add ar7 lzma loader

git-svn-id: svn://svn.openwrt.org/openwrt/trunk/openwrt@1557 3c298f89-4303-0410-b956-a3cf2f4a3e73

6 files changed, 880 insertions, 1325 deletions

diff --git a/target/linux/image/ar7/Makefile b/target/linux/image/ar7/Makefile
index 3cde04bc3..672530277 100644
--- a/target/linux/image/ar7/Makefile
+++ b/target/linux/image/ar7/Makefile
@@ -5,13 +5,14 @@ KDIR:=$(BUILD_DIR)/linux-$(KERNEL)-ar7
 PKG_BUILD_DIR:=$(BUILD_DIR)/ar7loader
 
 LOADADDR := 0x94020000
+KERNEL_ENTRY := 0x${shell nm $(KDIR)/linux-$(KERNEL)*/vmlinux | grep kernel_entry | cut -d' ' -f1}
 OUTPUT_FORMAT := elf32-tradlittlemips
 
 CFLAGS := -D__KERNEL__ -Wall -Wstrict-prototypes -Wno-trigraphs -Os \
 	-fno-strict-aliasing -fno-common -fomit-frame-pointer -G 0 -mno-abicalls -fno-pic \
 	-pipe -mlong-calls -fno-common \
 	-mabi=32 -march=mips32 -Wa,-32 -Wa,-march=mips32 -Wa,-mips32 -Wa,--trap \
-
+	-DLOADADDR=$(LOADADDR)
 
 $(PKG_BUILD_DIR):
 	mkdir -p $(PKG_BUILD_DIR)
@@ -24,6 +25,9 @@ $(PKG_BUILD_DIR)/ld.script: src/ld.script.in
 	sed -e 's/@@OUTPUT_FORMAT@@/$(OUTPUT_FORMAT)/' \
 	    -e 's/@@LOADADDR@@/$(LOADADDR)/' <$< >$@
 
+$(PKG_BUILD_DIR)/LzmaDecode.o: src/LzmaDecode.c
+	$(TARGET_CC) $(CFLAGS) -c -o $@ $<
+
 $(PKG_BUILD_DIR)/loader.o: src/loader.c
 	$(TARGET_CC) $(CFLAGS) -c -o $@ $<
 
@@ -33,10 +37,14 @@ $(PKG_BUILD_DIR)/srec2bin: src/srec2bin.c
 $(KDIR)/vmlinux.gz: $(KDIR)/vmlinux
 	gzip -c -vf9 < $< > $@
 
-$(BIN_DIR)/openwrt-ar7-zimage.bin: $(KDIR)/vmlinux.gz compile
+$(KDIR)/vmlinux.lzma: $(KDIR)/vmlinux
+	cat $^ | $(STAGING_DIR)/bin/lzma e -si -so -eos -lc1 -lp2 -pb2 > $@ || (rm -f $@ && false)
+
+$(BIN_DIR)/openwrt-ar7-zimage.bin: $(KDIR)/vmlinux.lzma compile
 	$(TARGET_CROSS)ld -T $(PKG_BUILD_DIR)/zimage.script -r -b binary $< -o $(KDIR)/zimage.o
-	$(TARGET_CROSS)ld -static -G 0 -no-warn-mismatch -R $(KDIR)/linux-$(KERNEL)*/vmlinux -T $(PKG_BUILD_DIR)/ld.script \
+	$(TARGET_CROSS)ld -static -G 0 --defsym kernel_entry=$(KERNEL_ENTRY) -T $(PKG_BUILD_DIR)/ld.script \
 		$(PKG_BUILD_DIR)/loader.o \
+		$(PKG_BUILD_DIR)/LzmaDecode.o \
 		$(KDIR)/zimage.o \
 		-o $(KDIR)/loader
 	$(TARGET_CROSS)objcopy -O srec $(KDIR)/loader $(KDIR)/ram_zimage.sre
@@ -49,8 +57,8 @@ ifeq ($(FS),jffs2-4MB)
 ALIGN:=bs=65536 conv=sync
 endif
 
-$(BIN_DIR)/openwrt-ar7-$(KERNEL)-$(FS).bin:
-	dd if=$(BIN_DIR)/openwrt-ar7-zimage.bin $(ALIGN) > $@
+$(BIN_DIR)/openwrt-ar7-$(KERNEL)-$(FS).bin: $(BIN_DIR)/openwrt-ar7-zimage.bin
+	dd if=$< $(ALIGN) > $@
 	cat $(BUILD_DIR)/linux-$(KERNEL)-ar7/root.$(FS) >> $@
 
 define pattern_template
@@ -70,6 +78,6 @@ clean:
 	rm -f $(BIN_DIR)/openwrt-ar7*
 
 prepare: $(PKG_BUILD_DIR) $(PKG_BUILD_DIR)/zimage.script $(PKG_BUILD_DIR)/ld.script
-compile: prepare $(PKG_BUILD_DIR)/loader.o $(PKG_BUILD_DIR)/srec2bin
+compile: prepare $(PKG_BUILD_DIR)/loader.o $(PKG_BUILD_DIR)/LzmaDecode.o $(PKG_BUILD_DIR)/srec2bin
 install: $(BIN_DIR)/openwrt-ar7-zimage.bin $(BIN_DIR)/openwrt-ar7-$(KERNEL)-$(FS).bin
-	
+
diff --git a/target/linux/image/ar7/src/LzmaDecode.c b/target/linux/image/ar7/src/LzmaDecode.c
new file mode 100644
index 000000000..951700bdd
--- /dev/null
+++ b/target/linux/image/ar7/src/LzmaDecode.c
@@ -0,0 +1,663 @@
+/*
+  LzmaDecode.c
+  LZMA Decoder
+  
+  LZMA SDK 4.05 Copyright (c) 1999-2004 Igor Pavlov (2004-08-25)
+  http://www.7-zip.org/
+
+  LZMA SDK is licensed under two licenses:
+  1) GNU Lesser General Public License (GNU LGPL)
+  2) Common Public License (CPL)
+  It means that you can select one of these two licenses and 
+  follow rules of that license.
+
+  SPECIAL EXCEPTION:
+  Igor Pavlov, as the author of this code, expressly permits you to 
+  statically or dynamically link your code (or bind by name) to the 
+  interfaces of this file without subjecting your linked code to the 
+  terms of the CPL or GNU LGPL. Any modifications or additions 
+  to this file, however, are subject to the LGPL or CPL terms.
+*/
+
+#include "LzmaDecode.h"
+
+#ifndef Byte
+#define Byte unsigned char
+#endif
+
+#define kNumTopBits 24
+#define kTopValue ((UInt32)1 << kNumTopBits)
+
+#define kNumBitModelTotalBits 11
+#define kBitModelTotal (1 << kNumBitModelTotalBits)
+#define kNumMoveBits 5
+
+typedef struct _CRangeDecoder
+{
+  Byte *Buffer;
+  Byte *BufferLim;
+  UInt32 Range;
+  UInt32 Code;
+  #ifdef _LZMA_IN_CB
+  ILzmaInCallback *InCallback;
+  int Result;
+  #endif
+  int ExtraBytes;
+} CRangeDecoder;
+
+Byte RangeDecoderReadByte(CRangeDecoder *rd)
+{
+  if (rd->Buffer == rd->BufferLim)
+  {
+    #ifdef _LZMA_IN_CB
+    UInt32 size;
+    rd->Result = rd->InCallback->Read(rd->InCallback, &rd->Buffer, &size);
+    rd->BufferLim = rd->Buffer + size;
+    if (size == 0)
+    #endif
+    {
+      rd->ExtraBytes = 1;
+      return 0xFF;
+    }
+  }
+  return (*rd->Buffer++);
+}
+
+/* #define ReadByte (*rd->Buffer++) */
+#define ReadByte (RangeDecoderReadByte(rd))
+
+void RangeDecoderInit(CRangeDecoder *rd,
+  #ifdef _LZMA_IN_CB
+    ILzmaInCallback *inCallback
+  #else
+    Byte *stream, UInt32 bufferSize
+  #endif
+    )
+{
+  int i;
+  #ifdef _LZMA_IN_CB
+  rd->InCallback = inCallback;
+  rd->Buffer = rd->BufferLim = 0;
+  #else
+  rd->Buffer = stream;
+  rd->BufferLim = stream + bufferSize;
+  #endif
+  rd->ExtraBytes = 0;
+  rd->Code = 0;
+  rd->Range = (0xFFFFFFFF);
+  for(i = 0; i < 5; i++)
+    rd->Code = (rd->Code << 8) | ReadByte;
+}
+
+#define RC_INIT_VAR UInt32 range = rd->Range; UInt32 code = rd->Code;        
+#define RC_FLUSH_VAR rd->Range = range; rd->Code = code;
+#define RC_NORMALIZE if (range < kTopValue) { range <<= 8; code = (code << 8) | ReadByte; }
+
+UInt32 RangeDecoderDecodeDirectBits(CRangeDecoder *rd, int numTotalBits)
+{
+  RC_INIT_VAR
+  UInt32 result = 0;
+  int i;
+  for (i = numTotalBits; i > 0; i--)
+  {
+    /* UInt32 t; */
+    range >>= 1;
+
+    result <<= 1;
+    if (code >= range)
+    {
+      code -= range;
+      result |= 1;
+    }
+    /*
+    t = (code - range) >> 31;
+    t &= 1;
+    code -= range & (t - 1);
+    result = (result + result) | (1 - t);
+    */
+    RC_NORMALIZE
+  }
+  RC_FLUSH_VAR
+  return result;
+}
+
+int RangeDecoderBitDecode(CProb *prob, CRangeDecoder *rd)
+{
+  UInt32 bound = (rd->Range >> kNumBitModelTotalBits) * *prob;
+  if (rd->Code < bound)
+  {
+    rd->Range = bound;
+    *prob += (kBitModelTotal - *prob) >> kNumMoveBits;
+    if (rd->Range < kTopValue)
+    {
+      rd->Code = (rd->Code << 8) | ReadByte;
+      rd->Range <<= 8;
+    }
+    return 0;
+  }
+  else
+  {
+    rd->Range -= bound;
+    rd->Code -= bound;
+    *prob -= (*prob) >> kNumMoveBits;
+    if (rd->Range < kTopValue)
+    {
+      rd->Code = (rd->Code << 8) | ReadByte;
+      rd->Range <<= 8;
+    }
+    return 1;
+  }
+}
+
+#define RC_GET_BIT2(prob, mi, A0, A1) \
+  UInt32 bound = (range >> kNumBitModelTotalBits) * *prob; \
+  if (code < bound) \
+    { A0; range = bound; *prob += (kBitModelTotal - *prob) >> kNumMoveBits; mi <<= 1; } \
+  else \
+    { A1; range -= bound; code -= bound; *prob -= (*prob) >> kNumMoveBits; mi = (mi + mi) + 1; } \
+  RC_NORMALIZE
+
+#define RC_GET_BIT(prob, mi) RC_GET_BIT2(prob, mi, ; , ;)               
+
+int RangeDecoderBitTreeDecode(CProb *probs, int numLevels, CRangeDecoder *rd)
+{
+  int mi = 1;
+  int i;
+  #ifdef _LZMA_LOC_OPT
+  RC_INIT_VAR
+  #endif
+  for(i = numLevels; i > 0; i--)
+  {
+    #ifdef _LZMA_LOC_OPT
+    CProb *prob = probs + mi;
+    RC_GET_BIT(prob, mi)
+    #else
+    mi = (mi + mi) + RangeDecoderBitDecode(probs + mi, rd);
+    #endif
+  }
+  #ifdef _LZMA_LOC_OPT
+  RC_FLUSH_VAR
+  #endif
+  return mi - (1 << numLevels);
+}
+
+int RangeDecoderReverseBitTreeDecode(CProb *probs, int numLevels, CRangeDecoder *rd)
+{
+  int mi = 1;
+  int i;
+  int symbol = 0;
+  #ifdef _LZMA_LOC_OPT
+  RC_INIT_VAR
+  #endif
+  for(i = 0; i < numLevels; i++)
+  {
+    #ifdef _LZMA_LOC_OPT
+    CProb *prob = probs + mi;
+    RC_GET_BIT2(prob, mi, ; , symbol |= (1 << i))
+    #else
+    int bit = RangeDecoderBitDecode(probs + mi, rd);
+    mi = mi + mi + bit;
+    symbol |= (bit << i);
+    #endif
+  }
+  #ifdef _LZMA_LOC_OPT
+  RC_FLUSH_VAR
+  #endif
+  return symbol;
+}
+
+Byte LzmaLiteralDecode(CProb *probs, CRangeDecoder *rd)
+{ 
+  int symbol = 1;
+  #ifdef _LZMA_LOC_OPT
+  RC_INIT_VAR
+  #endif
+  do
+  {
+    #ifdef _LZMA_LOC_OPT
+    CProb *prob = probs + symbol;
+    RC_GET_BIT(prob, symbol)
+    #else
+    symbol = (symbol + symbol) | RangeDecoderBitDecode(probs + symbol, rd);
+    #endif
+  }
+  while (symbol < 0x100);
+  #ifdef _LZMA_LOC_OPT
+  RC_FLUSH_VAR
+  #endif
+  return symbol;
+}
+
+Byte LzmaLiteralDecodeMatch(CProb *probs, CRangeDecoder *rd, Byte matchByte)
+{ 
+  int symbol = 1;
+  #ifdef _LZMA_LOC_OPT
+  RC_INIT_VAR
+  #endif
+  do
+  {
+    int bit;
+    int matchBit = (matchByte >> 7) & 1;
+    matchByte <<= 1;
+    #ifdef _LZMA_LOC_OPT
+    {
+      CProb *prob = probs + ((1 + matchBit) << 8) + symbol;
+      RC_GET_BIT2(prob, symbol, bit = 0, bit = 1)
+    }
+    #else
+    bit = RangeDecoderBitDecode(probs + ((1 + matchBit) << 8) + symbol, rd);
+    symbol = (symbol << 1) | bit;
+    #endif
+    if (matchBit != bit)
+    {
+      while (symbol < 0x100)
+      {
+        #ifdef _LZMA_LOC_OPT
+        CProb *prob = probs + symbol;
+        RC_GET_BIT(prob, symbol)
+        #else
+        symbol = (symbol + symbol) | RangeDecoderBitDecode(probs + symbol, rd);
+        #endif
+      }
+      break;
+    }
+  }
+  while (symbol < 0x100);
+  #ifdef _LZMA_LOC_OPT
+  RC_FLUSH_VAR
+  #endif
+  return symbol;
+}
+
+#define kNumPosBitsMax 4
+#define kNumPosStatesMax (1 << kNumPosBitsMax)
+
+#define kLenNumLowBits 3
+#define kLenNumLowSymbols (1 << kLenNumLowBits)
+#define kLenNumMidBits 3
+#define kLenNumMidSymbols (1 << kLenNumMidBits)
+#define kLenNumHighBits 8
+#define kLenNumHighSymbols (1 << kLenNumHighBits)
+
+#define LenChoice 0
+#define LenChoice2 (LenChoice + 1)
+#define LenLow (LenChoice2 + 1)
+#define LenMid (LenLow + (kNumPosStatesMax << kLenNumLowBits))
+#define LenHigh (LenMid + (kNumPosStatesMax << kLenNumMidBits))
+#define kNumLenProbs (LenHigh + kLenNumHighSymbols) 
+
+int LzmaLenDecode(CProb *p, CRangeDecoder *rd, int posState)
+{
+  if(RangeDecoderBitDecode(p + LenChoice, rd) == 0)
+    return RangeDecoderBitTreeDecode(p + LenLow +
+        (posState << kLenNumLowBits), kLenNumLowBits, rd);
+  if(RangeDecoderBitDecode(p + LenChoice2, rd) == 0)
+    return kLenNumLowSymbols + RangeDecoderBitTreeDecode(p + LenMid +
+        (posState << kLenNumMidBits), kLenNumMidBits, rd);
+  return kLenNumLowSymbols + kLenNumMidSymbols + 
+      RangeDecoderBitTreeDecode(p + LenHigh, kLenNumHighBits, rd);
+}
+
+#define kNumStates 12
+
+#define kStartPosModelIndex 4
+#define kEndPosModelIndex 14
+#define kNumFullDistances (1 << (kEndPosModelIndex >> 1))
+
+#define kNumPosSlotBits 6
+#define kNumLenToPosStates 4
+
+#define kNumAlignBits 4
+#define kAlignTableSize (1 << kNumAlignBits)
+
+#define kMatchMinLen 2
+
+#define IsMatch 0
+#define IsRep (IsMatch + (kNumStates << kNumPosBitsMax))
+#define IsRepG0 (IsRep + kNumStates)
+#define IsRepG1 (IsRepG0 + kNumStates)
+#define IsRepG2 (IsRepG1 + kNumStates)
+#define IsRep0Long (IsRepG2 + kNumStates)
+#define PosSlot (IsRep0Long + (kNumStates << kNumPosBitsMax))
+#define SpecPos (PosSlot + (kNumLenToPosStates << kNumPosSlotBits))
+#define Align (SpecPos + kNumFullDistances - kEndPosModelIndex)
+#define LenCoder (Align + kAlignTableSize)
+#define RepLenCoder (LenCoder + kNumLenProbs)
+#define Literal (RepLenCoder + kNumLenProbs)
+
+#if Literal != LZMA_BASE_SIZE
+StopCompilingDueBUG
+#endif
+
+#ifdef _LZMA_OUT_READ
+
+typedef struct _LzmaVarState
+{
+  CRangeDecoder RangeDecoder;
+  Byte *Dictionary;
+  UInt32 DictionarySize;
+  UInt32 DictionaryPos;
+  UInt32 GlobalPos;
+  UInt32 Reps[4];
+  int lc;
+  int lp;
+  int pb;
+  int State;
+  int PreviousIsMatch;
+  int RemainLen;
+} LzmaVarState;
+
+int LzmaDecoderInit(
+    unsigned char *buffer, UInt32 bufferSize,
+    int lc, int lp, int pb,
+    unsigned char *dictionary, UInt32 dictionarySize,
+    #ifdef _LZMA_IN_CB
+    ILzmaInCallback *inCallback
+    #else
+    unsigned char *inStream, UInt32 inSize
+    #endif
+    )
+{
+  LzmaVarState *vs = (LzmaVarState *)buffer;
+  CProb *p = (CProb *)(buffer + sizeof(LzmaVarState));
+  UInt32 numProbs = Literal + ((UInt32)LZMA_LIT_SIZE << (lc + lp));
+  UInt32 i;
+  if (bufferSize < numProbs * sizeof(CProb) + sizeof(LzmaVarState))
+    return LZMA_RESULT_NOT_ENOUGH_MEM;
+  vs->Dictionary = dictionary;
+  vs->DictionarySize = dictionarySize;
+  vs->DictionaryPos = 0;
+  vs->GlobalPos = 0;
+  vs->Reps[0] = vs->Reps[1] = vs->Reps[2] = vs->Reps[3] = 1;
+  vs->lc = lc;
+  vs->lp = lp;
+  vs->pb = pb;
+  vs->State = 0;
+  vs->PreviousIsMatch = 0;
+  vs->RemainLen = 0;
+  dictionary[dictionarySize - 1] = 0;
+  for (i = 0; i < numProbs; i++)
+    p[i] = kBitModelTotal >> 1; 
+  RangeDecoderInit(&vs->RangeDecoder, 
+      #ifdef _LZMA_IN_CB
+      inCallback
+      #else
+      inStream, inSize
+      #endif
+  );
+  return LZMA_RESULT_OK;
+}
+
+int LzmaDecode(unsigned char *buffer, 
+    unsigned char *outStream, UInt32 outSize,
+    UInt32 *outSizeProcessed)
+{
+  LzmaVarState *vs = (LzmaVarState *)buffer;
+  CProb *p = (CProb *)(buffer + sizeof(LzmaVarState));
+  CRangeDecoder rd = vs->RangeDecoder;
+  int state = vs->State;
+  int previousIsMatch = vs->PreviousIsMatch;
+  Byte previousByte;
+  UInt32 rep0 = vs->Reps[0], rep1 = vs->Reps[1], rep2 = vs->Reps[2], rep3 = vs->Reps[3];
+  UInt32 nowPos = 0;
+  UInt32 posStateMask = (1 << (vs->pb)) - 1;
+  UInt32 literalPosMask = (1 << (vs->lp)) - 1;
+  int lc = vs->lc;
+  int len = vs->RemainLen;
+  UInt32 globalPos = vs->GlobalPos;
+
+  Byte *dictionary = vs->Dictionary;
+  UInt32 dictionarySize = vs->DictionarySize;
+  UInt32 dictionaryPos = vs->DictionaryPos;
+
+  if (len == -1)
+  {
+    *outSizeProcessed = 0;
+    return LZMA_RESULT_OK;
+  }
+
+  while(len > 0 && nowPos < outSize)
+  {
+    UInt32 pos = dictionaryPos - rep0;
+    if (pos >= dictionarySize)
+      pos += dictionarySize;
+    outStream[nowPos++] = dictionary[dictionaryPos] = dictionary[pos];
+    if (++dictionaryPos == dictionarySize)
+      dictionaryPos = 0;
+    len--;
+  }
+  if (dictionaryPos == 0)
+    previousByte = dictionary[dictionarySize - 1];
+  else
+    previousByte = dictionary[dictionaryPos - 1];
+#else
+
+int LzmaDecode(
+    Byte *buffer, UInt32 bufferSize,
+    int lc, int lp, int pb,
+    #ifdef _LZMA_IN_CB
+    ILzmaInCallback *inCallback,
+    #else
+    unsigned char *inStream, UInt32 inSize,
+    #endif
+    unsigned char *outStream, UInt32 outSize,
+    UInt32 *outSizeProcessed)
+{
+  UInt32 numProbs = Literal + ((UInt32)LZMA_LIT_SIZE << (lc + lp));
+  CProb *p = (CProb *)buffer;
+  CRangeDecoder rd;
+  UInt32 i;
+  int state = 0;
+  int previousIsMatch = 0;
+  Byte previousByte = 0;
+  UInt32 rep0 = 1, rep1 = 1, rep2 = 1, rep3 = 1;
+  UInt32 nowPos = 0;
+  UInt32 posStateMask = (1 << pb) - 1;
+  UInt32 literalPosMask = (1 << lp) - 1;
+  int len = 0;
+  if (bufferSize < numProbs * sizeof(CProb))
+    return LZMA_RESULT_NOT_ENOUGH_MEM;
+  for (i = 0; i < numProbs; i++)
+    p[i] = kBitModelTotal >> 1; 
+  RangeDecoderInit(&rd, 
+      #ifdef _LZMA_IN_CB
+      inCallback
+      #else
+      inStream, inSize
+      #endif
+      );
+#endif
+
+  *outSizeProcessed = 0;
+  while(nowPos < outSize)
+  {
+    int posState = (int)(
+        (nowPos 
+        #ifdef _LZMA_OUT_READ
+        + globalPos
+        #endif
+        )
+        & posStateMask);
+    #ifdef _LZMA_IN_CB
+    if (rd.Result != LZMA_RESULT_OK)
+      return rd.Result;
+    #endif
+    if (rd.ExtraBytes != 0)
+      return LZMA_RESULT_DATA_ERROR;
+    if (RangeDecoderBitDecode(p + IsMatch + (state << kNumPosBitsMax) + posState, &rd) == 0)
+    {
+      CProb *probs = p + Literal + (LZMA_LIT_SIZE * 
+        (((
+        (nowPos 
+        #ifdef _LZMA_OUT_READ
+        + globalPos
+        #endif
+        )
+        & literalPosMask) << lc) + (previousByte >> (8 - lc))));
+
+      if (state < 4) state = 0;
+      else if (state < 10) state -= 3;
+      else state -= 6;
+      if (previousIsMatch)
+      {
+        Byte matchByte;
+        #ifdef _LZMA_OUT_READ
+        UInt32 pos = dictionaryPos - rep0;
+        if (pos >= dictionarySize)
+          pos += dictionarySize;
+        matchByte = dictionary[pos];
+        #else
+        matchByte = outStream[nowPos - rep0];
+        #endif
+        previousByte = LzmaLiteralDecodeMatch(probs, &rd, matchByte);
+        previousIsMatch = 0;
+      }
+      else
+        previousByte = LzmaLiteralDecode(probs, &rd);
+      outStream[nowPos++] = previousByte;
+      #ifdef _LZMA_OUT_READ
+      dictionary[dictionaryPos] = previousByte;
+      if (++dictionaryPos == dictionarySize)
+        dictionaryPos = 0;
+      #endif
+    }
+    else             
+    {
+      previousIsMatch = 1;
+      if (RangeDecoderBitDecode(p + IsRep + state, &rd) == 1)
+      {
+        if (RangeDecoderBitDecode(p + IsRepG0 + state, &rd) == 0)
+        {
+          if (RangeDecoderBitDecode(p + IsRep0Long + (state << kNumPosBitsMax) + posState, &rd) == 0)
+          {
+            #ifdef _LZMA_OUT_READ
+            UInt32 pos;
+            #endif
+            if (
+               (nowPos 
+                #ifdef _LZMA_OUT_READ
+                + globalPos
+                #endif
+               )
+               == 0)
+              return LZMA_RESULT_DATA_ERROR;
+            state = state < 7 ? 9 : 11;
+            #ifdef _LZMA_OUT_READ
+            pos = dictionaryPos - rep0;
+            if (pos >= dictionarySize)
+              pos += dictionarySize;
+            previousByte = dictionary[pos];
+            dictionary[dictionaryPos] = previousByte;
+            if (++dictionaryPos == dictionarySize)
+              dictionaryPos = 0;
+            #else
+            previousByte = outStream[nowPos - rep0];
+            #endif
+            outStream[nowPos++] = previousByte;
+            continue;
+          }
+        }
+        else
+        {
+          UInt32 distance;
+          if(RangeDecoderBitDecode(p + IsRepG1 + state, &rd) == 0)
+            distance = rep1;
+          else 
+          {
+            if(RangeDecoderBitDecode(p + IsRepG2 + state, &rd) == 0)
+              distance = rep2;
+            else
+            {
+              distance = rep3;
+              rep3 = rep2;
+            }
+            rep2 = rep1;
+          }
+          rep1 = rep0;
+          rep0 = distance;
+        }
+        len = LzmaLenDecode(p + RepLenCoder, &rd, posState);
+        state = state < 7 ? 8 : 11;
+      }
+      else
+      {
+        int posSlot;
+        rep3 = rep2;
+        rep2 = rep1;
+        rep1 = rep0;
+        state = state < 7 ? 7 : 10;
+        len = LzmaLenDecode(p + LenCoder, &rd, posState);
+        posSlot = RangeDecoderBitTreeDecode(p + PosSlot +
+            ((len < kNumLenToPosStates ? len : kNumLenToPosStates - 1) << 
+            kNumPosSlotBits), kNumPosSlotBits, &rd);
+        if (posSlot >= kStartPosModelIndex)
+        {
+          int numDirectBits = ((posSlot >> 1) - 1);
+          rep0 = ((2 | ((UInt32)posSlot & 1)) << numDirectBits);
+          if (posSlot < kEndPosModelIndex)
+          {
+            rep0 += RangeDecoderReverseBitTreeDecode(
+                p + SpecPos + rep0 - posSlot - 1, numDirectBits, &rd);
+          }
+          else
+          {
+            rep0 += RangeDecoderDecodeDirectBits(&rd, 
+                numDirectBits - kNumAlignBits) << kNumAlignBits;
+            rep0 += RangeDecoderReverseBitTreeDecode(p + Align, kNumAlignBits, &rd);
+          }
+        }
+        else
+          rep0 = posSlot;
+        rep0++;
+      }
+      if (rep0 == (UInt32)(0))
+      {
+        /* it's for stream version */
+        len = -1;
+        break;
+      }
+      if (rep0 > nowPos 
+        #ifdef _LZMA_OUT_READ
+        + globalPos
+        #endif
+        )
+      {
+        return LZMA_RESULT_DATA_ERROR;
+      }
+      len += kMatchMinLen;
+      do
+      {
+        #ifdef _LZMA_OUT_READ
+        UInt32 pos = dictionaryPos - rep0;
+        if (pos >= dictionarySize)
+          pos += dictionarySize;
+        previousByte = dictionary[pos];
+        dictionary[dictionaryPos] = previousByte;
+        if (++dictionaryPos == dictionarySize)
+          dictionaryPos = 0;
+        #else
+        previousByte = outStream[nowPos - rep0];
+        #endif
+        outStream[nowPos++] = previousByte;
+        len--;
+      }
+      while(len > 0 && nowPos < outSize);
+    }
+  }
+
+  #ifdef _LZMA_OUT_READ
+  vs->RangeDecoder = rd;
+  vs->DictionaryPos = dictionaryPos;
+  vs->GlobalPos = globalPos + nowPos;
+  vs->Reps[0] = rep0;
+  vs->Reps[1] = rep1;
+  vs->Reps[2] = rep2;
+  vs->Reps[3] = rep3;
+  vs->State = state;
+  vs->PreviousIsMatch = previousIsMatch;
+  vs->RemainLen = len;
+  #endif
+
+  *outSizeProcessed = nowPos;
+  return LZMA_RESULT_OK;
+}
diff --git a/target/linux/image/ar7/src/LzmaDecode.h b/target/linux/image/ar7/src/LzmaDecode.h
new file mode 100644
index 000000000..f58944e3c
--- /dev/null
+++ b/target/linux/image/ar7/src/LzmaDecode.h
@@ -0,0 +1,100 @@
+/* 
+  LzmaDecode.h
+  LZMA Decoder interface
+
+  LZMA SDK 4.05 Copyright (c) 1999-2004 Igor Pavlov (2004-08-25)
+  http://www.7-zip.org/
+
+  LZMA SDK is licensed under two licenses:
+  1) GNU Lesser General Public License (GNU LGPL)
+  2) Common Public License (CPL)
+  It means that you can select one of these two licenses and 
+  follow rules of that license.
+
+  SPECIAL EXCEPTION:
+  Igor Pavlov, as the author of this code, expressly permits you to 
+  statically or dynamically link your code (or bind by name) to the 
+  interfaces of this file without subjecting your linked code to the 
+  terms of the CPL or GNU LGPL. Any modifications or additions 
+  to this file, however, are subject to the LGPL or CPL terms.
+*/
+
+#ifndef __LZMADECODE_H
+#define __LZMADECODE_H
+
+/* #define _LZMA_IN_CB */
+/* Use callback for input data */
+
+/* #define _LZMA_OUT_READ */
+/* Use read function for output data */
+
+/* #define _LZMA_PROB32 */
+/* It can increase speed on some 32-bit CPUs, 
+   but memory usage will be doubled in that case */
+
+/* #define _LZMA_LOC_OPT */
+/* Enable local speed optimizations inside code */
+
+#ifndef UInt32
+#ifdef _LZMA_UINT32_IS_ULONG
+#define UInt32 unsigned long
+#else
+#define UInt32 unsigned int
+#endif
+#endif
+
+#ifdef _LZMA_PROB32
+#define CProb UInt32
+#else
+#define CProb unsigned short
+#endif
+
+#define LZMA_RESULT_OK 0
+#define LZMA_RESULT_DATA_ERROR 1
+#define LZMA_RESULT_NOT_ENOUGH_MEM 2
+
+#ifdef _LZMA_IN_CB
+typedef struct _ILzmaInCallback
+{
+  int (*Read)(void *object, unsigned char **buffer, UInt32 *bufferSize);
+} ILzmaInCallback;
+#endif
+
+#define LZMA_BASE_SIZE 1846
+#define LZMA_LIT_SIZE 768
+
+/* 
+bufferSize = (LZMA_BASE_SIZE + (LZMA_LIT_SIZE << (lc + lp)))* sizeof(CProb)
+bufferSize += 100 in case of _LZMA_OUT_READ
+by default CProb is unsigned short, 
+but if specify _LZMA_PROB_32, CProb will be UInt32(unsigned int)
+*/
+
+#ifdef _LZMA_OUT_READ
+int LzmaDecoderInit(
+    unsigned char *buffer, UInt32 bufferSize,
+    int lc, int lp, int pb,
+    unsigned char *dictionary, UInt32 dictionarySize,
+  #ifdef _LZMA_IN_CB
+    ILzmaInCallback *inCallback
+  #else
+    unsigned char *inStream, UInt32 inSize
+  #endif
+);
+#endif
+
+int LzmaDecode(
+    unsigned char *buffer, 
+  #ifndef _LZMA_OUT_READ
+    UInt32 bufferSize,
+    int lc, int lp, int pb,
+  #ifdef _LZMA_IN_CB
+    ILzmaInCallback *inCallback,
+  #else
+    unsigned char *inStream, UInt32 inSize,
+  #endif
+  #endif
+    unsigned char *outStream, UInt32 outSize,
+    UInt32 *outSizeProcessed);
+
+#endif
diff --git a/target/linux/image/ar7/src/ld.script.in b/target/linux/image/ar7/src/ld.script.in
index 9a9f3ef4f..40389e644 100644
--- a/target/linux/image/ar7/src/ld.script.in
+++ b/target/linux/image/ar7/src/ld.script.in
@@ -5,15 +5,15 @@ ENTRY(tikernelunzip)
 {
 
 	/* Allocate memory space on top of kernel bss space */
-	. = _fbss;
+	. = 0x94200000;
 	.text :
 	{
 		*(.text)
-			*(.rodata)
-			*(.rodata1)
-			*(.gnu.warning)
-			*(.text.init)
-			*(.data.init)
+		*(.rodata)
+		*(.rodata1)
+		*(.gnu.warning)
+		*(.text.init)
+		*(.data.init)
 	}                    
 
 	.data :
@@ -21,21 +21,14 @@ ENTRY(tikernelunzip)
 		*(*)
 	}
 
-bss :
+	.bss :
 	{
-		inflate_bss_start = .;
 		*(.dynbss)
-			*(.bss)
-			*(COMMON)
-			*(.sbss)
-			*(.scommon)
-			inflate_bss_end = .;
+		*(COMMON)
+		*(.bss)
+		*(.sbss)
+		*(.scommon)
 		. = ALIGN (0x8000);
-		inflate_slide_window = .;
-		. += 0x8000;  /* slide window is 8000h */
-		inflate_free_memory_start = .;
+		workspace = .;
 	}
-
-
-
 }
diff --git a/target/linux/image/ar7/src/loader.c b/target/linux/image/ar7/src/loader.c
index f4f92950e..22b909d7e 100644
--- a/target/linux/image/ar7/src/loader.c
+++ b/target/linux/image/ar7/src/loader.c
@@ -12,1338 +12,129 @@
  *   directly from Flash or ROM memory on embeded systems.
  */
 
-/*
-   Inflate deflated (PKZIP's method 8 compressed) data.  (compress
-   with the gzip -3 option which will compress it in a compatible
-   format).
-
-   The compression method searches for as much of the current string of bytes
-   (up to a length of 258) in the previous 32 K bytes.  If it doesn't find any
-   matches (of at least length 3), it codes the next byte.  Otherwise, it
-   codes the length of the matched string and its distance backwards from
-   the current position.  There is a single Huffman code that codes both
-   single bytes (called "literals") and match lengths.  A second Huffman
-   code codes the distance information, which follows a length code.  Each
-   length or distance code actually represents a base value and a number
-   of "extra" (sometimes zero) bits to get to add to the base value.  At
-   the end of each deflated block is a special end-of-block (EOB) literal/
-   length code.  The decoding process is basically: get a literal/length
-   code; if EOB then done; if a literal, emit the decoded byte; if a
-   length then get the distance and emit the referred-to bytes from the
-   sliding window of previously emitted data.
-
-   There are (currently) three kinds of inflate blocks: stored, fixed, and
-   dynamic.  The compressor deals with some chunk of data at a time, and
-   decides which method to use on a chunk-by-chunk basis.  A chunk might
-   typically be 32 K or 64 K.  If the chunk is incompressible, then the
-   "stored" method is used.  In this case, the bytes are simply stored as
-   is, eight bits per byte, with none of the above coding.  The bytes are
-   preceded by a count, since there is no longer an EOB code.
-
-   If the data is compressible, then either the fixed or dynamic methods
-   are used.  In the dynamic method, the compressed data is preceded by
-   an encoding of the literal/length and distance Huffman codes that are
-   to be used to decode this block.  The representation is itself Huffman
-   coded, and so is preceded by a description of that code.  These code
-   descriptions take up a little space, and so for small blocks, there is
-   a predefined set of codes, called the fixed codes.  The fixed method is
-   used if the block codes up smaller that way (usually for quite small
-   chunks), otherwise the dynamic method is used.  In the latter case, the
-   codes are customized to the probabilities in the current block, and so
-   can code it much better than the pre-determined fixed codes.
-
-   The Huffman codes themselves are decoded using a multi-level table
-   lookup, in order to maximize the speed of decoding plus the speed of
-   building the decoding tables.  See the comments below that precede the
-   lbits and dbits tuning parameters.
- */
-
-
-/*
-   Notes beyond the 1.93a appnote.txt:
-
-   1. Distance pointers never point before the beginning of the output
-      stream.
-   2. Distance pointers can point back across blocks, up to 32k away.
-   3. There is an implied maximum of 7 bits for the bit length table and
-      15 bits for the actual data.
-   4. If only one code exists, then it is encoded using one bit.  (Zero
-      would be more efficient, but perhaps a little confusing.)  If two
-      codes exist, they are coded using one bit each (0 and 1).
-   5. There is no way of sending zero distance codes--a dummy must be
-      sent if there are none.  (History: a pre 2.0 version of PKZIP would
-      store blocks with no distance codes, but this was discovered to be
-      too harsh a criterion.)  Valid only for 1.93a.  2.04c does allow
-      zero distance codes, which is sent as one code of zero bits in
-      length.
-   6. There are up to 286 literal/length codes.  Code 256 represents the
-      end-of-block.  Note however that the static length tree defines
-      288 codes just to fill out the Huffman codes.  Codes 286 and 287
-      cannot be used though, since there is no length base or extra bits
-      defined for them.  Similarly, there are up to 30 distance codes.
-      However, static trees define 32 codes (all 5 bits) to fill out the
-      Huffman codes, but the last two had better not show up in the data.
-   7. Unzip can check dynamic Huffman blocks for complete code sets.
-      The exception is that a single code would not be complete (see #4).
-   8. The five bits following the block type is really the number of
-      literal codes sent minus 257.
-   9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits
-      (1+6+6).  Therefore, to output three times the length, you output
-      three codes (1+1+1), whereas to output four times the same length,
-      you only need two codes (1+3).  Hmm.
-  10. In the tree reconstruction algorithm, Code = Code + Increment
-      only if BitLength(i) is not zero.  (Pretty obvious.)
-  11. Correction: 4 Bits: # of Bit Length codes - 4     (4 - 19)
-  12. Note: length code 284 can represent 227-258, but length code 285
-      really is 258.  The last length deserves its own, short code
-      since it gets used a lot in very redundant files.  The length
-      258 is special since 258 - 3 (the min match length) is 255.
-  13. The literal/length and distance code bit lengths are read as a
-      single stream of lengths.  It is possible (and advantageous) for
-      a repeat code (16, 17, or 18) to go across the boundary between
-      the two sets of lengths.
- */
-
-#include "gzip.h"
 #include <linux/config.h>
-
-
-
-#ifndef STATIC
-#define STATIC
-#endif /* !STATIC */
-
-#define slide window
-
-/* Huffman code lookup table entry--this entry is four bytes for machines
-   that have 16-bit pointers (e.g. PC's in the small or medium model).
-   Valid extra bits are 0..13.  e == 15 is EOB (end of block), e == 16
-   means that v is a literal, 16 < e < 32 means that v is a pointer to
-   the next table, which codes e - 16 bits, and lastly e == 99 indicates
-   an unused code.  If a code with e == 99 is looked up, this implies an
-   error in the data. */
-struct huft {
-  uch e;                /* number of extra bits or operation */
-  uch b;                /* number of bits in this code or subcode */
-  union {
-    ush n;              /* literal, length base, or distance base */
-    struct huft *t;     /* pointer to next level of table */
-  } v;
-};
-
+#include "gzip.h"
+#include "LzmaDecode.h"
 
 /* Function prototypes */
-STATIC int huft_build OF((unsigned *, unsigned, unsigned,
-		const ush *, const ush *, struct huft **, int *));
-STATIC int huft_free OF((struct huft *));
-STATIC int inflate_codes OF((struct huft *, struct huft *, int, int));
-STATIC int inflate_stored OF((void));
-STATIC int inflate_fixed OF((void));
-STATIC int inflate_dynamic OF((void));
-STATIC int inflate_block OF((int *));
-STATIC int inflate OF((void));
-static void flush_window(void);
-static void gzip_mark(void **);
-static void gzip_release(void **);
-STATIC uch get_byte(void);
-STATIC void memzero(int *, int );
-static void makecrc(void);
-static void *malloc(int);
-static void free(void *);
+unsigned char get_byte(void);
 int tikernelunzip(int,char *[], char *[]);
 static int tidecompress(uch *, uch *);
-#if !defined(NOMEMCPY)
-static uch *memcpy(uch *, const uch *, int);
-#endif
 
 void kernel_entry(int, char *[], char *[]);
 void (*ke)(int, char *[], char *[]); /* Gen reference to kernel function */
+void (*prnt)(unsigned int, char *);		/* Gen reference to Yamon print function */
+void printf(char *ptr);			/* Generate our own printf */
 
-void (*prnt)(unsigned int, char *);        /* Gen reference to Yamon print function */
-
-void printf(char *ptr);          /* Generate our own printf */
-
-
-
-/* The inflate algorithm uses a sliding 32 K byte window on the uncompressed
-   stream to find repeated byte strings.  This is implemented here as a
-   circular buffer.  The index is updated simply by incrementing and then
-   ANDing with 0x7fff (32K-1). */
-/* It is left to other modules to supply the 32 K area.  It is assumed
-   to be usable as if it were declared "uch slide[32768];" or as just
-   "uch *slide;" and then malloc'ed in the latter case.  The definition
-   must be in unzip.h, included above. */
-/* unsigned wp;             current position in slide */
-#define wp outcnt
-#define flush_output(w) (wp=(w),flush_window())
-
-/* Tables for deflate from PKZIP's appnote.txt. */
-static const unsigned border[] = {    /* Order of the bit length code lengths */
-        16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15};
-static const ush cplens[] = {         /* Copy lengths for literal codes 257..285 */
-        3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31,
-        35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0};
-        /* note: see note #13 above about the 258 in this list. */
-static const ush cplext[] = {         /* Extra bits for literal codes 257..285 */
-        0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2,
-        3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */
-static const ush cpdist[] = {         /* Copy offsets for distance codes 0..29 */
-        1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193,
-        257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145,
-        8193, 12289, 16385, 24577};
-static const ush cpdext[] = {         /* Extra bits for distance codes */
-        0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6,
-        7, 7, 8, 8, 9, 9, 10, 10, 11, 11,
-        12, 12, 13, 13};
-
-//bvb extern uch kernelimage[];
-
-
-
-
-/* Macros for inflate() bit peeking and grabbing.
-   The usage is:
-
-        NEEDBITS(j)
-        x = b & mask_bits[j];
-        DUMPBITS(j)
-
-   where NEEDBITS makes sure that b has at least j bits in it, and
-   DUMPBITS removes the bits from b.  The macros use the variable k
-   for the number of bits in b.  Normally, b and k are register
-   variables for speed, and are initialized at the beginning of a
-   routine that uses these macros from a global bit buffer and count.
-
-   If we assume that EOB will be the longest code, then we will never
-   ask for bits with NEEDBITS that are beyond the end of the stream.
-   So, NEEDBITS should not read any more bytes than are needed to
-   meet the request.  Then no bytes need to be "returned" to the buffer
-   at the end of the last block.
-
-   However, this assumption is not true for fixed blocks--the EOB code
-   is 7 bits, but the other literal/length codes can be 8 or 9 bits.
-   (The EOB code is shorter than other codes because fixed blocks are
-   generally short.  So, while a block always has an EOB, many other
-   literal/length codes have a significantly lower probability of
-   showing up at all.)  However, by making the first table have a
-   lookup of seven bits, the EOB code will be found in that first
-   lookup, and so will not require that too many bits be pulled from
-   the stream.
- */
-
-STATIC ulg bb;                         /* bit buffer */
-STATIC unsigned bk;                    /* bits in bit buffer */
-ulg bytes_out;
-static ulg free_mem_ptr;
-//bvb static ulg free_mem_ptr_end;
-
-STATIC const ush mask_bits[] = {
-    0x0000,
-    0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff,
-    0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff
-};
-
-#define NEXTBYTE()  ((uch)get_byte())
-#define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}}
-#define DUMPBITS(n) {b>>=(n); k-=(n);}
-
-
-/*
-   Huffman code decoding is performed using a multi-level table lookup.
-   The fastest way to decode is to simply build a lookup table whose
-   size is determined by the longest code.  However, the time it takes
-   to build this table can also be a factor if the data being decoded
-   is not very long.  The most common codes are necessarily the
-   shortest codes, so those codes dominate the decoding time, and hence
-   the speed.  The idea is you can have a shorter table that decodes the
-   shorter, more probable codes, and then point to subsidiary tables for
-   the longer codes.  The time it costs to decode the longer codes is
-   then traded against the time it takes to make longer tables.
-
-   This results of this trade are in the variables lbits and dbits
-   below.  lbits is the number of bits the first level table for literal/
-   length codes can decode in one step, and dbits is the same thing for
-   the distance codes.  Subsequent tables are also less than or equal to
-   those sizes.  These values may be adjusted either when all of the
-   codes are shorter than that, in which case the longest code length in
-   bits is used, or when the shortest code is *longer* than the requested
-   table size, in which case the length of the shortest code in bits is
-   used.
-
-   There are two different values for the two tables, since they code a
-   different number of possibilities each.  The literal/length table
-   codes 286 possible values, or in a flat code, a little over eight
-   bits.  The distance table codes 30 possible values, or a little less
-   than five bits, flat.  The optimum values for speed end up being
-   about one bit more than those, so lbits is 8+1 and dbits is 5+1.
-   The optimum values may differ though from machine to machine, and
-   possibly even between compilers.  Your mileage may vary.
- */
-
-
-STATIC const int lbits = 9;          /* bits in base literal/length lookup table */
-STATIC const int dbits = 6;          /* bits in base distance lookup table */
-
-
-/* If BMAX needs to be larger than 16, then h and x[] should be ulg. */
-#define BMAX 16         /* maximum bit length of any code (16 for explode) */
-#define N_MAX 288       /* maximum number of codes in any set */
-
-
-STATIC unsigned hufts;         /* track memory usage */
-
-
-STATIC int huft_build(b, n, s, d, e, t, m)
-unsigned *b;            /* code lengths in bits (all assumed <= BMAX) */
-unsigned n;             /* number of codes (assumed <= N_MAX) */
-unsigned s;             /* number of simple-valued codes (0..s-1) */
-const ush *d;                 /* list of base values for non-simple codes */
-const ush *e;                 /* list of extra bits for non-simple codes */
-struct huft **t;        /* result: starting table */
-int *m;                 /* maximum lookup bits, returns actual */
-/* Given a list of code lengths and a maximum table size, make a set of
-   tables to decode that set of codes.  Return zero on success, one if
-   the given code set is incomplete (the tables are still built in this
-   case), two if the input is invalid (all zero length codes or an
-   oversubscribed set of lengths), and three if not enough memory. */
-{
-  unsigned a;                   /* counter for codes of length k */
-  unsigned c[BMAX+1];           /* bit length count table */
-  unsigned f;                   /* i repeats in table every f entries */
-  int g;                        /* maximum code length */
-  int h;                        /* table level */
-  register unsigned i;          /* counter, current code */
-  register unsigned j;          /* counter */
-  register int k;               /* number of bits in current code */
-  int l;                        /* bits per table (returned in m) */
-  register unsigned *p;         /* pointer into c[], b[], or v[] */
-  register struct huft *q;      /* points to current table */
-  struct huft r;                /* table entry for structure assignment */
-  struct huft *u[BMAX];         /* table stack */
-  unsigned v[N_MAX];            /* values in order of bit length */
-  register int w;               /* bits before this table == (l * h) */
-  unsigned x[BMAX+1];           /* bit offsets, then code stack */
-  unsigned *xp;                 /* pointer into x */
-  int y;                        /* number of dummy codes added */
-  unsigned z;                   /* number of entries in current table */
-
-
-  /* Generate counts for each bit length */
-  memzero(c, sizeof(c));
-  p = b;  i = n;
-  do {
-      /*    Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"), 	  n-i, *p)); */
-
-    c[*p]++;                    /* assume all entries <= BMAX */
-    p++;                      /* Can't combine with above line (Solaris bug) */
-  } while (--i);
-  if (c[0] == n)                /* null input--all zero length codes */
-  {
-    *t = (struct huft *)NULL;
-    *m = 0;
-    return 0;
-  }
-
-
-  /* Find minimum and maximum length, bound *m by those */
-  l = *m;
-  for (j = 1; j <= BMAX; j++)
-    if (c[j])
-      break;
-  k = j;                        /* minimum code length */
-  if ((unsigned)l < j)
-    l = j;
-  for (i = BMAX; i; i--)
-    if (c[i])
-      break;
-  g = i;                        /* maximum code length */
-  if ((unsigned)l > i)
-    l = i;
-  *m = l;
-
-
-  /* Adjust last length count to fill out codes, if needed */
-  for (y = 1 << j; j < i; j++, y <<= 1)
-    if ((y -= c[j]) < 0)
-      return 2;                 /* bad input: more codes than bits */
-  if ((y -= c[i]) < 0)
-    return 2;
-  c[i] += y;
-
-
-  /* Generate starting offsets into the value table for each length */
-  x[1] = j = 0;
-  p = c + 1;  xp = x + 2;
-  while (--i) {                 /* note that i == g from above */
-    *xp++ = (j += *p++);
-  }
-
-
-  /* Make a table of values in order of bit lengths */
-  p = b;  i = 0;
-  do {
-    if ((j = *p++) != 0)
-      v[x[j]++] = i;
-  } while (++i < n);
-
-
-  /* Generate the Huffman codes and for each, make the table entries */
-  x[0] = i = 0;                 /* first Huffman code is zero */
-  p = v;                        /* grab values in bit order */
-  h = -1;                       /* no tables yet--level -1 */
-  w = -l;                       /* bits decoded == (l * h) */
-  u[0] = (struct huft *)NULL;   /* just to keep compilers happy */
-  q = (struct huft *)NULL;      /* ditto */
-  z = 0;                        /* ditto */
-
-  /* go through the bit lengths (k already is bits in shortest code) */
-  for (; k <= g; k++)
-  {
-    a = c[k];
-    while (a--)
-    {
-      /* here i is the Huffman code of length k bits for value *p */
-      /* make tables up to required level */
-      while (k > w + l)
-      {
-        h++;
-        w += l;                 /* previous table always l bits */
-
-        /* compute minimum size table less than or equal to l bits */
-        z = (z = g - w) > (unsigned)l ? l : z;  /* upper limit on table size */
-        if ((f = 1 << (j = k - w)) > a + 1)     /* try a k-w bit table */
-        {                       /* too few codes for k-w bit table */
-          f -= a + 1;           /* deduct codes from patterns left */
-          xp = c + k;
-          while (++j < z)       /* try smaller tables up to z bits */
-          {
-            if ((f <<= 1) <= *++xp)
-              break;            /* enough codes to use up j bits */
-            f -= *xp;           /* else deduct codes from patterns */
-          }
-        }
-        z = 1 << j;             /* table entries for j-bit table */
-
-        /* allocate and link in new table */
-        if ((q = (struct huft *)malloc((z + 1)*sizeof(struct huft))) ==
-            (struct huft *)NULL)
-        {
-          if (h)
-            huft_free(u[0]);
-          return 3;             /* not enough memory */
-        }
-        hufts += z + 1;         /* track memory usage */
-        *t = q + 1;             /* link to list for huft_free() */
-        *(t = &(q->v.t)) = (struct huft *)NULL;
-        u[h] = ++q;             /* table starts after link */
-
-        /* connect to last table, if there is one */
-        if (h)
-        {
-          x[h] = i;             /* save pattern for backing up */
-          r.b = (uch)l;         /* bits to dump before this table */
-          r.e = (uch)(16 + j);  /* bits in this table */
-          r.v.t = q;            /* pointer to this table */
-          j = i >> (w - l);     /* (get around Turbo C bug) */
-          u[h-1][j] = r;        /* connect to last table */
-        }
-      }
-
-      /* set up table entry in r */
-      r.b = (uch)(k - w);
-      if (p >= v + n)
-        r.e = 99;               /* out of values--invalid code */
-      else if (*p < s)
-      {
-        r.e = (uch)(*p < 256 ? 16 : 15);    /* 256 is end-of-block code */
-        r.v.n = (ush)(*p);             /* simple code is just the value */
-	p++;                           /* one compiler does not like *p++ */
-      }
-      else
-      {
-        r.e = (uch)e[*p - s];   /* non-simple--look up in lists */
-        r.v.n = d[*p++ - s];
-      }
-
-      /* fill code-like entries with r */
-      f = 1 << (k - w);
-      for (j = i >> w; j < z; j += f)
-        q[j] = r;
-
-      /* backwards increment the k-bit code i */
-      for (j = 1 << (k - 1); i & j; j >>= 1)
-        i ^= j;
-      i ^= j;
-
-      /* backup over finished tables */
-      while ((i & ((1 << w) - 1)) != x[h])
-      {
-        h--;                    /* don't need to update q */
-        w -= l;
-      }
-    }
-  }
-
-
-  /* Return true (1) if we were given an incomplete table */
-  return y != 0 && g != 1;
-}
-
-
-
-STATIC int huft_free(t)
-struct huft *t;         /* table to free */
-/* Free the malloc'ed tables built by huft_build(), which makes a linked
-   list of the tables it made, with the links in a dummy first entry of
-   each table. */
-{
-  register struct huft *p, *q;
-
-
-  /* Go through linked list, freeing from the malloced (t[-1]) address. */
-  p = t;
-  while (p != (struct huft *)NULL)
-  {
-    q = (--p)->v.t;
-    free((char*)p);
-    p = q;
-  }
-  return 0;
-}
-
-
-STATIC int inflate_codes(tl, td, bl, bd)
-struct huft *tl, *td;   /* literal/length and distance decoder tables */
-int bl, bd;             /* number of bits decoded by tl[] and td[] */
-/* inflate (decompress) the codes in a deflated (compressed) block.
-   Return an error code or zero if it all goes ok. */
-{
-  register unsigned e;  /* table entry flag/number of extra bits */
-  unsigned n, d;        /* length and index for copy */
-  unsigned w;           /* current window position */
-  struct huft *t;       /* pointer to table entry */
-  unsigned ml, md;      /* masks for bl and bd bits */
-  register ulg b;       /* bit buffer */
-  register unsigned k;  /* number of bits in bit buffer */
-
-
-  /* make local copies of globals */
-  b = bb;                       /* initialize bit buffer */
-  k = bk;
-  w = wp;                       /* initialize window position */
-
-  /* inflate the coded data */
-  ml = mask_bits[bl];           /* precompute masks for speed */
-  md = mask_bits[bd];
-  for (;;)                      /* do until end of block */
-  {
-    NEEDBITS((unsigned)bl)
-    if ((e = (t = tl + ((unsigned)b & ml))->e) > 16)
-    {
-      do {
-        if (e == 99)
-   	{
-          return 1;
-   	}
-        DUMPBITS(t->b)
-        e -= 16;
-        NEEDBITS(e)
-      } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16);
-    }
-    DUMPBITS(t->b)
-    if (e == 16)                /* then it's a literal */
-    {
-      slide[w++] = (uch)t->v.n;
-      /*      Tracevv((stderr, "%c", slide[w-1])); */
-      if (w == WSIZE)
-      {
-        flush_output(w);
-        w = 0;
-      }
-    }
-    else                        /* it's an EOB or a length */
-    {
-      /* exit if end of block */
-      if (e == 15)
-      {
-        break;
-      }
-
-      /* get length of block to copy */
-      NEEDBITS(e)
-      n = t->v.n + ((unsigned)b & mask_bits[e]);
-      DUMPBITS(e);
-
-      /* decode distance of block to copy */
-      NEEDBITS((unsigned)bd)
-      if ((e = (t = td + ((unsigned)b & md))->e) > 16)
-      {
-        do {
-          if (e == 99)
-	  {
-            return 1;
-	  }
-          DUMPBITS(t->b)
-          e -= 16;
-          NEEDBITS(e)
-        } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16);
-      }
-      DUMPBITS(t->b)
-      NEEDBITS(e)
-      d = w - t->v.n - ((unsigned)b & mask_bits[e]);
-      DUMPBITS(e)
-	/*      Tracevv((stderr,"\\[%d,%d]", w-d, n)); */
-
-      /* do the copy */
-      do {
-        n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e);
-#if !defined(NOMEMCPY) && !defined(DEBUG)
-        if (w - d >= e)         /* (this test assumes unsigned comparison) */
-        {
-          memcpy(slide + w, slide + d, e);
-          w += e;
-          d += e;
-        }
-        else                      /* do it slow to avoid memcpy() overlap */
-#endif /* !NOMEMCPY */
-          do {
-            slide[w++] = slide[d++];
-	    /*	    Tracevv((stderr, "%c", slide[w-1])); */
-          } while (--e);
-
-        if (w == WSIZE)
-        {
-          flush_output(w);
-          w = 0;
-        }
-      } while (n);
-    }
-  }
-
-
-  /* restore the globals from the locals */
-  wp = w;                       /* restore global window pointer */
-  bb = b;                       /* restore global bit buffer */
-  bk = k;
-
-  /* done */
-  return 0;
-}
-
-
-
-STATIC int inflate_stored()
-/* "decompress" an inflated type 0 (stored) block. */
+int tikernelunzip(int argc, char *argv[], char *arge[])
 {
-  unsigned n;           /* number of bytes in block */
-  unsigned w;           /* current window position */
-  register ulg b;       /* bit buffer */
-  register unsigned k;  /* number of bits in bit buffer */
-
-
-  /* make local copies of globals */
-  b = bb;                       /* initialize bit buffer */
-  k = bk;
-  w = wp;                       /* initialize window position */
-
+	extern unsigned int _ftext;
+	extern uch kernelimage[];
+	uch *in, *out;
+	int status;
 
-  /* go to byte boundary */
-  n = k & 7;
-  DUMPBITS(n);
+	printf("Launching kernel decompressor.\n");
 
+	out = (unsigned char *) LOADADDR;
+	in = &(kernelimage[0]);
 
-  /* get the length and its complement */
-  NEEDBITS(16)
-  n = ((unsigned)b & 0xffff);
-  DUMPBITS(16)
-  NEEDBITS(16)
-  if (n != (unsigned)((~b) & 0xffff))
-    return 1;                   /* error in compressed data */
-  DUMPBITS(16)
+	status = tidecompress(in, out);
 
+	if (status == 0) {
+		printf("Kernel decompressor was successful ... launching kernel.\n");
 
-  /* read and output the compressed data */
-  while (n--)
-  {
-    NEEDBITS(8)
-    slide[w++] = (uch)b;
-    if (w == WSIZE)
-    {
-      flush_output(w);
-      w = 0;
-    }
-    DUMPBITS(8)
-  }
+		ke = ( void(*)(int, char *[],char*[]))kernel_entry;
+		(*ke)(argc,argv,arge);
 
-
-  /* restore the globals from the locals */
-  wp = w;                       /* restore global window pointer */
-  bb = b;                       /* restore global bit buffer */
-  bk = k;
-
-  return 0;
+		return (0);
+	} else {
+		printf("Error in decompression.\n");
+		return(1);
+	}
 }
 
-
-
-STATIC int inflate_fixed()
-/* decompress an inflated type 1 (fixed Huffman codes) block.  We should
-   either replace this with a custom decoder, or at least precompute the
-   Huffman tables. */
+#if 0
+char hex[] = {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'};
+void print_i(int i)
 {
-  int i;                /* temporary variable */
-  struct huft *tl;      /* literal/length code table */
-  struct huft *td;      /* distance code table */
-  int bl;               /* lookup bits for tl */
-  int bd;               /* lookup bits for td */
-  unsigned l[288];      /* length list for huft_build */
-
-
-  /* set up literal table */
-  for (i = 0; i < 144; i++)
-    l[i] = 8;
-  for (; i < 256; i++)
-    l[i] = 9;
-  for (; i < 280; i++)
-    l[i] = 7;
-  for (; i < 288; i++)          /* make a complete, but wrong code set */
-    l[i] = 8;
-  bl = 7;
-  if ((i = huft_build(l, 288, 257, cplens, cplext, &tl, &bl)) != 0)
-    return i;
-
+	int j;
+	char buf[11];
 
-  /* set up distance table */
-  for (i = 0; i < 30; i++)      /* make an incomplete code set */
-    l[i] = 5;
-  bd = 5;
-  if ((i = huft_build(l, 30, 0, cpdist, cpdext, &td, &bd)) > 1)
-  {
-    huft_free(tl);
-
-    return i;
-  }
-
-
-  /* decompress until an end-of-block code */
-  {
-    int iii;
-
-    iii = inflate_codes(tl, td, bl, bd);
-    if (iii)
-      return 1;
-  }
+	buf[0] = '0';
+	buf[1] = 'x';
+	buf[10] = 0;
+	
+	for (j = 0; j < 8; j++)
+	{
+		buf[2 + 7 - j] = hex[i & 0xf];
+		i = i >> 4;
+	}
 
-  /* free the decoding tables, return */
-  huft_free(tl);
-  huft_free(td);
-  return 0;
+	printf(buf);
 }
-
-
-
-STATIC int inflate_dynamic()
-/* decompress an inflated type 2 (dynamic Huffman codes) block. */
-{
-  int i;                /* temporary variables */
-  unsigned j;
-  unsigned l;           /* last length */
-  unsigned m;           /* mask for bit lengths table */
-  unsigned n;           /* number of lengths to get */
-  struct huft *tl;      /* literal/length code table */
-  struct huft *td;      /* distance code table */
-  int bl;               /* lookup bits for tl */
-  int bd;               /* lookup bits for td */
-  unsigned nb;          /* number of bit length codes */
-  unsigned nl;          /* number of literal/length codes */
-  unsigned nd;          /* number of distance codes */
-#ifdef PKZIP_BUG_WORKAROUND
-  unsigned ll[288+32];  /* literal/length and distance code lengths */
-#else
-  unsigned ll[286+30];  /* literal/length and distance code lengths */
-#endif
-  register ulg b;       /* bit buffer */
-  register unsigned k;  /* number of bits in bit buffer */
-
-
-  /* make local bit buffer */
-  b = bb;
-  k = bk;
-
-  /* read in table lengths */
-  NEEDBITS(5)
-  nl = 257 + ((unsigned)b & 0x1f);      /* number of literal/length codes */
-  DUMPBITS(5)
-  NEEDBITS(5)
-  nd = 1 + ((unsigned)b & 0x1f);        /* number of distance codes */
-  DUMPBITS(5)
-  NEEDBITS(4)
-  nb = 4 + ((unsigned)b & 0xf);         /* number of bit length codes */
-  DUMPBITS(4)
-#ifdef PKZIP_BUG_WORKAROUND
-  if (nl > 288 || nd > 32)
-#else
-  if (nl > 286 || nd > 30)
 #endif
-    return 1;                   /* bad lengths */
-
-
-  /* read in bit-length-code lengths */
-  for (j = 0; j < nb; j++)
-  {
-    NEEDBITS(3)
-    ll[border[j]] = (unsigned)b & 7;
-    DUMPBITS(3)
-  }
-  for (; j < 19; j++)
-    ll[border[j]] = 0;
-
-
-  /* build decoding table for trees--single level, 7 bit lookup */
-  bl = 7;
-  if ((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl)) != 0)
-  {
-    if (i == 1)
-      huft_free(tl);
-    return i;                   /* incomplete code set */
-  }
-
-
-  /* read in literal and distance code lengths */
-  n = nl + nd;
-  m = mask_bits[bl];
-  i = l = 0;
-  while ((unsigned)i < n)
-  {
-    NEEDBITS((unsigned)bl)
-    j = (td = tl + ((unsigned)b & m))->b;
-    DUMPBITS(j)
-    j = td->v.n;
-    if (j < 16)                 /* length of code in bits (0..15) */
-      ll[i++] = l = j;          /* save last length in l */
-    else if (j == 16)           /* repeat last length 3 to 6 times */
-    {
-      NEEDBITS(2)
-      j = 3 + ((unsigned)b & 3);
-      DUMPBITS(2)
-      if ((unsigned)i + j > n)
-        return 1;
-      while (j--)
-        ll[i++] = l;
-    }
-    else if (j == 17)           /* 3 to 10 zero length codes */
-    {
-      NEEDBITS(3)
-      j = 3 + ((unsigned)b & 7);
-      DUMPBITS(3)
-      if ((unsigned)i + j > n)
-        return 1;
-      while (j--)
-        ll[i++] = 0;
-      l = 0;
-    }
-    else                        /* j == 18: 11 to 138 zero length codes */
-    {
-      NEEDBITS(7)
-      j = 11 + ((unsigned)b & 0x7f);
-      DUMPBITS(7)
-      if ((unsigned)i + j > n)
-        return 1;
-      while (j--)
-        ll[i++] = 0;
-      l = 0;
-    }
-  }
-
-
-  /* free decoding table for trees */
-  huft_free(tl);
-
-
-  /* restore the global bit buffer */
-  bb = b;
-  bk = k;
-
-
-  /* build the decoding tables for literal/length and distance codes */
-  bl = lbits;
-  if ((i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl)) != 0)
-  {
-    if (i == 1) {
-      /*      error(" incomplete literal tree\n"); */
-      huft_free(tl);
-    }
-    return i;                   /* incomplete code set */
-  }
-  bd = dbits;
-  if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0)
-  {
-    if (i == 1) {
-      /*      error(" incomplete distance tree\n"); */
-#ifdef PKZIP_BUG_WORKAROUND
-      i = 0;
-    }
-#else
-      huft_free(td);
-    }
-    huft_free(tl);
-    return i;                   /* incomplete code set */
-#endif
-  }
-
-  /* decompress until an end-of-block code */
-  {
-	int iii;
-	iii = inflate_codes(tl, td, bl, bd);
-	if (iii )
-    		return 1;
-  }
-
-  /* free the decoding tables, return */
-  huft_free(tl);
-  huft_free(td);
-
-  return 0;
-}
-
-
-
-STATIC int inflate_block(e)
-int *e;                 /* last block flag */
-/* decompress an inflated block */
-{
-  unsigned t;           /* block type */
-  register ulg b;       /* bit buffer */
-  register unsigned k;  /* number of bits in bit buffer */
-
-
-  /* make local bit buffer */
-  b = bb;
-  k = bk;
-
-  /* read in last block bit */
-  NEEDBITS(1);
-  *e = (int)b & 1;
-  DUMPBITS(1);
-
-
-  /* read in block type */
-  NEEDBITS(2);
-  t = (unsigned)b & 3;
-  DUMPBITS(2);
-
-
-  /* restore the global bit buffer */
-  bb = b;
-  bk = k;
-
-  /* inflate that block type */
-  if (t == 2)
-    return inflate_dynamic();
-  if (t == 0)
-    return inflate_stored();
-  if (t == 1)
-    return inflate_fixed();
-
-
-  /* bad block type */
-  return 2;
-}
-
-
-
-STATIC int inflate()
-/* decompress an inflated entry */
-{
-  int e;                /* last block flag */
-  int r;                /* result code */
-  unsigned h;           /* maximum struct huft's malloc'ed */
-  void *ptr;
-
-  /* initialize window, bit buffer */
-  wp = 0;
-  bk = 0;
-  bb = 0;
-
-  /* Initialize crc table */
-  makecrc();
-
-
-  /* decompress until the last block */
-  h = 0;
-  do {
-    hufts = 0;
-    gzip_mark(&ptr);
-    r = inflate_block(&e);
-    if (r != 0) {
-      gzip_release(&ptr);
-      return r;
-    }
-    gzip_release(&ptr);
-    if (hufts > h)
-      h = hufts;
-  } while (!e);
-
-  /* Undo too much lookahead. The next read will be byte aligned so we
-   * can discard unused bits in the last meaningful byte.
-   */
-  while (bk >= 8) {
-    bk -= 8;
-    inptr--;
-  }
-
-  /* flush out slide */
-  flush_output(wp);
-
-
-  /* return success */
-#ifdef DEBUG
-  fprintf(stderr, "<%u> ", h);
-#endif /* DEBUG */
-  return 0;
-}
-
-/**********************************************************************
- *
- * The following are support routines for inflate.c
- *
- **********************************************************************/
-
-static ulg crc_32_tab[256];
-static ulg crc;		/* initialized in makecrc() so it'll reside in bss */
-#define CRC_VALUE (crc ^ 0xffffffffL)
-
-/*
- * Code to compute the CRC-32 table. Borrowed from
- * gzip-1.0.3/makecrc.c.
- */
-
-static void
-makecrc(void)
-{
-/* Not copyrighted 1990 Mark Adler	*/
-
-  unsigned long c;      /* crc shift register */
-  unsigned long e;      /* polynomial exclusive-or pattern */
-  int i;                /* counter for all possible eight bit values */
-  int k;                /* byte being shifted into crc apparatus */
-
-  /* terms of polynomial defining this crc (except x^32): */
-  static const int p[] = {0,1,2,4,5,7,8,10,11,12,16,22,23,26};
-
-  /* Make exclusive-or pattern from polynomial */
-  e = 0;
-  for (i = 0; i < sizeof(p)/sizeof(int); i++)
-    e |= 1L << (31 - p[i]);
-
-  crc_32_tab[0] = 0;
-
-  for (i = 1; i < 256; i++)
-  {
-    c = 0;
-    for (k = i | 256; k != 1; k >>= 1)
-    {
-      c = c & 1 ? (c >> 1) ^ e : c >> 1;
-      if (k & 1)
-        c ^= e;
-    }
-    crc_32_tab[i] = c;
-  }
-
-  /* this is initialized here so this code could reside in ROM */
-  crc = (ulg)0xffffffffL; /* shift register contents */
-}
-
-/* gzip flag byte */
-#define ASCII_FLAG   0x01 /* bit 0 set: file probably ASCII text */
-#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
-#define EXTRA_FIELD  0x04 /* bit 2 set: extra field present */
-#define ORIG_NAME    0x08 /* bit 3 set: original file name present */
-#define COMMENT      0x10 /* bit 4 set: file comment present */
-#define ENCRYPTED    0x20 /* bit 5 set: file is encrypted */
-#define RESERVED     0xC0 /* bit 6,7:   reserved */
-
-/*
- * Do the uncompression!
- */
-static int gunzip(void)
-{
-  uch flags;
-  unsigned char magic[2]; /* magic header */
-  char method;
-  ulg orig_crc = 0;       /* original crc */
-  ulg orig_len = 0;       /* original uncompressed length */
-  int res;
-
-  magic[0] = (unsigned char)get_byte();
-  magic[1] = (unsigned char)get_byte();
-  method = (unsigned char)get_byte();
-
-
-  if (magic[0] != 037 ||
-      ((magic[1] != 0213) && (magic[1] != 0236))) {
-    /*	    error("bad gzip magic numbers"); */
-    //bvb printf("Compressed Kernel image Magic number error: 0x%x 0x%x\n",
-    //bvb (unsigned int)magic[0], (unsigned int)magic[1]);
-    return -1;
-  }
-
-  /* We only support method #8, DEFLATED */
-  if (method != 8)  {
-    /*	    error("internal error, invalid method"); */
-    //bvb printf("Kernel Compression Method number is %d(must be 8)\n",
-    //bvb (unsigned int) method);
-
-    return -1;
-  }
-
-  flags  = (uch)get_byte();
-  if ((flags & ENCRYPTED) != 0) {
-    /*	    error("Input is encrypted\n"); */
-    return -1;
-  }
-  if ((flags & CONTINUATION) != 0) {
-    /*	    error("Multi part input\n"); */
-    return -1;
-  }
-  if ((flags & RESERVED) != 0) {
-    /*	    error("Input has invalid flags\n"); */
-    return -1;
-  }
-  (ulg)get_byte();	/* Get timestamp */
-  /* bvb
-  ((ulg)get_byte()) << 8;
-  ((ulg)get_byte()) << 16;
-  ((ulg)get_byte()) << 24;
-  */
-  (ulg)get_byte();
-  (ulg)get_byte();
-  (ulg)get_byte();
-
-  (void)get_byte();  /* Ignore extra flags for the moment */
-  (void)get_byte();  /* Ignore OS type for the moment */
-
-  if ((flags & EXTRA_FIELD) != 0) {
-    unsigned len = (unsigned)get_byte();
-    len |= ((unsigned)get_byte())<<8;
-    while (len--) (void)get_byte();
-  }
-
-  /* Get original file name if it was truncated */
-  if ((flags & ORIG_NAME) != 0) {
-    /* Discard the old name */
-    while (get_byte() != 0) /* null */ ;
-  }
-
-  /* Discard file comment if any */
-  if ((flags & COMMENT) != 0) {
-    while (get_byte() != 0) /* null */ ;
-  }
-
-  /* Decompress */
-  res = inflate();
-  if (res) {
-    switch (res) {
-      case 0:
-        break;
-      case 1:
-        //bvb printf("Error: invalid compressed format (err=1)\n");
-        break;
-      case 2:
-        //bvb printf("Error: invalid compressed format (err=2)\n");
-        break;
-      case 3:
-        //bvb printf("Error: out of memory\n");
-        break;
-      default:
-        //bvb printf("Error: invalid compressed format (other)\n");
-		break;
-    }
-    return -1;
-  }
-
-  /* Get the crc and original length */
-  /* crc32  (see algorithm.doc)
-   * uncompressed input size modulo 2^32
-   */
-  orig_crc = (ulg) get_byte();
-  orig_crc |= (ulg) get_byte() << 8;
-  orig_crc |= (ulg) get_byte() << 16;
-  orig_crc |= (ulg) get_byte() << 24;
-
-  orig_len = (ulg) get_byte();
-  orig_len |= (ulg) get_byte() << 8;
-  orig_len |= (ulg) get_byte() << 16;
-  orig_len |= (ulg) get_byte() << 24;
-
-  /* Validate decompression */
-  if (orig_crc != CRC_VALUE) {
-    //bvb printf("ERROR: crc error\n");
-    return -1;
-  }
-  if (orig_len != bytes_out) {
-    //bvb printf("Error: CRC length error\n");
-    return -1;
-  }
-  //bvb printf("Kernel Compression OK\n");
-  return 0;
-}
-
-int tikernelunzip(int argc, char *argv[], char *arge[])
-{
-  extern unsigned int _ftext;
-  extern uch kernelimage[];
-  uch *in, *out;
-  int status;
-  //bvb int *p;
-
-  printf("Launching kernel decompressor.\n");
-
-  //    out = (uch *)OUTBUF_ADDR;
-  out = (uch *)&_ftext;
-  in = &(kernelimage[0]);  /* temp test file */
-
-  status = tidecompress(in, out);
-
-  if (status == 0)
-    {
-      //bvb printf("Kernel Decompressor was successful, addr:0x%x\n",
-      //bvb (unsigned int)out);
-      //bvb return(0);
-
-      printf("Kernel decompressor was successful ... launching kernel.\n");
-
-      ke = ( void(*)(int, char *[],char*[]))kernel_entry;
-      (*ke)(argc,argv,arge);
-
-      return (0);
-
-    }
-  else
-    {
-      //bvb printf("Error in compression: status=0x%x\n", status);
-      printf("Error in decompression!\n");
-      return(1);
-    }
-
-  //bvb p = (int *)0xb6000000;
-  //bvb *p = 0x46464646;
-
-}
-
 
 int tidecompress(uch *indata, uch *outdata)
 {
-    extern unsigned int inflate_free_memory_start;
-    extern unsigned int inflate_slide_window;
-
-    int i;
-    //bvb int *p;
-    //bvb int status;
-    int j;
-
-
-    j = 0;
-    //bvb p = (int *)0xb6000000;
-    //bvb *p = 0x556e7a70;
-
-    /* Setup memory limits */
-    //bvb freememstart = (void *)FREEMEM_START;
-    freememstart = (void *)&inflate_free_memory_start;
-    window = (uch *)&inflate_slide_window; /* only if using raw memory */
-
-    bytes_out = 0;
-    output_ptr = 0;
-    output_data = outdata;
-    input_data = indata;
-
-    i = gunzip();
-    return(i);
+	extern unsigned int workspace;
+	extern unsigned char kernelimage[], kernelimage_end[];
+	unsigned int i;  /* temp value */
+	unsigned int lc; /* literal context bits */
+	unsigned int lp; /* literal pos state bits */
+	unsigned int pb; /* pos state bits */
+	unsigned int osize; /* uncompressed size */
+	unsigned int wsize; /* window size */
+	unsigned int insize = kernelimage_end - kernelimage;
+	int status;
+	
+	output_ptr = 0;
+	output_data = outdata;
+	input_data = indata;
+
+	/* lzma args */
+	i = get_byte();
+	lc = i % 9, i = i / 9;
+	lp = i % 5, pb = i / 5;
+
+	/* skip rest of the LZMA coder property */
+	for (i = 0; i < 4; i++)
+		get_byte();
+	
+	/* read the lower half of uncompressed size in the header */
+	osize = ((unsigned int)get_byte()) +
+		((unsigned int)get_byte() << 8) +
+		((unsigned int)get_byte() << 16) +
+		((unsigned int)get_byte() << 24);
+
+	/* skip rest of the header (upper half of uncompressed size) */
+	for (i = 0; i < 4; i++)
+		get_byte();
+	
+	i = 0;
+	wsize = (LZMA_BASE_SIZE + (LZMA_LIT_SIZE << (lc + lp))) * sizeof(CProb);
+
+	if ((status = LzmaDecode((unsigned char *) &workspace, wsize, lc, lp, pb,
+		indata + 13, insize - 13, (unsigned char *) output_data, osize, &i)) == LZMA_RESULT_OK)
+			return 0;
+
+	return status;
 }
 
 
 void printf(char *ptr)
 {
-  unsigned int *tempptr = (unsigned int  *)0x90000534;
-  prnt = ( void (*)(unsigned int, char *)) *tempptr;
-  (*prnt)(0,ptr);
-}
-
-
-uch get_byte()
-{
-    uch c;
-
-    c = *input_data;
-    input_data++;
-
-    return(c);
-}
-
-void memzero(int table[], int size)
-{
-    int i;
-    int j = size/4;
-
-    for(i=0; i<j; i++)
-    {
-        table[i] = 0;
-    }
-}
-
-/* ===========================================================================
- * Write the output window window[0..outcnt-1] and update crc and bytes_out.
- * (Used for the decompressed data only.)
- */
-void flush_window()
-{
-	ulg c = crc;
-	unsigned n;
-	uch *in, *out, ch;
-
-
-	in = window;
-	out = &output_data[output_ptr];
-	for (n = 0; n < outcnt; n++) {
-		ch = *out++ = *in++;
-		c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8);
-	}
-	crc = c;
-	bytes_out += (ulg)outcnt;
-	output_ptr += (ulg)outcnt;
-	outcnt = 0;
-
-        //bvb printf("Bytes uncompressed: %d\r", bytes_out);
-}
-
-static void gzip_mark(void **ptr)
-{
-  /*	arch_decomp_wdog(); */
-	*ptr = (void *) free_mem_ptr;
-}
-
-static void gzip_release(void **ptr)
-{
-  /*	arch_decomp_wdog(); */
-	free_mem_ptr = (long) *ptr;
+	unsigned int *tempptr = (unsigned int  *)0x90000534;
+	prnt = ( void (*)(unsigned int, char *)) *tempptr;
+	(*prnt)(0,ptr);
 }
 
-void *malloc(int size)
+unsigned char get_byte()
 {
-    uch *p;
-    void *r;
-
-    r = freememstart;
-    p = (uch *)r;
-
-    p = p + size;
-    freememstart = (void *)p;
+	unsigned char c;
+	
+	c = *input_data;
+	input_data++;
 
-    return(r);
+	return c;
 }
 
-void free(void *p)
-{
-}
-
-
diff --git a/target/linux/image/ar7/src/zimage.script.in b/target/linux/image/ar7/src/zimage.script.in
index 5fb5dccdf..1a0865b08 100644
--- a/target/linux/image/ar7/src/zimage.script.in
+++ b/target/linux/image/ar7/src/zimage.script.in
@@ -6,6 +6,6 @@ OUTPUT_ARCH(mips)
 	{
 		kernelimage = .;
 		*(.data)
-			kernelimage_end = .;
+		kernelimage_end = .;
 	}
 }