE_CORRUPT_BKPT;
}
assert( pCur->pPage->intKey==0 );
assert( pCur->idx>=0 && pCur->idx<pCur->pPage->nCell );
rc = accessPayload(pCur, offset, amt, (unsigned char*)pBuf, 0, 0);
}
return rc;
}
/*
** Read part of the data associated with cursor pCur. Exactly
** "amt" bytes will be transfered into pBuf[]. The transfer
** begins at "offset".
**
** Return SQLITE_OK on success or an error code if anything goes
** wrong. An error is returned if "offset+amt" is larger than
** the available payload.
*/
int sqlite3BtreeData(BtCursor *pCur, u32 offset, u32 amt, void *pBuf){
int rc;
assert( cursorHoldsMutex(pCur) );
rc = restoreOrClearCursorPosition(pCur);
if( rc==SQLITE_OK ){
assert( pCur->eState==CURSOR_VALID );
assert( pCur->pPage!=0 );
assert( pCur->idx>=0 && pCur->idx<pCur->pPage->nCell );
rc = accessPayload(pCur, offset, amt, pBuf, 1, 0);
}
return rc;
}
/*
** Return a pointer to payload information from the entry that the
** pCur cursor is pointing to. The pointer is to the beginning of
** the key if skipKey==0 and it points to the beginning of data if
** skipKey==1. The number of bytes of available key/data is written
** into *pAmt. If *pAmt==0, then the value returned will not be
** a valid pointer.
**
** This routine is an optimization. It is common for the entire key
** and data to fit on the local page and for there to be no overflow
** pages. When that is so, this routine can be used to access the
** key and data without making a copy. If the key and/or data spills
** onto overflow pages, then accessPayload() must be used to reassembly
** the key/data and copy it into a preallocated buffer.
**
** The pointer returned by this routine looks directly into the cached
** page of the database. The data might change or move the next time
** any btree routine is called.
*/
static const unsigned char *fetchPayload(
BtCursor *pCur, /* Cursor pointing to entry to read from */
int *pAmt, /* Write the number of available bytes here */
int skipKey /* read beginning at data if this is true */
){
unsigned char *aPayload;
MemPage *pPage;
u32 nKey;
int nLocal;
assert( pCur!=0 && pCur->pPage!=0 );
assert( pCur->eState==CURSOR_VALID );
assert( cursorHoldsMutex(pCur) );
pPage = pCur->pPage;
assert( pCur->idx>=0 && pCur->idx<pPage->nCell );
getCellInfo(pCur);
aPayload = pCur->info.pCell;
aPayload += pCur->info.nHeader;
if( pPage->intKey ){
nKey = 0;
}else{
nKey = pCur->info.nKey;
}
if( skipKey ){
aPayload += nKey;
nLocal = pCur->info.nLocal - nKey;
}else{
nLocal = pCur->info.nLocal;
if( nLocal>nKey ){
nLocal = nKey;
}
}
*pAmt = nLocal;
return aPayload;
}
/*
** For the entry that cursor pCur is point to, return as
** many bytes of the key or data as are available on the local
** b-tree page. Write the number of available bytes into *pAmt.
**
** The pointer returned is ephemeral. The key/data may move
** or be destroyed on the next call to any Btree routine,
** including calls from other threads against the same cache.
** Hence, a mutex on the BtShared should be held prior to calling
** this routine.
**
** These routines is used to get quick access to key and data
** in the common case where no overflow pages are used.
*/
const void *sqlite3BtreeKeyFetch(BtCursor *pCur, int *pAmt){
assert( cursorHoldsMutex(pCur) );
if( pCur->eState==CURSOR_VALID ){
return (const void*)fetchPayload(pCur, pAmt, 0);
}
return 0;
}
const void *sqlite3BtreeDataFetch(BtCursor *pCur, int *pAmt){
assert( cursorHoldsMutex(pCur) );
if( pCur->eState==CURSOR_VALID ){
return (const void*)fetchPayload(pCur, pAmt, 1);
}
return 0;
}
/*
** Move the cursor down to a new child page. The newPgno argument is the
** page number of the child page to move to.
*/
static int moveToChild(BtCursor *pCur, u32 newPgno){
int rc;
MemPage *pNewPage;
MemPage *pOldPage;
BtShared *pBt = pCur->pBt;
assert( cursorHoldsMutex(pCur) );
assert( pCur->eState==CURSOR_VALID );
rc = getAndInitPage(pBt, newPgno, &pNewPage, pCur->pPage);
if( rc ) return rc;
pNewPage->idxParent = pCur->idx;
pOldPage = pCur->pPage;
pOldPage->idxShift = 0;
releasePage(pOldPage);
pCur->pPage = pNewPage;
pCur->idx = 0;
pCur->info.nSize = 0;
pCur->validNKey = 0;
if( pNewPage->nCell<1 ){
return SQLITE_CORRUPT_BKPT;
}
return SQLITE_OK;
}
/*
** Return true if the page is the virtual root of its table.
**
** The virtual root page is the root page for most tables. But
** for the table rooted on page 1, sometime the real root page
** is empty except for the right-pointer. In such cases the
** virtual root page is the page that the right-pointer of page
** 1 is pointing to.
*/
int sqlite3BtreeIsRootPage(MemPage *pPage){
MemPage *pParent;
assert( sqlite3_mutex_held(pPage->pBt->mutex) );
pParent = pPage->pParent;
if( pParent==0 ) return 1;
if( pParent->pgno>1 ) return 0;
if( get2byte(&pParent->aData[pParent->hdrOffset+3])==0 ) return 1;
return 0;
}
/*
** Move the cursor up to the parent page.
**
** pCur->idx is set to the cell index that contains the pointer
** to the page we are coming from. If we are coming from the
** right-most child page then pCur->idx is set to one more than
** the largest cell index.
*/
void sqlite3BtreeMoveToParent(BtCursor *pCur){
MemPage *pParent;
MemPage *pPage;
int idxParent;
assert( cursorHoldsMutex(pCur) );
assert( pCur->eState==CURSOR_VALID );
pPage = pCur->pPage;
assert( pPage!=0 );
assert( !sqlite3BtreeIsRootPage(pPage) );
pParent = pPage->pParent;
assert( pParent!=0 );
idxParent = pPage->idxParent;
sqlite3PagerRef(pParent->pDbPage);
releasePage(pPage);
pCur->pPage = pParent;
pCur->info.nSize = 0;
pCur->validNKey = 0;
assert( pParent->idxShift==0 );
pCur->idx = idxParent;
}
/*
** Move the cursor to the root page
*/
static int moveToRoot(BtCursor *pCur){
MemPage *pRoot;
int rc = SQLITE_OK;
Btree *p = pCur->pBtree;
BtShared *pBt = p->pBt;
assert( cursorHoldsMutex(pCur) );
assert( CURSOR_INVALID < CURSOR_REQUIRESEEK );
assert( CURSOR_VALID < CURSOR_REQUIRESEEK );
assert( CURSOR_FAULT > CURSOR_REQUIRESEEK );
if( pCur->eState>=CURSOR_REQUIRESEEK ){
if( pCur->eState==CURSOR_FAULT ){
return pCur->skip;
}
clearCursorPosition(pCur);
}
pRoot = pCur->pPage;
if( pRoot && pRoot->pgno==pCur->pgnoRoot ){
assert( pRoot->isInit );
}else{
if(
SQLITE_OK!=(rc = getAndInitPage(pBt, pCur->pgnoRoot, &pRoot, 0))
){
pCur->eState = CURSOR_INVALID;
return rc;
}
releasePage(pCur->pPage);
pCur->pPage = pRoot;
}
pCur->idx = 0;
pCur->info.nSize = 0;
pCur->atLast = 0;
pCur->validNKey = 0;
if( pRoot->nCell==0 && !pRoot->leaf ){
Pgno subpage;
assert( pRoot->pgno==1 );
subpage = get4byte(&pRoot->aData[pRoot->hdrOffset+8]);
assert( subpage>0 );
pCur->eState = CURSOR_VALID;
rc = moveToChild(pCur, subpage);
}
pCur->eState = ((pCur->pPage->nCell>0)?CURSOR_VALID:CURSOR_INVALID);
return rc;
}
/*
** Move the cursor down to the left-most leaf entry beneath the
** entry to which it is currently pointing.
**
** The left-most leaf is the one with the smallest key - the first
** in ascending order.
*/
static int moveToLeftmost(BtCursor *pCur){
Pgno pgno;
int rc = SQLITE_OK;
MemPage *pPage;
assert( cursorHoldsMutex(pCur) );
assert( pCur->eState==CURSOR_VALID );
while( rc==SQLITE_OK && !(pPage = pCur->pPage)->leaf ){
assert( pCur->idx>=0 && pCur->idx<pPage->nCell );
pgno = get4byte(findCell(pPage, pCur->idx));
rc = moveToChild(pCur, pgno);
}
return rc;
}
/*
** Move the cursor down to the right-most leaf entry beneath the
** page to which it is currently pointing. Notice the difference
** between moveToLeftmost() and moveToRightmost(). moveToLeftmost()
** finds the left-most entry beneath the *entry* whereas moveToRightmost()
** finds the right-most entry beneath the *page*.
**
** The right-most entry is the one with the largest key - the last
** key in ascending order.
*/
static int moveToRightmost(BtCursor *pCur){
Pgno pgno;
int rc = SQLITE_OK;
MemPage *pPage;
assert( cursorHoldsMutex(pCur) );
assert( pCur->eState==CURSOR_VALID );
while( rc==SQLITE_OK && !(pPage = pCur->pPage)->leaf ){
pgno = get4byte(&pPage->aData[pPage->hdrOffset+8]);
pCur->idx = pPage->nCell;
rc = moveToChild(pCur, pgno);
}
if( rc==SQLITE_OK ){
pCur->idx = pPage->nCell - 1;
pCur->info.nSize = 0;
pCur->validNKey = 0;
}
return SQLITE_OK;
}
/* Move the cursor to the first entry in the table. Return SQLITE_OK
** on success. Set *pRes to 0 if the cursor actually points to something
** or set *pRes to 1 if the table is empty.
*/
int sqlite3BtreeFirst(BtCursor *pCur, int *pRes){
int rc;
assert( cursorHoldsMutex(pCur) );
assert( sqlite3_mutex_held(pCur->pBtree->db->mutex) );
rc = moveToRoot(pCur);
if( rc==SQLITE_OK ){
if( pCur->eState==CURSOR_INVALID ){
assert( pCur->pPage->nCell==0 );
*pRes = 1;
rc = SQLITE_OK;
}else{
assert( pCur->pPage->nCell>0 );
*pRes = 0;
rc = moveToLeftmost(pCur);
}
}
return rc;
}
/* Move the cursor to the last entry in the table. Return SQLITE_OK
** on success. Set *pRes to 0 if the cursor actually points to something
** or set *pRes to 1 if the table is empty.
*/
int sqlite3BtreeLast(BtCursor *pCur, int *pRes){
int rc;
assert( cursorHoldsMutex(pCur) );
assert( sqlite3_mutex_held(pCur->pBtree->db->mutex) );
rc = moveToRoot(pCur);
if( rc==SQLITE_OK ){
if( CURSOR_INVALID==pCur->eState ){
assert( pCur->pPage->nCell==0 );
*pRes = 1;
}else{
assert( pCur->eState==CURSOR_VALID );
*pRes = 0;
rc = moveToRightmost(pCur);
getCellInfo(pCur);
pCur->atLast = rc==SQLITE_OK;
}
}
return rc;
}
/* Move the cursor so that it points to an entry near the key
** specified by pKey/nKey/pUnKey. Return a success code.
**
** For INTKEY tables, only the nKey parameter is used. pKey
** and pUnKey must be NULL. For index tables, either pUnKey
** must point to a key that has already been unpacked, or else
** pKey/nKey describes a blob containing the key.
**
** If an exact match is not found, then the cursor is always
** left pointing at a leaf page which would hold the entry if it
** were present. The cursor might point to an entry that comes