Replace certificate based gating of multicast like/gather with a simpler more efficient method, fix some minor issues with request based com/cert push, and clean up some other random stuff.

6 files changed, 392 insertions, 472 deletions

diff --git a/node/Address.hpp b/node/Address.hpp
index a2214c9e..ae0566fe 100644
--- a/node/Address.hpp
+++ b/node/Address.hpp
@@ -54,28 +54,16 @@ public:
 	 * @param bits Raw address -- 5 bytes, big-endian byte order
 	 * @param len Length of array
 	 */
-	Address(const void *bits,unsigned int len)
-	{
-		setTo(bits,len);
-	}
+	Address(const void *bits,unsigned int len) { setTo(bits,len); }
 
-	inline Address &operator=(const Address &a)
-	{
-		_a = a._a;
-		return *this;
-	}
-
-	inline Address &operator=(const uint64_t a)
-	{
-		_a = (a & 0xffffffffffULL);
-		return *this;
-	}
+	inline Address &operator=(const Address &a) { _a = a._a; return *this; }
+	inline Address &operator=(const uint64_t a) { _a = (a & 0xffffffffffULL); return *this; }
 
 	/**
 	 * @param bits Raw address -- 5 bytes, big-endian byte order
 	 * @param len Length of array
 	 */
-	inline void setTo(const void *bits,unsigned int len)
+	inline void setTo(const void *bits,const unsigned int len)
 	{
 		if (len < ZT_ADDRESS_LENGTH) {
 			_a = 0;
@@ -94,7 +82,7 @@ public:
 	 * @param bits Buffer to hold 5-byte address in big-endian byte order
 	 * @param len Length of array
 	 */
-	inline void copyTo(void *bits,unsigned int len) const
+	inline void copyTo(void *const bits,const unsigned int len) const
 	{
 		if (len < ZT_ADDRESS_LENGTH)
 			return;
@@ -125,26 +113,17 @@ public:
 	/**
 	 * @return Integer containing address (0 to 2^40)
 	 */
-	inline uint64_t toInt() const
-	{
-		return _a;
-	}
+	inline uint64_t toInt() const { return _a; }
 
 	/**
 	 * @return Hash code for use with Hashtable
 	 */
-	inline unsigned long hashCode() const
-	{
-		return (unsigned long)_a;
-	}
+	inline unsigned long hashCode() const { return (unsigned long)_a; }
 
 	/**
 	 * @return Hexadecimal string
 	 */
-	inline char *toString(char buf[11]) const
-	{
-		return Utils::hex10(_a,buf);
-	}
+	inline char *toString(char buf[11]) const { return Utils::hex10(_a,buf); }
 
 	/**
 	 * @return True if this address is not zero
@@ -152,11 +131,6 @@ public:
 	inline operator bool() const { return (_a != 0); }
 
 	/**
-	 * Set to null/zero
-	 */
-	inline void zero() { _a = 0; }
-
-	/**
 	 * Check if this address is reserved
 	 *
 	 * The all-zero null address and any address beginning with 0xff are
@@ -165,16 +139,15 @@ public:
 	 *
 	 * @return True if address is reserved and may not be used
 	 */
-	inline bool isReserved() const
-	{
-		return ((!_a)||((_a >> 32) == ZT_ADDRESS_RESERVED_PREFIX));
-	}
+	inline bool isReserved() const { return ((!_a)||((_a >> 32) == ZT_ADDRESS_RESERVED_PREFIX)); }
 
 	/**
 	 * @param i Value from 0 to 4 (inclusive)
 	 * @return Byte at said position (address interpreted in big-endian order)
 	 */
-	inline unsigned char operator[](unsigned int i) const { return (unsigned char)((_a >> (32 - (i * 8))) & 0xff); }
+	inline uint8_t operator[](unsigned int i) const { return (uint8_t)(_a >> (32 - (i * 8))); }
+
+	inline void zero() { _a = 0; }
 
 	inline bool operator==(const uint64_t &a) const { return (_a == (a & 0xffffffffffULL)); }
 	inline bool operator!=(const uint64_t &a) const { return (_a != (a & 0xffffffffffULL)); }
diff --git a/node/C25519.cpp b/node/C25519.cpp
index 209ac445..cab7b9d5 100644
--- a/node/C25519.cpp
+++ b/node/C25519.cpp
@@ -2003,25 +2003,6 @@ extern "C" void ed25519_amd64_asm_sign(const unsigned char *sk,const unsigned ch
 
 namespace ZeroTier {
 
-#ifdef ZT_CONTROLLER
-struct C25519CacheKey
-{
-	uint64_t messageDigest[4];
-	uint64_t publicKey[4];
-	inline unsigned long hashCode() const { return (unsigned long)(messageDigest[0] ^ publicKey[0]); }
-	inline bool operator==(const C25519CacheKey &k) const { return (memcmp(this,&k,sizeof(C25519CacheKey)) == 0); }
-	inline bool operator!=(const C25519CacheKey &k) const { return (memcmp(this,&k,sizeof(C25519CacheKey)) != 0); }
-};
-struct C25519CacheValue
-{
-	uint64_t signature[12];
-	uint64_t timestamp;
-};
-static uint64_t _ed25519TimestampCounter = 0;
-static Hashtable<C25519CacheKey,C25519CacheValue> _ed25519Cache;
-static Mutex _ed25519CacheLock;
-#endif
-
 void C25519::agree(const C25519::Private &mine,const C25519::Public &their,void *keybuf,unsigned int keylen)
 {
 	unsigned char rawkey[32];
@@ -2043,21 +2024,6 @@ void C25519::sign(const C25519::Private &myPrivate,const C25519::Public &myPubli
 	unsigned char digest[64]; // we sign the first 32 bytes of SHA-512(msg)
 	SHA512::hash(digest,msg,len);
 
-#ifdef ZT_CONTROLLER
-	C25519CacheKey ck;
-	ZT_FAST_MEMCPY(ck.messageDigest,digest,32);
-	ZT_FAST_MEMCPY(ck.publicKey,myPublic.data + 32,32);
-	C25519CacheValue *cv = (C25519CacheValue *)0;
-	{
-		Mutex::Lock l(_ed25519CacheLock);
-		cv = _ed25519Cache.get(ck);
-	}
-	if (cv) {
-		ZT_FAST_MEMCPY(signature,cv->signature,ZT_C25519_SIGNATURE_LEN);
-		return;
-	}
-#endif
-
 #ifdef ZT_USE_FAST_X64_ED25519
 	ed25519_amd64_asm_sign(myPrivate.data + 32,myPublic.data + 32,digest,(unsigned char *)signature);
 #else
@@ -2103,28 +2069,6 @@ void C25519::sign(const C25519::Private &myPrivate,const C25519::Public &myPubli
 	for(unsigned int i=0;i<32;i++)
 		sig[32 + i] = s[i];
 #endif
-
-#ifdef ZT_CONTROLLER
-	C25519CacheValue cvn;
-	memcpy(cvn.signature,signature,ZT_C25519_SIGNATURE_LEN);
-	{
-		Mutex::Lock l(_ed25519CacheLock);
-
-		if (_ed25519Cache.size() > 1048576) {
-			const uint64_t before = _ed25519TimestampCounter - ((1048576 / 3) * 2);
-			Hashtable< C25519CacheKey,C25519CacheValue >::Iterator i(_ed25519Cache);
-			C25519CacheKey *ik = (C25519CacheKey *)0;
-			C25519CacheValue *iv = (C25519CacheValue *)0;
-			while (i.next(ik,iv)) {
-				if (iv->timestamp < before)
-					_ed25519Cache.erase(*ik);
-			}
-		}
-
-		cvn.timestamp = ++_ed25519TimestampCounter;
-		_ed25519Cache.set(ck,cvn);
-	}
-#endif
 }
 
 bool C25519::verify(const C25519::Public &their,const void *msg,unsigned int len,const void *signature)
@@ -2135,20 +2079,6 @@ bool C25519::verify(const C25519::Public &their,const void *msg,unsigned int len
 	if (!Utils::secureEq(sig + 64,digest,32))
 		return false;
 
-#ifdef ZT_CONTROLLER
-	C25519CacheKey ck;
-	ZT_FAST_MEMCPY(ck.messageDigest,digest,32);
-	ZT_FAST_MEMCPY(ck.publicKey,their.data + 32,32);
-	C25519CacheValue *cv = (C25519CacheValue *)0;
-	{
-		Mutex::Lock l(_ed25519CacheLock);
-		cv = _ed25519Cache.get(ck);
-	}
-	if (cv) {
-		return Utils::secureEq(cv->signature,signature,ZT_C25519_SIGNATURE_LEN);
-	}
-#endif
-
 	unsigned char t2[32];
 	ge25519 get1, get2;
 	sc25519 schram, scs;
diff --git a/node/IncomingPacket.cpp b/node/IncomingPacket.cpp
index aec37a6b..9caa3093 100644
--- a/node/IncomingPacket.cpp
+++ b/node/IncomingPacket.cpp
@@ -761,9 +761,24 @@ bool IncomingPacket::_doECHO(const RuntimeEnvironment *RR,void *tPtr,const Share
 bool IncomingPacket::_doMULTICAST_LIKE(const RuntimeEnvironment *RR,void *tPtr,const SharedPtr<Peer> &peer)
 {
 	const int64_t now = RR->node->now();
+	bool authorized = false;
+	uint64_t lastNwid = 0;
+
 	// Packet contains a series of 18-byte network,MAC,ADI tuples
-	for(unsigned int ptr=ZT_PACKET_IDX_PAYLOAD;ptr<size();ptr+=18)
-		RR->mc->add(tPtr,now,at<uint64_t>(ptr),MulticastGroup(MAC(field(ptr + 8,6),6),at<uint32_t>(ptr + 14)),peer->address());
+	for(unsigned int ptr=ZT_PACKET_IDX_PAYLOAD;ptr<size();ptr+=18) {
+		const uint64_t nwid = at<uint64_t>(ptr);
+		if (nwid != lastNwid) {
+			lastNwid = nwid;
+			SharedPtr<Network> network(RR->node->network(nwid));
+			if (network)
+				authorized = network->gate(tPtr,peer);
+			if (!authorized)
+				authorized = ((RR->topology->amUpstream())||(RR->node->localControllerHasAuthorized(now,nwid,peer->address())));
+		}
+		if (authorized)
+			RR->mc->add(tPtr,now,nwid,MulticastGroup(MAC(field(ptr + 8,6),6),at<uint32_t>(ptr + 14)),peer->address());
+	}
+
 	peer->received(tPtr,_path,hops(),packetId(),payloadLength(),Packet::VERB_MULTICAST_LIKE,0,Packet::VERB_NOP,false,0);
 	return true;
 }
diff --git a/node/Membership.hpp b/node/Membership.hpp
index 55ba5373..90b6be6a 100644
--- a/node/Membership.hpp
+++ b/node/Membership.hpp
@@ -196,7 +196,7 @@ private:
 	}
 
 	template<typename C>
-	void _cleanCredImpl(const NetworkConfig &nconf,Hashtable<uint32_t,C> &remoteCreds)
+	inline void _cleanCredImpl(const NetworkConfig &nconf,Hashtable<uint32_t,C> &remoteCreds)
 	{
 		uint32_t *k = (uint32_t *)0;
 		C *v = (C *)0;
diff --git a/node/Node.cpp b/node/Node.cpp
index c96ae8fd..3342e6ca 100644
--- a/node/Node.cpp
+++ b/node/Node.cpp
@@ -270,11 +270,13 @@ ZT_ResultCode Node::processBackgroundTasks(void *tptr,int64_t now,volatile int64
 			RR->topology->getUpstreamsToContact(alwaysContact);
 
 			// Uncomment to dump stats
+			/*
 			for(unsigned int i=0;i<32;i++) {
 				if (_stats.inVerbCounts[i] > 0)
 					printf("%.2x\t%12lld %lld\n",i,(unsigned long long)_stats.inVerbCounts[i],(unsigned long long)_stats.inVerbBytes[i]);
 			}
 			printf("\n");
+			*/
 
 			// Check last receive time on designated upstreams to see if we seem to be online
 			int64_t lastReceivedFromUpstream = 0;
diff --git a/node/Packet.cpp b/node/Packet.cpp
index 3978cc48..448b421c 100644
--- a/node/Packet.cpp
+++ b/node/Packet.cpp
@@ -42,8 +42,8 @@
 #ifdef _MSC_VER
 #define FORCE_INLINE static __forceinline
 #include <intrin.h>
-#pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
-#pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */
+#pragma warning(disable : 4127)		/* disable: C4127: conditional expression is constant */
+#pragma warning(disable : 4293)		/* disable: C4293: too large shift (32-bits) */
 #else
 #define FORCE_INLINE static inline
 #endif
@@ -155,16 +155,16 @@ namespace {
   A library is provided to take care of it, see lz4frame.h.
 */
 
-#define LZ4_VERSION_MAJOR    1    /* for breaking interface changes  */
-#define LZ4_VERSION_MINOR    7    /* for new (non-breaking) interface capabilities */
-#define LZ4_VERSION_RELEASE  5    /* for tweaks, bug-fixes, or development */
+#define LZ4_VERSION_MAJOR	1	/* for breaking interface changes  */
+#define LZ4_VERSION_MINOR	7	/* for new (non-breaking) interface capabilities */
+#define LZ4_VERSION_RELEASE  5	/* for tweaks, bug-fixes, or development */
 #define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
 #define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE
 #define LZ4_QUOTE(str) #str
 #define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
 #define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION)
 #define LZ4_MEMORY_USAGE 14
-#define LZ4_MAX_INPUT_SIZE        0x7E000000   /* 2 113 929 216 bytes */
+#define LZ4_MAX_INPUT_SIZE		0x7E000000   /* 2 113 929 216 bytes */
 #define LZ4_COMPRESSBOUND(isize)  ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
 
 typedef union LZ4_stream_u LZ4_stream_t;   /* incomplete type (defined later) */
@@ -173,7 +173,7 @@ static inline void LZ4_resetStream (LZ4_stream_t* streamPtr);
 
 #define LZ4_HASHLOG   (LZ4_MEMORY_USAGE-2)
 #define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
-#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)       /* required as macro for static allocation */
+#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)	   /* required as macro for static allocation */
 
 typedef struct {
 	uint32_t hashTable[LZ4_HASH_SIZE_U32];
@@ -192,14 +192,14 @@ typedef struct {
 } LZ4_streamDecode_t_internal;
 
 #define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4)
-#define LZ4_STREAMSIZE     (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
+#define LZ4_STREAMSIZE	 (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
 union LZ4_stream_u {
 	unsigned long long table[LZ4_STREAMSIZE_U64];
 	LZ4_stream_t_internal internal_donotuse;
 } ;  /* previously typedef'd to LZ4_stream_t */
 
 #define LZ4_STREAMDECODESIZE_U64  4
-#define LZ4_STREAMDECODESIZE     (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long))
+#define LZ4_STREAMDECODESIZE	 (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long))
 union LZ4_streamDecode_u {
 	unsigned long long table[LZ4_STREAMDECODESIZE_U64];
 	LZ4_streamDecode_t_internal internal_donotuse;
@@ -224,8 +224,8 @@ union LZ4_streamDecode_u {
 #endif
 
 #define ALLOCATOR(n,s) calloc(n,s)
-#define FREEMEM        free
-#define MEM_INIT       memset
+#define FREEMEM		free
+#define MEM_INIT	   memset
 
 typedef  uint8_t BYTE;
 typedef uint16_t U16;
@@ -280,21 +280,21 @@ static inline void LZ4_write32(void* memPtr, U32 value)
 static inline U16 LZ4_readLE16(const void* memPtr)
 {
 	if (LZ4_isLittleEndian()) {
-	    return LZ4_read16(memPtr);
+		return LZ4_read16(memPtr);
 	} else {
-	    const BYTE* p = (const BYTE*)memPtr;
-	    return (U16)((U16)p[0] + (p[1]<<8));
+		const BYTE* p = (const BYTE*)memPtr;
+		return (U16)((U16)p[0] + (p[1]<<8));
 	}
 }
 
 static inline void LZ4_writeLE16(void* memPtr, U16 value)
 {
 	if (LZ4_isLittleEndian()) {
-	    LZ4_write16(memPtr, value);
+		LZ4_write16(memPtr, value);
 	} else {
-	    BYTE* p = (BYTE*)memPtr;
-	    p[0] = (BYTE) value;
-	    p[1] = (BYTE)(value>>8);
+		BYTE* p = (BYTE*)memPtr;
+		p[0] = (BYTE) value;
+		p[1] = (BYTE)(value>>8);
 	}
 }
 
@@ -330,63 +330,63 @@ static const int LZ4_minLength = (MFLIMIT+1);
 #define RUN_BITS (8-ML_BITS)
 #define RUN_MASK ((1U<<RUN_BITS)-1)
 
-#define LZ4_STATIC_ASSERT(c)    { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
+#define LZ4_STATIC_ASSERT(c)	{ enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
 
 static inline unsigned LZ4_NbCommonBytes (reg_t val)
 {
 	if (LZ4_isLittleEndian()) {
-	    if (sizeof(val)==8) {
-#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        unsigned long r = 0;
-	        _BitScanForward64( &r, (U64)val );
-	        return (int)(r>>3);
-#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        return (__builtin_ctzll((U64)val) >> 3);
-#       else
-	        static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
-	        return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
-#       endif
-	    } else /* 32 bits */ {
-#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        unsigned long r;
-	        _BitScanForward( &r, (U32)val );
-	        return (int)(r>>3);
-#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        return (__builtin_ctz((U32)val) >> 3);
-#       else
-	        static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
-	        return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
-#       endif
-	    }
+		if (sizeof(val)==8) {
+#	   if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			unsigned long r = 0;
+			_BitScanForward64( &r, (U64)val );
+			return (int)(r>>3);
+#	   elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			return (__builtin_ctzll((U64)val) >> 3);
+#	   else
+			static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
+			return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
+#	   endif
+		} else /* 32 bits */ {
+#	   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			unsigned long r;
+			_BitScanForward( &r, (U32)val );
+			return (int)(r>>3);
+#	   elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			return (__builtin_ctz((U32)val) >> 3);
+#	   else
+			static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
+			return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
+#	   endif
+		}
 	} else   /* Big Endian CPU */ {
-	    if (sizeof(val)==8) {
-#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        unsigned long r = 0;
-	        _BitScanReverse64( &r, val );
-	        return (unsigned)(r>>3);
-#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        return (__builtin_clzll((U64)val) >> 3);
-#       else
-	        unsigned r;
-	        if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
-	        if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
-	        r += (!val);
-	        return r;
-#       endif
-	    } else /* 32 bits */ {
-#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        unsigned long r = 0;
-	        _BitScanReverse( &r, (unsigned long)val );
-	        return (unsigned)(r>>3);
-#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-	        return (__builtin_clz((U32)val) >> 3);
-#       else
-	        unsigned r;
-	        if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
-	        r += (!val);
-	        return r;
-#       endif
-	    }
+		if (sizeof(val)==8) {
+#	   if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			unsigned long r = 0;
+			_BitScanReverse64( &r, val );
+			return (unsigned)(r>>3);
+#	   elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			return (__builtin_clzll((U64)val) >> 3);
+#	   else
+			unsigned r;
+			if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
+			if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
+			r += (!val);
+			return r;
+#	   endif
+		} else /* 32 bits */ {
+#	   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			unsigned long r = 0;
+			_BitScanReverse( &r, (unsigned long)val );
+			return (unsigned)(r>>3);
+#	   elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+			return (__builtin_clz((U32)val) >> 3);
+#	   else
+			unsigned r;
+			if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
+			r += (!val);
+			return r;
+#	   endif
+		}
 	}
 }
 
@@ -396,10 +396,10 @@ static inline unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE
 	const BYTE* const pStart = pIn;
 
 	while (likely(pIn<pInLimit-(STEPSIZE-1))) {
-	    reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
-	    if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
-	    pIn += LZ4_NbCommonBytes(diff);
-	    return (unsigned)(pIn - pStart);
+		reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+		if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
+		pIn += LZ4_NbCommonBytes(diff);
+		return (unsigned)(pIn - pStart);
 	}
 
 	if ((STEPSIZE==8) && (pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }
@@ -425,9 +425,9 @@ static inline int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize
 static inline U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
 {
 	if (tableType == byU16)
-	    return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
+		return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
 	else
-	    return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
+		return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
 }
 
 static inline U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
@@ -436,9 +436,9 @@ static inline U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
 	static const U64 prime8bytes = 11400714785074694791ULL;
 	const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
 	if (LZ4_isLittleEndian())
-	    return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
+		return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
 	else
-	    return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
+		return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
 }
 
 FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
@@ -477,16 +477,16 @@ FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableTy
 }
 
 FORCE_INLINE int LZ4_compress_generic(
-	             LZ4_stream_t_internal* const cctx,
-	             const char* const source,
-	             char* const dest,
-	             const int inputSize,
-	             const int maxOutputSize,
-	             const limitedOutput_directive outputLimited,
-	             const tableType_t tableType,
-	             const dict_directive dict,
-	             const dictIssue_directive dictIssue,
-	             const U32 acceleration)
+				 LZ4_stream_t_internal* const cctx,
+				 const char* const source,
+				 char* const dest,
+				 const int inputSize,
+				 const int maxOutputSize,
+				 const limitedOutput_directive outputLimited,
+				 const tableType_t tableType,
+				 const dict_directive dict,
+				 const dictIssue_directive dictIssue,
+				 const U32 acceleration)
 {
 	const BYTE* ip = (const BYTE*) source;
 	const BYTE* base;
@@ -511,20 +511,20 @@ FORCE_INLINE int LZ4_compress_generic(
 	{
 	case noDict:
 	default:
-	    base = (const BYTE*)source;
-	    lowLimit = (const BYTE*)source;
-	    break;
+		base = (const BYTE*)source;
+		lowLimit = (const BYTE*)source;
+		break;
 	case withPrefix64k:
-	    base = (const BYTE*)source - cctx->currentOffset;
-	    lowLimit = (const BYTE*)source - cctx->dictSize;
-	    break;
+		base = (const BYTE*)source - cctx->currentOffset;
+		lowLimit = (const BYTE*)source - cctx->dictSize;
+		break;
 	case usingExtDict:
-	    base = (const BYTE*)source - cctx->currentOffset;
-	    lowLimit = (const BYTE*)source;
-	    break;
+		base = (const BYTE*)source - cctx->currentOffset;
+		lowLimit = (const BYTE*)source;
+		break;
 	}
 	if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
-	if (inputSize<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */
+	if (inputSize<LZ4_minLength) goto _last_literals;				  /* Input too small, no compression (all literals) */
 
 	/* First Byte */
 	LZ4_putPosition(ip, cctx->hashTable, tableType, base);
@@ -532,143 +532,143 @@ FORCE_INLINE int LZ4_compress_generic(
 
 	/* Main Loop */
 	for ( ; ; ) {
-	    ptrdiff_t refDelta = 0;
-	    const BYTE* match;
-	    BYTE* token;
-
-	    /* Find a match */
-	    {   const BYTE* forwardIp = ip;
-	        unsigned step = 1;
-	        unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
-	        do {
-	            U32 const h = forwardH;
-	            ip = forwardIp;
-	            forwardIp += step;
-	            step = (searchMatchNb++ >> LZ4_skipTrigger);
-
-	            if (unlikely(forwardIp > mflimit)) goto _last_literals;
-
-	            match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
-	            if (dict==usingExtDict) {
-	                if (match < (const BYTE*)source) {
-	                    refDelta = dictDelta;
-	                    lowLimit = dictionary;
-	                } else {
-	                    refDelta = 0;
-	                    lowLimit = (const BYTE*)source;
-	            }   }
-	            forwardH = LZ4_hashPosition(forwardIp, tableType);
-	            LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
-
-	        } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
-	            || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
-	            || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
-	    }
-
-	    /* Catch up */
-	    while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
-
-	    /* Encode Literals */
-	    {   unsigned const litLength = (unsigned)(ip - anchor);
-	        token = op++;
-	        if ((outputLimited) &&  /* Check output buffer overflow */
-	            (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
-	            return 0;
-	        if (litLength >= RUN_MASK) {
-	            int len = (int)litLength-RUN_MASK;
-	            *token = (RUN_MASK<<ML_BITS);
-	            for(; len >= 255 ; len-=255) *op++ = 255;
-	            *op++ = (BYTE)len;
-	        }
-	        else *token = (BYTE)(litLength<<ML_BITS);
-
-	        /* Copy Literals */
-	        LZ4_wildCopy(op, anchor, op+litLength);
-	        op+=litLength;
-	    }
+		ptrdiff_t refDelta = 0;
+		const BYTE* match;
+		BYTE* token;
+
+		/* Find a match */
+		{   const BYTE* forwardIp = ip;
+			unsigned step = 1;
+			unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
+			do {
+				U32 const h = forwardH;
+				ip = forwardIp;
+				forwardIp += step;
+				step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+				if (unlikely(forwardIp > mflimit)) goto _last_literals;
+
+				match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
+				if (dict==usingExtDict) {
+					if (match < (const BYTE*)source) {
+						refDelta = dictDelta;
+						lowLimit = dictionary;
+					} else {
+						refDelta = 0;
+						lowLimit = (const BYTE*)source;
+				}   }
+				forwardH = LZ4_hashPosition(forwardIp, tableType);
+				LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
+
+			} while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
+				|| ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
+				|| (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
+		}
+
+		/* Catch up */
+		while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
+
+		/* Encode Literals */
+		{   unsigned const litLength = (unsigned)(ip - anchor);
+			token = op++;
+			if ((outputLimited) &&  /* Check output buffer overflow */
+				(unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
+				return 0;
+			if (litLength >= RUN_MASK) {
+				int len = (int)litLength-RUN_MASK;
+				*token = (RUN_MASK<<ML_BITS);
+				for(; len >= 255 ; len-=255) *op++ = 255;
+				*op++ = (BYTE)len;
+			}
+			else *token = (BYTE)(litLength<<ML_BITS);
+
+			/* Copy Literals */
+			LZ4_wildCopy(op, anchor, op+litLength);
+			op+=litLength;
+		}
 
 _next_match:
-	    /* Encode Offset */
-	    LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
-
-	    /* Encode MatchLength */
-	    {   unsigned matchCode;
-
-	        if ((dict==usingExtDict) && (lowLimit==dictionary)) {
-	            const BYTE* limit;
-	            match += refDelta;
-	            limit = ip + (dictEnd-match);
-	            if (limit > matchlimit) limit = matchlimit;
-	            matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
-	            ip += MINMATCH + matchCode;
-	            if (ip==limit) {
-	                unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit);
-	                matchCode += more;
-	                ip += more;
-	            }
-	        } else {
-	            matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
-	            ip += MINMATCH + matchCode;
-	        }
-
-	        if ( outputLimited &&    /* Check output buffer overflow */
-	            (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
-	            return 0;
-	        if (matchCode >= ML_MASK) {
-	            *token += ML_MASK;
-	            matchCode -= ML_MASK;
-	            LZ4_write32(op, 0xFFFFFFFF);
-	            while (matchCode >= 4*255) op+=4, LZ4_write32(op, 0xFFFFFFFF), matchCode -= 4*255;
-	            op += matchCode / 255;
-	            *op++ = (BYTE)(matchCode % 255);
-	        } else
-	            *token += (BYTE)(matchCode);
-	    }
-
-	    anchor = ip;
-
-	    /* Test end of chunk */
-	    if (ip > mflimit) break;
-
-	    /* Fill table */
-	    LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
-
-	    /* Test next position */
-	    match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
-	    if (dict==usingExtDict) {
-	        if (match < (const BYTE*)source) {
-	            refDelta = dictDelta;
-	            lowLimit = dictionary;
-	        } else {
-	            refDelta = 0;
-	            lowLimit = (const BYTE*)source;
-	    }   }
-	    LZ4_putPosition(ip, cctx->hashTable, tableType, base);
-	    if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
-	        && (match+MAX_DISTANCE>=ip)
-	        && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
-	    { token=op++; *token=0; goto _next_match; }
-
-	    /* Prepare next loop */
-	    forwardH = LZ4_hashPosition(++ip, tableType);
+		/* Encode Offset */
+		LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+
+		/* Encode MatchLength */
+		{   unsigned matchCode;
+
+			if ((dict==usingExtDict) && (lowLimit==dictionary)) {
+				const BYTE* limit;
+				match += refDelta;
+				limit = ip + (dictEnd-match);
+				if (limit > matchlimit) limit = matchlimit;
+				matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
+				ip += MINMATCH + matchCode;
+				if (ip==limit) {
+					unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+					matchCode += more;
+					ip += more;
+				}
+			} else {
+				matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
+				ip += MINMATCH + matchCode;
+			}
+
+			if ( outputLimited &&	/* Check output buffer overflow */
+				(unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
+				return 0;
+			if (matchCode >= ML_MASK) {
+				*token += ML_MASK;
+				matchCode -= ML_MASK;
+				LZ4_write32(op, 0xFFFFFFFF);
+				while (matchCode >= 4*255) op+=4, LZ4_write32(op, 0xFFFFFFFF), matchCode -= 4*255;
+				op += matchCode / 255;
+				*op++ = (BYTE)(matchCode % 255);
+			} else
+				*token += (BYTE)(matchCode);
+		}
+
+		anchor = ip;
+
+		/* Test end of chunk */
+		if (ip > mflimit) break;
+
+		/* Fill table */
+		LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
+
+		/* Test next position */
+		match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
+		if (dict==usingExtDict) {
+			if (match < (const BYTE*)source) {
+				refDelta = dictDelta;
+				lowLimit = dictionary;
+			} else {
+				refDelta = 0;
+				lowLimit = (const BYTE*)source;
+		}   }
+		LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+		if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
+			&& (match+MAX_DISTANCE>=ip)
+			&& (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
+		{ token=op++; *token=0; goto _next_match; }
+
+		/* Prepare next loop */
+		forwardH = LZ4_hashPosition(++ip, tableType);
 	}
 
 _last_literals:
 	/* Encode Last Literals */
 	{   size_t const lastRun = (size_t)(iend - anchor);
-	    if ( (outputLimited) &&  /* Check output buffer overflow */
-	        ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
-	        return 0;
-	    if (lastRun >= RUN_MASK) {
-	        size_t accumulator = lastRun - RUN_MASK;
-	        *op++ = RUN_MASK << ML_BITS;
-	        for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
-	        *op++ = (BYTE) accumulator;
-	    } else {
-	        *op++ = (BYTE)(lastRun<<ML_BITS);
-	    }
-	    ZT_FAST_MEMCPY(op, anchor, lastRun);
-	    op += lastRun;
+		if ( (outputLimited) &&  /* Check output buffer overflow */
+			((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
+			return 0;
+		if (lastRun >= RUN_MASK) {
+			size_t accumulator = lastRun - RUN_MASK;
+			*op++ = RUN_MASK << ML_BITS;
+			for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+			*op++ = (BYTE) accumulator;
+		} else {
+			*op++ = (BYTE)(lastRun<<ML_BITS);
+		}
+		ZT_FAST_MEMCPY(op, anchor, lastRun);
+		op += lastRun;
 	}
 
 	/* End */
@@ -682,15 +682,15 @@ static inline int LZ4_compress_fast_extState(void* state, const char* source, ch
 	//if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
 
 	if (maxOutputSize >= LZ4_compressBound(inputSize)) {
-	    if (inputSize < LZ4_64Klimit)
-	        return LZ4_compress_generic(ctx, source, dest, inputSize,             0,    notLimited,                        byU16, noDict, noDictIssue, acceleration);
-	    else
-	        return LZ4_compress_generic(ctx, source, dest, inputSize,             0,    notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+		if (inputSize < LZ4_64Klimit)
+			return LZ4_compress_generic(ctx, source, dest, inputSize,			 0,	notLimited,						byU16, noDict, noDictIssue, acceleration);
+		else
+			return LZ4_compress_generic(ctx, source, dest, inputSize,			 0,	notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
 	} else {
-	    if (inputSize < LZ4_64Klimit)
-	        return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput,                        byU16, noDict, noDictIssue, acceleration);
-	    else
-	        return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+		if (inputSize < LZ4_64Klimit)
+			return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput,						byU16, noDict, noDictIssue, acceleration);
+		else
+			return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
 	}
 }
 
@@ -717,19 +717,19 @@ static inline void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
 }
 
 FORCE_INLINE int LZ4_decompress_generic(
-	             const char* const source,
-	             char* const dest,
-	             int inputSize,
-	             int outputSize,         /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */
-
-	             int endOnInput,         /* endOnOutputSize, endOnInputSize */
-	             int partialDecoding,    /* full, partial */
-	             int targetOutputSize,   /* only used if partialDecoding==partial */
-	             int dict,               /* noDict, withPrefix64k, usingExtDict */
-	             const BYTE* const lowPrefix,  /* == dest when no prefix */
-	             const BYTE* const dictStart,  /* only if dict==usingExtDict */
-	             const size_t dictSize         /* note : = 0 if noDict */
-	             )
+				 const char* const source,
+				 char* const dest,
+				 int inputSize,
+				 int outputSize,		 /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */
+
+				 int endOnInput,		 /* endOnOutputSize, endOnInputSize */
+				 int partialDecoding,	/* full, partial */
+				 int targetOutputSize,   /* only used if partialDecoding==partial */
+				 int dict,			   /* noDict, withPrefix64k, usingExtDict */
+				 const BYTE* const lowPrefix,  /* == dest when no prefix */
+				 const BYTE* const dictStart,  /* only if dict==usingExtDict */
+				 const size_t dictSize		 /* note : = 0 if noDict */
+				 )
 {
 	/* Local Variables */
 	const BYTE* ip = (const BYTE*) source;
@@ -750,125 +750,125 @@ FORCE_INLINE int LZ4_decompress_generic(
 
 
 	/* Special cases */
-	if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT;                        /* targetOutputSize too high => decode everything */
+	if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT;						/* targetOutputSize too high => decode everything */
 	if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
 	if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);
 
 	/* Main Loop : decode sequences */
 	while (1) {
-	    size_t length;
-	    const BYTE* match;
-	    size_t offset;
-
-	    /* get literal length */
-	    unsigned const token = *ip++;
-	    if ((length=(token>>ML_BITS)) == RUN_MASK) {
-	        unsigned s;
-	        do {
-	            s = *ip++;
-	            length += s;
-	        } while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) & (s==255) );
-	        if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error;   /* overflow detection */
-	        if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error;   /* overflow detection */
-	    }
-
-	    /* copy literals */
-	    cpy = op+length;
-	    if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
-	        || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
-	    {
-	        if (partialDecoding) {
-	            if (cpy > oend) goto _output_error;                           /* Error : write attempt beyond end of output buffer */
-	            if ((endOnInput) && (ip+length > iend)) goto _output_error;   /* Error : read attempt beyond end of input buffer */
-	        } else {
-	            if ((!endOnInput) && (cpy != oend)) goto _output_error;       /* Error : block decoding must stop exactly there */
-	            if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error;   /* Error : input must be consumed */
-	        }
-	        ZT_FAST_MEMCPY(op, ip, length);
-	        ip += length;
-	        op += length;
-	        break;     /* Necessarily EOF, due to parsing restrictions */
-	    }
-	    LZ4_wildCopy(op, ip, cpy);
-	    ip += length; op = cpy;
-
-	    /* get offset */
-	    offset = LZ4_readLE16(ip); ip+=2;
-	    match = op - offset;
-	    if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error;   /* Error : offset outside buffers */
-	    LZ4_write32(op, (U32)offset);   /* costs ~1%; silence an msan warning when offset==0 */
-
-	    /* get matchlength */
-	    length = token & ML_MASK;
-	    if (length == ML_MASK) {
-	        unsigned s;
-	        do {
-	            s = *ip++;
-	            if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
-	            length += s;
-	        } while (s==255);
-	        if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
-	    }
-	    length += MINMATCH;
-
-	    /* check external dictionary */
-	    if ((dict==usingExtDict) && (match < lowPrefix)) {
-	        if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */
-
-	        if (length <= (size_t)(lowPrefix-match)) {
-	            /* match can be copied as a single segment from external dictionary */
-	            memmove(op, dictEnd - (lowPrefix-match), length);
-	            op += length;
-	        } else {
-	            /* match encompass external dictionary and current block */
-	            size_t const copySize = (size_t)(lowPrefix-match);
-	            size_t const restSize = length - copySize;
-	            ZT_FAST_MEMCPY(op, dictEnd - copySize, copySize);
-	            op += copySize;
-	            if (restSize > (size_t)(op-lowPrefix)) {  /* overlap copy */
-	                BYTE* const endOfMatch = op + restSize;
-	                const BYTE* copyFrom = lowPrefix;
-	                while (op < endOfMatch) *op++ = *copyFrom++;
-	            } else {
-	                ZT_FAST_MEMCPY(op, lowPrefix, restSize);
-	                op += restSize;
-	        }   }
-	        continue;
-	    }
-
-	    /* copy match within block */
-	    cpy = op + length;
-	    if (unlikely(offset<8)) {
-	        const int dec64 = dec64table[offset];
-	        op[0] = match[0];
-	        op[1] = match[1];
-	        op[2] = match[2];
-	        op[3] = match[3];
-	        match += dec32table[offset];
-	        ZT_FAST_MEMCPY(op+4, match, 4);
-	        match -= dec64;
-	    } else { LZ4_copy8(op, match); match+=8; }
-	    op += 8;
-
-	    if (unlikely(cpy>oend-12)) {
-	        BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
-	        if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
-	        if (op < oCopyLimit) {
-	            LZ4_wildCopy(op, match, oCopyLimit);
-	            match += oCopyLimit - op;
-	            op = oCopyLimit;
-	        }
-	        while (op<cpy) *op++ = *match++;
-	    } else {
-	        LZ4_copy8(op, match);
-	        if (length>16) LZ4_wildCopy(op+8, match+8, cpy);
-	    }
-	    op=cpy;   /* correction */
+		size_t length;
+		const BYTE* match;
+		size_t offset;
+
+		/* get literal length */
+		unsigned const token = *ip++;
+		if ((length=(token>>ML_BITS)) == RUN_MASK) {
+			unsigned s;
+			do {
+				s = *ip++;
+				length += s;
+			} while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) & (s==255) );
+			if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error;   /* overflow detection */
+			if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error;   /* overflow detection */
+		}
+
+		/* copy literals */
+		cpy = op+length;
+		if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
+			|| ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
+		{
+			if (partialDecoding) {
+				if (cpy > oend) goto _output_error;						   /* Error : write attempt beyond end of output buffer */
+				if ((endOnInput) && (ip+length > iend)) goto _output_error;   /* Error : read attempt beyond end of input buffer */
+			} else {
+				if ((!endOnInput) && (cpy != oend)) goto _output_error;	   /* Error : block decoding must stop exactly there */
+				if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error;   /* Error : input must be consumed */
+			}
+			ZT_FAST_MEMCPY(op, ip, length);
+			ip += length;
+			op += length;
+			break;	 /* Necessarily EOF, due to parsing restrictions */
+		}
+		LZ4_wildCopy(op, ip, cpy);
+		ip += length; op = cpy;
+
+		/* get offset */
+		offset = LZ4_readLE16(ip); ip+=2;
+		match = op - offset;
+		if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error;   /* Error : offset outside buffers */
+		LZ4_write32(op, (U32)offset);   /* costs ~1%; silence an msan warning when offset==0 */
+
+		/* get matchlength */
+		length = token & ML_MASK;
+		if (length == ML_MASK) {
+			unsigned s;
+			do {
+				s = *ip++;
+				if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
+				length += s;
+			} while (s==255);
+			if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
+		}
+		length += MINMATCH;
+
+		/* check external dictionary */
+		if ((dict==usingExtDict) && (match < lowPrefix)) {
+			if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */
+
+			if (length <= (size_t)(lowPrefix-match)) {
+				/* match can be copied as a single segment from external dictionary */
+				memmove(op, dictEnd - (lowPrefix-match), length);
+				op += length;
+			} else {
+				/* match encompass external dictionary and current block */
+				size_t const copySize = (size_t)(lowPrefix-match);
+				size_t const restSize = length - copySize;
+				ZT_FAST_MEMCPY(op, dictEnd - copySize, copySize);
+				op += copySize;
+				if (restSize > (size_t)(op-lowPrefix)) {  /* overlap copy */
+					BYTE* const endOfMatch = op + restSize;
+					const BYTE* copyFrom = lowPrefix;
+					while (op < endOfMatch) *op++ = *copyFrom++;
+				} else {
+					ZT_FAST_MEMCPY(op, lowPrefix, restSize);
+					op += restSize;
+			}   }
+			continue;
+		}
+
+		/* copy match within block */
+		cpy = op + length;
+		if (unlikely(offset<8)) {
+			const int dec64 = dec64table[offset];
+			op[0] = match[0];
+			op[1] = match[1];
+			op[2] = match[2];
+			op[3] = match[3];
+			match += dec32table[offset];
+			ZT_FAST_MEMCPY(op+4, match, 4);
+			match -= dec64;
+		} else { LZ4_copy8(op, match); match+=8; }
+		op += 8;
+
+		if (unlikely(cpy>oend-12)) {
+			BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
+			if (cpy > oend-LASTLITERALS) goto _output_error;	/* Error : last LASTLITERALS bytes must be literals (uncompressed) */
+			if (op < oCopyLimit) {
+				LZ4_wildCopy(op, match, oCopyLimit);
+				match += oCopyLimit - op;
+				op = oCopyLimit;
+			}
+			while (op<cpy) *op++ = *match++;
+		} else {
+			LZ4_copy8(op, match);
+			if (length>16) LZ4_wildCopy(op+8, match+8, cpy);
+		}
+		op=cpy;   /* correction */
 	}
 
 	/* end of decoding */
 	if (endOnInput)
-	   return (int) (((char*)op)-dest);     /* Nb of output bytes decoded */
+	   return (int) (((char*)op)-dest);	 /* Nb of output bytes decoded */
 	else
 	   return (int) (((const char*)ip)-source);   /* Nb of input bytes read */
 
@@ -989,7 +989,7 @@ bool Packet::compress()
 
 	if ((!compressed())&&(size() > (ZT_PACKET_IDX_PAYLOAD + 64))) { // don't bother compressing tiny packets
 		int pl = (int)(size() - ZT_PACKET_IDX_PAYLOAD);
-		int cl = LZ4_compress_fast(data + ZT_PACKET_IDX_PAYLOAD,buf,pl,ZT_PROTO_MAX_PACKET_LENGTH * 2,2);
+		int cl = LZ4_compress_fast(data + ZT_PACKET_IDX_PAYLOAD,buf,pl,ZT_PROTO_MAX_PACKET_LENGTH * 2,1);
 		if ((cl > 0)&&(cl < pl)) {
 			data[ZT_PACKET_IDX_VERB] |= (char)ZT_PROTO_VERB_FLAG_COMPRESSED;
 			setSize((unsigned int)cl + ZT_PACKET_IDX_PAYLOAD);