${CMAKE_CURRENT_SOURCE_DIR}/ffdecsa

    ${CMAKE_CURRENT_SOURCE_DIR}/ffdecsa

execute_process (COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/config.sh --enabled WITH_EMU OUTPUT_VARIABLE CONFIG_WITH_EMU OUTPUT_STRIP_TRAILING_WHITESPACE)

if (CONFIG_WITH_EMU MATCHES "Y" AND NOT WITH_EMU EQUAL 1)

	add_definitions ("-DWITH_EMU")

	set (WITH_EMU "1")

	message(STATUS "  EMU is added by config compiling with EMU")

endif(CONFIG_WITH_EMU MATCHES "Y" AND NOT WITH_EMU EQUAL 1)

add_subdirectory (ffdecsa)

#enable sse2 on x86

if (CMAKE_SYSTEM_PROCESSOR MATCHES "(x86)|(X86)|(amd64)|(AMD64)")

    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -msse -msse2 -msse3")

endif (CMAKE_SYSTEM_PROCESSOR MATCHES "(x86)|(X86)|(amd64)|(AMD64)")

if (NOT OSCamOperatingSystem MATCHES "Mac OS X")

if (NOT DEFINED ENV{ANDROID_NDK})

if (NOT DEFINED ENV{ANDROID_STANDALONE_TOOLCHAIN})

  if(WITH_EMU)

	if(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/SoftCam.Key)

 		execute_process(COMMAND cp ${CMAKE_CURRENT_SOURCE_DIR}/SoftCam.Key ${CMAKE_CURRENT_BINARY_DIR}/SoftCam.Key)

	else(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/SoftCam.Key)

		execute_process(COMMAND touch ${CMAKE_CURRENT_BINARY_DIR}/SoftCam.Key)

	endif(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/SoftCam.Key)

	execute_process(COMMAND touch ${CMAKE_CURRENT_BINARY_DIR}/utils/SoftCam.Key)

	set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--format=binary -Wl,SoftCam.Key -Wl,--format=default" ) 

 endif(WITH_EMU)

endif (NOT DEFINED ENV{ANDROID_STANDALONE_TOOLCHAIN})

endif (NOT DEFINED ENV{ANDROID_NDK})

endif (NOT OSCamOperatingSystem MATCHES "Mac OS X")

if (WITH_EMU)

	message(STATUS "  Compile with EMU support")

endif (WITH_EMU)

TARGETHELP := $(shell $(CC) --target-help 2>&1)

ifneq (,$(findstring sse2,$(TARGETHELP)))

override CFLAGS += -fexpensive-optimizations -mmmx -msse -msse2 -msse3

else

override CFLAGS += -fexpensive-optimizations

endif

SRC-$(CONFIG_WITH_EMU) += module-emulator.c

SRC-$(CONFIG_WITH_EMU) += module-emulator-osemu.c

SRC-$(CONFIG_WITH_EMU) += module-emulator-stream.c

SRC-$(CONFIG_WITH_EMU) += ffdecsa/ffdecsa.c

UNAME := $(shell uname -s)

ifneq ($(UNAME),Darwin)

ifndef ANDROID_NDK

ifndef ANDROID_STANDALONE_TOOLCHAIN

ifeq "$(CONFIG_WITH_EMU)" "y"

TOUCH_SK := $(shell touch SoftCam.Key)

override LDFLAGS += -Wl,--format=binary -Wl,SoftCam.Key -Wl,--format=default

endif

endif

endif

endif

#define WITH_EMU 1

CONFIG_WITH_EMU=y

	enabled WITH_EMU && enable_opt READER_VIACCESS >/dev/null

	enabled WITH_EMU && enable_opt READER_DRE >/dev/null

	enabled WITH_EMU && enable_opt MODULE_NEWCAMD >/dev/null

		WITH_EMU			"Emulator support"						$(check_test "WITH_EMU") \

void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,

					 const unsigned long length, const AES_KEY *key,

					 unsigned char *ivec, const int enc)

{

	unsigned long n;

	unsigned long len = length;

	unsigned char tmp[AES_BLOCK_SIZE];

	assert(in && out && key && ivec);

	assert((AES_ENCRYPT == enc)||(AES_DECRYPT == enc));

	if(AES_ENCRYPT == enc)

	{

		while(len >= AES_BLOCK_SIZE)

		{

			for(n=0; n < AES_BLOCK_SIZE; ++n)

				tmp[n] = in[n] ^ ivec[n];

			AES_encrypt(tmp, out, key);

			memcpy(ivec, out, AES_BLOCK_SIZE);

			len -= AES_BLOCK_SIZE;

			in += AES_BLOCK_SIZE;

			out += AES_BLOCK_SIZE;

		}

		if(len)

		{

			for(n=0; n < len; ++n)

				tmp[n] = in[n] ^ ivec[n];

			for(n=len; n < AES_BLOCK_SIZE; ++n)

				tmp[n] = ivec[n];

			AES_encrypt(tmp, tmp, key);

			memcpy(out, tmp, AES_BLOCK_SIZE);

			memcpy(ivec, tmp, AES_BLOCK_SIZE);

		}

	}

	else

	{

		while(len >= AES_BLOCK_SIZE)

		{

			memcpy(tmp, in, AES_BLOCK_SIZE);

			AES_decrypt(in, out, key);

			for(n=0; n < AES_BLOCK_SIZE; ++n)

				out[n] ^= ivec[n];

			memcpy(ivec, tmp, AES_BLOCK_SIZE);

			len -= AES_BLOCK_SIZE;

			in += AES_BLOCK_SIZE;

			out += AES_BLOCK_SIZE;

		}

		if(len)

		{

			memcpy(tmp, in, AES_BLOCK_SIZE);

			AES_decrypt(tmp, tmp, key);

			for(n=0; n < len; ++n)

				out[n] ^= ivec[n];

			memcpy(ivec, tmp, AES_BLOCK_SIZE);

		}

	}

}

void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,

					 const unsigned long length, const AES_KEY *key,

					 unsigned char *ivec, const int enc);

void MD5_Init(MD5_CTX *ctx);

void MD5_Update(MD5_CTX *ctx, const unsigned char *buf, unsigned int len);

void MD5_Final(unsigned char digest[MD5_DIGEST_LENGTH], MD5_CTX *ctx);

char *__md5_crypt(const char *text_pass, const char *salt, char *crypted_passwd);

#endif

extern const struct s_cardreader cardreader_emu;

project (ffdecsa)

file (GLOB ffdecsa_srcs "ffdecsa.c")

file (GLOB ffdecsa_hdrs "*.h")

set (lib_name "ffdecsa")

add_library (${lib_name} STATIC ${ffdecsa_srcs} ${ffdecsa_hdrs})

		    GNU GENERAL PUBLIC LICENSE

		       Version 2, June 1991

 Copyright (C) 1989, 1991 Free Software Foundation, Inc.

                          675 Mass Ave, Cambridge, MA 02139, USA

 Everyone is permitted to copy and distribute verbatim copies

 of this license document, but changing it is not allowed.

			    Preamble

  The licenses for most software are designed to take away your

freedom to share and change it.  By contrast, the GNU General Public

License is intended to guarantee your freedom to share and change free

software--to make sure the software is free for all its users.  This

General Public License applies to most of the Free Software

Foundation's software and to any other program whose authors commit to

using it.  (Some other Free Software Foundation software is covered by

the GNU Library General Public License instead.)  You can apply it to

your programs, too.

  When we speak of free software, we are referring to freedom, not

price.  Our General Public Licenses are designed to make sure that you

have the freedom to distribute copies of free software (and charge for

this service if you wish), that you receive source code or can get it

if you want it, that you can change the software or use pieces of it

in new free programs; and that you know you can do these things.

  To protect your rights, we need to make restrictions that forbid

anyone to deny you these rights or to ask you to surrender the rights.

These restrictions translate to certain responsibilities for you if you

distribute copies of the software, or if you modify it.

  For example, if you distribute copies of such a program, whether

gratis or for a fee, you must give the recipients all the rights that

you have.  You must make sure that they, too, receive or can get the

source code.  And you must show them these terms so they know their

rights.

  We protect your rights with two steps: (1) copyright the software, and

(2) offer you this license which gives you legal permission to copy,

distribute and/or modify the software.

  Also, for each author's protection and ours, we want to make certain

that everyone understands that there is no warranty for this free

software.  If the software is modified by someone else and passed on, we

want its recipients to know that what they have is not the original, so

that any problems introduced by others will not reflect on the original

authors' reputations.

  Finally, any free program is threatened constantly by software

patents.  We wish to avoid the danger that redistributors of a free

program will individually obtain patent licenses, in effect making the

program proprietary.  To prevent this, we have made it clear that any

patent must be licensed for everyone's free use or not licensed at all.

  The precise terms and conditions for copying, distribution and

modification follow.

		    GNU GENERAL PUBLIC LICENSE

   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION

  0. This License applies to any program or other work which contains

a notice placed by the copyright holder saying it may be distributed

under the terms of this General Public License.  The "Program", below,

refers to any such program or work, and a "work based on the Program"

means either the Program or any derivative work under copyright law:

that is to say, a work containing the Program or a portion of it,

either verbatim or with modifications and/or translated into another

language.  (Hereinafter, translation is included without limitation in

the term "modification".)  Each licensee is addressed as "you".

Activities other than copying, distribution and modification are not

covered by this License; they are outside its scope.  The act of

running the Program is not restricted, and the output from the Program

is covered only if its contents constitute a work based on the

Program (independent of having been made by running the Program).

Whether that is true depends on what the Program does.

  1. You may copy and distribute verbatim copies of the Program's

source code as you receive it, in any medium, provided that you

conspicuously and appropriately publish on each copy an appropriate

copyright notice and disclaimer of warranty; keep intact all the

notices that refer to this License and to the absence of any warranty;

and give any other recipients of the Program a copy of this License

along with the Program.

You may charge a fee for the physical act of transferring a copy, and

you may at your option offer warranty protection in exchange for a fee.

  2. You may modify your copy or copies of the Program or any portion

of it, thus forming a work based on the Program, and copy and

distribute such modifications or work under the terms of Section 1

above, provided that you also meet all of these conditions:

    a) You must cause the modified files to carry prominent notices

    stating that you changed the files and the date of any change.

    b) You must cause any work that you distribute or publish, that in

    whole or in part contains or is derived from the Program or any

    part thereof, to be licensed as a whole at no charge to all third

    parties under the terms of this License.

    c) If the modified program normally reads commands interactively

    when run, you must cause it, when started running for such

    interactive use in the most ordinary way, to print or display an

    announcement including an appropriate copyright notice and a

    notice that there is no warranty (or else, saying that you provide

    a warranty) and that users may redistribute the program under

    these conditions, and telling the user how to view a copy of this

    License.  (Exception: if the Program itself is interactive but

    does not normally print such an announcement, your work based on

    the Program is not required to print an announcement.)

These requirements apply to the modified work as a whole.  If

identifiable sections of that work are not derived from the Program,

and can be reasonably considered independent and separate works in

themselves, then this License, and its terms, do not apply to those

sections when you distribute them as separate works.  But when you

distribute the same sections as part of a whole which is a work based

on the Program, the distribution of the whole must be on the terms of

this License, whose permissions for other licensees extend to the

entire whole, and thus to each and every part regardless of who wrote it.

Thus, it is not the intent of this section to claim rights or contest

your rights to work written entirely by you; rather, the intent is to

exercise the right to control the distribution of derivative or

collective works based on the Program.

In addition, mere aggregation of another work not based on the Program

with the Program (or with a work based on the Program) on a volume of

a storage or distribution medium does not bring the other work under

the scope of this License.

  3. You may copy and distribute the Program (or a work based on it,

under Section 2) in object code or executable form under the terms of

Sections 1 and 2 above provided that you also do one of the following:

    a) Accompany it with the complete corresponding machine-readable

    source code, which must be distributed under the terms of Sections

    1 and 2 above on a medium customarily used for software interchange; or,

    b) Accompany it with a written offer, valid for at least three

    years, to give any third party, for a charge no more than your

    cost of physically performing source distribution, a complete

    machine-readable copy of the corresponding source code, to be

    distributed under the terms of Sections 1 and 2 above on a medium

    customarily used for software interchange; or,

    c) Accompany it with the information you received as to the offer

    to distribute corresponding source code.  (This alternative is

    allowed only for noncommercial distribution and only if you

    received the program in object code or executable form with such

    an offer, in accord with Subsection b above.)

The source code for a work means the preferred form of the work for

making modifications to it.  For an executable work, complete source

code means all the source code for all modules it contains, plus any

associated interface definition files, plus the scripts used to

control compilation and installation of the executable.  However, as a

special exception, the source code distributed need not include

anything that is normally distributed (in either source or binary

form) with the major components (compiler, kernel, and so on) of the

operating system on which the executable runs, unless that component

itself accompanies the executable.

If distribution of executable or object code is made by offering

access to copy from a designated place, then offering equivalent

access to copy the source code from the same place counts as

distribution of the source code, even though third parties are not

compelled to copy the source along with the object code.

  4. You may not copy, modify, sublicense, or distribute the Program

except as expressly provided under this License.  Any attempt

otherwise to copy, modify, sublicense or distribute the Program is

void, and will automatically terminate your rights under this License.

However, parties who have received copies, or rights, from you under

this License will not have their licenses terminated so long as such

parties remain in full compliance.

  5. You are not required to accept this License, since you have not

signed it.  However, nothing else grants you permission to modify or

distribute the Program or its derivative works.  These actions are

prohibited by law if you do not accept this License.  Therefore, by

modifying or distributing the Program (or any work based on the

Program), you indicate your acceptance of this License to do so, and

all its terms and conditions for copying, distributing or modifying

the Program or works based on it.

  6. Each time you redistribute the Program (or any work based on the

Program), the recipient automatically receives a license from the

original licensor to copy, distribute or modify the Program subject to

these terms and conditions.  You may not impose any further

restrictions on the recipients' exercise of the rights granted herein.

You are not responsible for enforcing compliance by third parties to

this License.

  7. If, as a consequence of a court judgment or allegation of patent

infringement or for any other reason (not limited to patent issues),

conditions are imposed on you (whether by court order, agreement or

otherwise) that contradict the conditions of this License, they do not

excuse you from the conditions of this License.  If you cannot

distribute so as to satisfy simultaneously your obligations under this

License and any other pertinent obligations, then as a consequence you

may not distribute the Program at all.  For example, if a patent

license would not permit royalty-free redistribution of the Program by

all those who receive copies directly or indirectly through you, then

the only way you could satisfy both it and this License would be to

refrain entirely from distribution of the Program.

If any portion of this section is held invalid or unenforceable under

any particular circumstance, the balance of the section is intended to

apply and the section as a whole is intended to apply in other

circumstances.

It is not the purpose of this section to induce you to infringe any

patents or other property right claims or to contest validity of any

such claims; this section has the sole purpose of protecting the

integrity of the free software distribution system, which is

implemented by public license practices.  Many people have made

generous contributions to the wide range of software distributed

through that system in reliance on consistent application of that

system; it is up to the author/donor to decide if he or she is willing

to distribute software through any other system and a licensee cannot

impose that choice.

This section is intended to make thoroughly clear what is believed to

be a consequence of the rest of this License.

  8. If the distribution and/or use of the Program is restricted in

certain countries either by patents or by copyrighted interfaces, the

original copyright holder who places the Program under this License

may add an explicit geographical distribution limitation excluding

those countries, so that distribution is permitted only in or among

countries not thus excluded.  In such case, this License incorporates

the limitation as if written in the body of this License.

  9. The Free Software Foundation may publish revised and/or new versions

of the General Public License from time to time.  Such new versions will

be similar in spirit to the present version, but may differ in detail to

address new problems or concerns.

Each version is given a distinguishing version number.  If the Program

specifies a version number of this License which applies to it and "any

later version", you have the option of following the terms and conditions

either of that version or of any later version published by the Free

Software Foundation.  If the Program does not specify a version number of

this License, you may choose any version ever published by the Free Software

Foundation.

  10. If you wish to incorporate parts of the Program into other free

programs whose distribution conditions are different, write to the author

to ask for permission.  For software which is copyrighted by the Free

Software Foundation, write to the Free Software Foundation; we sometimes

make exceptions for this.  Our decision will be guided by the two goals

of preserving the free status of all derivatives of our free software and

of promoting the sharing and reuse of software generally.

			    NO WARRANTY

  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY

FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN

OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES

PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED

OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF

MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS

TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE

PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,

REPAIR OR CORRECTION.

  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING

WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR

REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,

INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING

OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED

TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY

YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER

PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE

POSSIBILITY OF SUCH DAMAGES.

		     END OF TERMS AND CONDITIONS

	Appendix: How to Apply These Terms to Your New Programs

  If you develop a new program, and you want it to be of the greatest

possible use to the public, the best way to achieve this is to make it

free software which everyone can redistribute and change under these terms.

  To do so, attach the following notices to the program.  It is safest

to attach them to the start of each source file to most effectively

convey the exclusion of warranty; and each file should have at least

the "copyright" line and a pointer to where the full notice is found.

    <one line to give the program's name and a brief idea of what it does.>

    Copyright (C) 19yy  <name of author>

    This program is free software; you can redistribute it and/or modify

    it under the terms of the GNU General Public License as published by

    the Free Software Foundation; either version 2 of the License, or

    (at your option) any later version.

    This program is distributed in the hope that it will be useful,

    but WITHOUT ANY WARRANTY; without even the implied warranty of

    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License

    along with this program; if not, write to the Free Software

    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.

Also add information on how to contact you by electronic and paper mail.

If the program is interactive, make it output a short notice like this

when it starts in an interactive mode:

    Gnomovision version 69, Copyright (C) 19yy name of author

    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.

    This is free software, and you are welcome to redistribute it

    under certain conditions; type `show c' for details.

The hypothetical commands `show w' and `show c' should show the appropriate

parts of the General Public License.  Of course, the commands you use may

be called something other than `show w' and `show c'; they could even be

mouse-clicks or menu items--whatever suits your program.

You should also get your employer (if you work as a programmer) or your

school, if any, to sign a "copyright disclaimer" for the program, if

necessary.  Here is a sample; alter the names:

  Yoyodyne, Inc., hereby disclaims all copyright interest in the program

  `Gnomovision' (which makes passes at compilers) written by James Hacker.

  <signature of Ty Coon>, 1 April 1989

  Ty Coon, President of Vice

This General Public License does not permit incorporating your program into

proprietary programs.  If your program is a subroutine library, you may

consider it more useful to permit linking proprietary applications with the

library.  If this is what you want to do, use the GNU Library General

Public License instead of this License.

parent:

	@$(MAKE) --no-print-directory -C ..

/* FFdecsa -- fast decsa algorithm

 *

 * Copyright (C) 2003-2004  fatih89r

 *

 * This program is free software; you can redistribute it and/or modify

 * it under the terms of the GNU General Public License as published by

 * the Free Software Foundation; either version 2 of the License, or

 * (at your option) any later version.

 *

 * This program is distributed in the hope that it will be useful,

 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

 * GNU General Public License for more details.

 *

 * You should have received a copy of the GNU General Public License

 * along with this program; if not, write to the Free Software

 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.

 */

#include <sys/types.h>

#include <string.h>

#include <stdio.h>

#include <stdlib.h>

#include "ffdecsa.h"

#ifndef NULL

#define NULL 0

#endif

//#define DEBUG

#ifdef DEBUG

#define DBG(a) a

#else

#define DBG(a)

#endif

//// parallelization stuff, large speed differences are possible

// possible choices

#define PARALLEL_32_4CHAR     320

#define PARALLEL_32_4CHARA    321

#define PARALLEL_32_INT       322

#define PARALLEL_64_8CHAR     640

#define PARALLEL_64_8CHARA    641

#define PARALLEL_64_2INT      642

#define PARALLEL_64_LONG      643

#define PARALLEL_64_MMX       644

#define PARALLEL_128_16CHAR  1280

#define PARALLEL_128_16CHARA 1281

#define PARALLEL_128_4INT    1282

#define PARALLEL_128_2LONG   1283

#define PARALLEL_128_2MMX    1284

#define PARALLEL_128_SSE     1285

#define PARALLEL_128_SSE2    1286

//////// our choice //////////////// our choice //////////////// our choice //////////////// our choice ////////

#ifndef PARALLEL_MODE

#if defined(__x86_64__) || defined(_M_X64)

#define PARALLEL_MODE PARALLEL_128_SSE2

#elif defined(__mips__) || defined(__mips) || defined(__MIPS__)

#define PARALLEL_MODE PARALLEL_64_LONG

#elif defined(__sh__) || defined(__SH4__)

#define PARALLEL_MODE PARALLEL_32_INT

#define COPY_UNALIGNED_PKT

#define MEMALIGN_VAL 4

#else

#define PARALLEL_MODE PARALLEL_32_INT

#endif

#endif

//////// our choice //////////////// our choice //////////////// our choice //////////////// our choice ////////

#include "parallel_generic.h"

//// conditionals

#if PARALLEL_MODE==PARALLEL_32_4CHAR

#include "parallel_032_4char.h"

#elif PARALLEL_MODE==PARALLEL_32_4CHARA

#include "parallel_032_4charA.h"

#elif PARALLEL_MODE==PARALLEL_32_INT

#include "parallel_032_int.h"

#elif PARALLEL_MODE==PARALLEL_64_8CHAR

#include "parallel_064_8char.h"

#elif PARALLEL_MODE==PARALLEL_64_8CHARA

#include "parallel_064_8charA.h"

#elif PARALLEL_MODE==PARALLEL_64_2INT

#include "parallel_064_2int.h"

#elif PARALLEL_MODE==PARALLEL_64_LONG

#include "parallel_064_long.h"

#elif PARALLEL_MODE==PARALLEL_64_MMX

#include "parallel_064_mmx.h"

#elif PARALLEL_MODE==PARALLEL_128_16CHAR

#include "parallel_128_16char.h"

#elif PARALLEL_MODE==PARALLEL_128_16CHARA

#include "parallel_128_16charA.h"

#elif PARALLEL_MODE==PARALLEL_128_4INT

#include "parallel_128_4int.h"

#elif PARALLEL_MODE==PARALLEL_128_2LONG

#include "parallel_128_2long.h"

#elif PARALLEL_MODE==PARALLEL_128_2MMX

#include "parallel_128_2mmx.h"

#elif PARALLEL_MODE==PARALLEL_128_SSE

#include "parallel_128_sse.h"

#elif PARALLEL_MODE==PARALLEL_128_SSE2

#include "parallel_128_sse2.h"

#else

#error "unknown/undefined parallel mode"

#endif

// stuff depending on conditionals

#define BYTES_PER_GROUP (GROUP_PARALLELISM/8)

#define BYPG BYTES_PER_GROUP

#define BITS_PER_GROUP GROUP_PARALLELISM

#define BIPG BITS_PER_GROUP

// platform specific

#ifdef __arm__

#if !defined(MEMALIGN_VAL) || MEMALIGN_VAL<4

#undef MEMALIGN_VAL

#define MEMALIGN_VAL 4

#endif

#define COPY_UNALIGNED_PKT

#endif

//

#ifndef MALLOC

#define MALLOC(X) malloc(X)

#endif

#ifndef FREE

#define FREE(X) free(X)

#endif

#ifdef MEMALIGN_VAL

#define MEMALIGN __attribute__((aligned(MEMALIGN_VAL)))

#else

#define MEMALIGN

#endif

//// debug tool

#ifdef DEBUG

static void dump_mem(const char *string, const unsigned char *p, int len, int linelen){

  int i;

  for(i=0;i<len;i++){

    if(i%linelen==0&&i) fprintf(stderr,"\n");

    if(i%linelen==0) fprintf(stderr,"%s %08x:",string,i);

    else{

      if(i%8==0) fprintf(stderr," ");

      if(i%4==0) fprintf(stderr," ");

    }

    fprintf(stderr," %02x",p[i]);

  }

  if(i%linelen==0) fprintf(stderr,"\n");

}

#endif

//////////////////////////////////////////////////////////////////////////////////

struct csa_key_t{

	unsigned char ck[8];

// used by stream

        int iA[8];  // iA[0] is for A1, iA[7] is for A8

        int iB[8];  // iB[0] is for B1, iB[7] is for B8

// used by stream (group)

        MEMALIGN group ck_g[8][8]; // [byte][bit:0=LSB,7=MSB]

        MEMALIGN group iA_g[8][4]; // [0 for A1][0 for LSB]

        MEMALIGN group iB_g[8][4]; // [0 for B1][0 for LSB]

// used by block

	unsigned char kk[56];

// used by block (group)

	MEMALIGN batch kkmulti[56]; // many times the same byte in every batch

};

struct csa_keys_t{

  struct csa_key_t even;

  struct csa_key_t odd;

};

//-----stream cypher

//-----key schedule for stream decypher

static void key_schedule_stream(

  unsigned char *ck,    // [In]  ck[0]-ck[7]   8 bytes   | Key.

  int *iA,              // [Out] iA[0]-iA[7]   8 nibbles | Key schedule.

  int *iB)              // [Out] iB[0]-iB[7]   8 nibbles | Key schedule.

{

    iA[0]=(ck[0]>>4)&0xf;

    iA[1]=(ck[0]   )&0xf;

    iA[2]=(ck[1]>>4)&0xf;

    iA[3]=(ck[1]   )&0xf;

    iA[4]=(ck[2]>>4)&0xf;

    iA[5]=(ck[2]   )&0xf;

    iA[6]=(ck[3]>>4)&0xf;

    iA[7]=(ck[3]   )&0xf;

    iB[0]=(ck[4]>>4)&0xf;

    iB[1]=(ck[4]   )&0xf;

    iB[2]=(ck[5]>>4)&0xf;

    iB[3]=(ck[5]   )&0xf;

    iB[4]=(ck[6]>>4)&0xf;

    iB[5]=(ck[6]   )&0xf;

    iB[6]=(ck[7]>>4)&0xf;

    iB[7]=(ck[7]   )&0xf;

}

//----- stream main function

#define STREAM_INIT

#include "stream.c"

#undef STREAM_INIT

#define STREAM_NORMAL

#include "stream.c"

#undef STREAM_NORMAL

//-----block decypher

//-----key schedule for block decypher

static void key_schedule_block(

  unsigned char *ck,    // [In]  ck[0]-ck[7]   8 bytes | Key.

  unsigned char *kk)    // [Out] kk[0]-kk[55] 56 bytes | Key schedule.

{

  static const unsigned char key_perm[0x40] = {

    0x12,0x24,0x09,0x07,0x2A,0x31,0x1D,0x15, 0x1C,0x36,0x3E,0x32,0x13,0x21,0x3B,0x40,

    0x18,0x14,0x25,0x27,0x02,0x35,0x1B,0x01, 0x22,0x04,0x0D,0x0E,0x39,0x28,0x1A,0x29,

    0x33,0x23,0x34,0x0C,0x16,0x30,0x1E,0x3A, 0x2D,0x1F,0x08,0x19,0x17,0x2F,0x3D,0x11,

    0x3C,0x05,0x38,0x2B,0x0B,0x06,0x0A,0x2C, 0x20,0x3F,0x2E,0x0F,0x03,0x26,0x10,0x37,

  };

  int i,j,k;

  int bit[64];

  int newbit[64];

  int kb[7][8];

  // 56 steps

  // 56 key bytes kk(55)..kk(0) by key schedule from ck

  // kb(6,0) .. kb(6,7) = ck(0) .. ck(7)

  kb[6][0] = ck[0];

  kb[6][1] = ck[1];

  kb[6][2] = ck[2];

  kb[6][3] = ck[3];

  kb[6][4] = ck[4];

  kb[6][5] = ck[5];

  kb[6][6] = ck[6];

  kb[6][7] = ck[7];

  // calculate kb[5] .. kb[0]

  for(i=5; i>=0; i--){

    // 64 bit perm on kb

    for(j=0; j<8; j++){

      for(k=0; k<8; k++){

        bit[j*8+k] = (kb[i+1][j] >> (7-k)) & 1;

        newbit[key_perm[j*8+k]-1] = bit[j*8+k];

      }

    }

    for(j=0; j<8; j++){

      kb[i][j] = 0;

      for(k=0; k<8; k++){

        kb[i][j] |= newbit[j*8+k] << (7-k);

      }

    }

  }

  // xor to give kk

  for(i=0; i<7; i++){

    for(j=0; j<8; j++){

      kk[i*8+j] = kb[i][j] ^ i;

    }

  }

}

//-----block utils

static inline __attribute__((always_inline)) void trasp_N_8 (unsigned char *in,unsigned char* out,int count){

  int *ri=(int *)in;

  int *ibi=(int *)out;

  int j,i,k,g;

  // copy and first step

  for(g=0;g<count;g++){

    ri[g]=ibi[2*g];

    ri[GROUP_PARALLELISM+g]=ibi[2*g+1];

  }

//dump_mem("NE1 r[roff]",&r[roff],GROUP_PARALLELISM*8,GROUP_PARALLELISM);

// now 01230123

#define INTS_PER_ROW (GROUP_PARALLELISM/8*2)

  for(j=0;j<8;j+=4){

    for(i=0;i<2;i++){

      for(k=0;k<INTS_PER_ROW;k++){

        unsigned int t,b;

        t=ri[INTS_PER_ROW*(j+i)+k];

        b=ri[INTS_PER_ROW*(j+i+2)+k];

        ri[INTS_PER_ROW*(j+i)+k]=     (t&0x0000ffff)      | ((b           )<<16);

        ri[INTS_PER_ROW*(j+i+2)+k]=  ((t           )>>16) |  (b&0xffff0000) ;

      }

    }

  }

//dump_mem("NE2 r[roff]",&r[roff],GROUP_PARALLELISM*8,GROUP_PARALLELISM);

// now 01010101

  for(j=0;j<8;j+=2){

    for(i=0;i<1;i++){

      for(k=0;k<INTS_PER_ROW;k++){

        unsigned int t,b;

        t=ri[INTS_PER_ROW*(j+i)+k];

        b=ri[INTS_PER_ROW*(j+i+1)+k];

        ri[INTS_PER_ROW*(j+i)+k]=     (t&0x00ff00ff)     | ((b&0x00ff00ff)<<8);

        ri[INTS_PER_ROW*(j+i+1)+k]=  ((t&0xff00ff00)>>8) |  (b&0xff00ff00);

      }

    }

  }

//dump_mem("NE3 r[roff]",&r[roff],GROUP_PARALLELISM*8,GROUP_PARALLELISM);

// now 00000000

}

static inline __attribute__((always_inline)) void trasp_8_N (unsigned char *in,unsigned char* out,int count){

  int *ri=(int *)in;

  int *bdi=(int *)out;

  int j,i,k,g;

#define INTS_PER_ROW (GROUP_PARALLELISM/8*2)

//dump_mem("NE1 r[roff]",&r[roff],GROUP_PARALLELISM*8,GROUP_PARALLELISM);

// now 00000000

  for(j=0;j<8;j+=2){

    for(i=0;i<1;i++){

      for(k=0;k<INTS_PER_ROW;k++){

        unsigned int t,b;

        t=ri[INTS_PER_ROW*(j+i)+k];

        b=ri[INTS_PER_ROW*(j+i+1)+k];

        ri[INTS_PER_ROW*(j+i)+k]=     (t&0x00ff00ff)     | ((b&0x00ff00ff)<<8);

        ri[INTS_PER_ROW*(j+i+1)+k]=  ((t&0xff00ff00)>>8) |  (b&0xff00ff00);

      }

    }

  }

//dump_mem("NE2 r[roff]",&r[roff],GROUP_PARALLELISM*8,GROUP_PARALLELISM);

// now 01010101

  for(j=0;j<8;j+=4){

    for(i=0;i<2;i++){

      for(k=0;k<INTS_PER_ROW;k++){

        unsigned int t,b;

        t=ri[INTS_PER_ROW*(j+i)+k];

        b=ri[INTS_PER_ROW*(j+i+2)+k];

        ri[INTS_PER_ROW*(j+i)+k]=     (t&0x0000ffff)      | ((b           )<<16);

        ri[INTS_PER_ROW*(j+i+2)+k]=  ((t           )>>16) |  (b&0xffff0000) ;

      }

    }

  }

//dump_mem("NE3 r[roff]",&r[roff],GROUP_PARALLELISM*8,GROUP_PARALLELISM);

// now 01230123

  for(g=0;g<count;g++){

    bdi[2*g]=ri[g];

    bdi[2*g+1]=ri[GROUP_PARALLELISM+g];

  }

}

//-----block main function

// block group

static void block_decypher_group(

  batch *kkmulti,       // [In]  kkmulti[0]-kkmulti[55] 56 batches | Key schedule (each batch has repeated equal bytes).

  unsigned char *ib,    // [In]  (ib0,ib1,...ib7)...x32 32*8 bytes | Initialization vector.

  unsigned char *bd,    // [Out] (bd0,bd1,...bd7)...x32 32*8 bytes | Block decipher.

  int count)

{

  // int is faster than unsigned char. apparently not

  static const unsigned char block_sbox[0x100] = {

    0x3A,0xEA,0x68,0xFE,0x33,0xE9,0x88,0x1A, 0x83,0xCF,0xE1,0x7F,0xBA,0xE2,0x38,0x12,

    0xE8,0x27,0x61,0x95,0x0C,0x36,0xE5,0x70, 0xA2,0x06,0x82,0x7C,0x17,0xA3,0x26,0x49,

    0xBE,0x7A,0x6D,0x47,0xC1,0x51,0x8F,0xF3, 0xCC,0x5B,0x67,0xBD,0xCD,0x18,0x08,0xC9,

    0xFF,0x69,0xEF,0x03,0x4E,0x48,0x4A,0x84, 0x3F,0xB4,0x10,0x04,0xDC,0xF5,0x5C,0xC6,

    0x16,0xAB,0xAC,0x4C,0xF1,0x6A,0x2F,0x3C, 0x3B,0xD4,0xD5,0x94,0xD0,0xC4,0x63,0x62,

    0x71,0xA1,0xF9,0x4F,0x2E,0xAA,0xC5,0x56, 0xE3,0x39,0x93,0xCE,0x65,0x64,0xE4,0x58,

    0x6C,0x19,0x42,0x79,0xDD,0xEE,0x96,0xF6, 0x8A,0xEC,0x1E,0x85,0x53,0x45,0xDE,0xBB,

    0x7E,0x0A,0x9A,0x13,0x2A,0x9D,0xC2,0x5E, 0x5A,0x1F,0x32,0x35,0x9C,0xA8,0x73,0x30,

    0x29,0x3D,0xE7,0x92,0x87,0x1B,0x2B,0x4B, 0xA5,0x57,0x97,0x40,0x15,0xE6,0xBC,0x0E,

    0xEB,0xC3,0x34,0x2D,0xB8,0x44,0x25,0xA4, 0x1C,0xC7,0x23,0xED,0x90,0x6E,0x50,0x00,

    0x99,0x9E,0x4D,0xD9,0xDA,0x8D,0x6F,0x5F, 0x3E,0xD7,0x21,0x74,0x86,0xDF,0x6B,0x05,

    0x8E,0x5D,0x37,0x11,0xD2,0x28,0x75,0xD6, 0xA7,0x77,0x24,0xBF,0xF0,0xB0,0x02,0xB7,

    0xF8,0xFC,0x81,0x09,0xB1,0x01,0x76,0x91, 0x7D,0x0F,0xC8,0xA0,0xF2,0xCB,0x78,0x60,

    0xD1,0xF7,0xE0,0xB5,0x98,0x22,0xB3,0x20, 0x1D,0xA6,0xDB,0x7B,0x59,0x9F,0xAE,0x31,

    0xFB,0xD3,0xB6,0xCA,0x43,0x72,0x07,0xF4, 0xD8,0x41,0x14,0x55,0x0D,0x54,0x8B,0xB9,

    0xAD,0x46,0x0B,0xAF,0x80,0x52,0x2C,0xFA, 0x8C,0x89,0x66,0xFD,0xB2,0xA9,0x9B,0xC0,

  };

  MEMALIGN unsigned char r[GROUP_PARALLELISM*(8+56)];  /* 56 because we will move back in memory while looping */

  MEMALIGN unsigned char sbox_in[GROUP_PARALLELISM],sbox_out[GROUP_PARALLELISM],perm_out[GROUP_PARALLELISM];

  int roff;

  int i,g,count_all=GROUP_PARALLELISM;

  roff=GROUP_PARALLELISM*56;

#define FASTTRASP1

#ifndef FASTTRASP1

  for(g=0;g<count;g++){

    // Init registers 

    int j;

    for(j=0;j<8;j++){

      r[roff+GROUP_PARALLELISM*j+g]=ib[8*g+j];

    }

  }

#else

  trasp_N_8((unsigned char *)&r[roff],(unsigned char *)ib,count);

#endif

//dump_mem("OLD r[roff]",&r[roff],GROUP_PARALLELISM*8,GROUP_PARALLELISM);

  // loop over kk[55]..kk[0]

  for(i=55;i>=0;i--){

    {

      MEMALIGN batch tkkmulti=kkmulti[i];

      batch *si=(batch *)sbox_in;

      batch *r6_N=(batch *)(r+roff+GROUP_PARALLELISM*6);

      for(g=0;g<count_all/BYTES_PER_BATCH;g++){

        si[g]=B_FFXOR(tkkmulti,r6_N[g]);              //FIXME: introduce FASTBATCH?

      }

    }

    // table lookup, this works on only one byte at a time

    // most difficult part of all

    // - can't be parallelized

    // - can't be synthetized through boolean terms (8 input bits are too many)

    for(g=0;g<count_all;g++){

      sbox_out[g]=block_sbox[sbox_in[g]];

    }

    // bit permutation

    {

      unsigned char *po=(unsigned char *)perm_out;

      unsigned char *so=(unsigned char *)sbox_out;

//dump_mem("pre perm ",(unsigned char *)so,GROUP_PARALLELISM,GROUP_PARALLELISM);

      for(g=0;g<count_all;g+=BYTES_PER_BATCH){

        MEMALIGN batch in,out;

        in=*(batch *)&so[g];

        out=B_FFOR(

	    B_FFOR(

	    B_FFOR(

	    B_FFOR(

	    B_FFOR(

	           B_FFSH8L(B_FFAND(in,B_FFN_ALL_29()),1),

	           B_FFSH8L(B_FFAND(in,B_FFN_ALL_02()),6)),

	           B_FFSH8L(B_FFAND(in,B_FFN_ALL_04()),3)),

	           B_FFSH8R(B_FFAND(in,B_FFN_ALL_10()),2)),

	           B_FFSH8R(B_FFAND(in,B_FFN_ALL_40()),6)),

	           B_FFSH8R(B_FFAND(in,B_FFN_ALL_80()),4));

        *(batch *)&po[g]=out;

      }

//dump_mem("post perm",(unsigned char *)po,GROUP_PARALLELISM,GROUP_PARALLELISM);

    }

    roff-=GROUP_PARALLELISM; /* virtual shift of registers */

#if 0

/* one by one */

    for(g=0;g<count_all;g++){

      r[roff+GROUP_PARALLELISM*0+g]=r[roff+GROUP_PARALLELISM*8+g]^sbox_out[g];

      r[roff+GROUP_PARALLELISM*6+g]^=perm_out[g];

      r[roff+GROUP_PARALLELISM*4+g]^=r[roff+GROUP_PARALLELISM*0+g];

      r[roff+GROUP_PARALLELISM*3+g]^=r[roff+GROUP_PARALLELISM*0+g];

      r[roff+GROUP_PARALLELISM*2+g]^=r[roff+GROUP_PARALLELISM*0+g];

    }

#else

    for(g=0;g<count_all;g+=BEST_SPAN){

      XOR_BEST_BY(&r[roff+GROUP_PARALLELISM*0+g],&r[roff+GROUP_PARALLELISM*8+g],&sbox_out[g]);

      XOREQ_BEST_BY(&r[roff+GROUP_PARALLELISM*6+g],&perm_out[g]);

      XOREQ_BEST_BY(&r[roff+GROUP_PARALLELISM*4+g],&r[roff+GROUP_PARALLELISM*0+g]);

      XOREQ_BEST_BY(&r[roff+GROUP_PARALLELISM*3+g],&r[roff+GROUP_PARALLELISM*0+g]);

      XOREQ_BEST_BY(&r[roff+GROUP_PARALLELISM*2+g],&r[roff+GROUP_PARALLELISM*0+g]);

    }

#endif

  }

#define FASTTRASP2

#ifndef FASTTRASP2

  for(g=0;g<count;g++){

    // Copy results

    int j;

    for(j=0;j<8;j++){

      bd[8*g+j]=r[roff+GROUP_PARALLELISM*j+g];

    }

  }

#else

  trasp_8_N((unsigned char *)&r[roff],(unsigned char *)bd,count);

#endif

}

//-----------------------------------EXTERNAL INTERFACE

//-----get internal parallelism

int get_internal_parallelism(void){

  return GROUP_PARALLELISM;

}

//-----get suggested cluster size

int get_suggested_cluster_size(void){

  int r;

  r=GROUP_PARALLELISM+GROUP_PARALLELISM/10;

  if(r<GROUP_PARALLELISM+5) r=GROUP_PARALLELISM+5;

  return r;

}

//-----key structure

void *get_key_struct(void){

  struct csa_keys_t *keys=(struct csa_keys_t *)MALLOC(sizeof(struct csa_keys_t));

  if(keys) {

    static const unsigned char pk[8] = { 0,0,0,0,0,0,0,0 };

    set_control_words(keys,pk,pk);

    }

  return keys;

}

void free_key_struct(void *keys){

  return FREE(keys);

}

//-----set control words

static void schedule_key(struct csa_key_t *key, const unsigned char *pk){

  // could be made faster, but is not run often

  int bi,by;

  int i,j;

// key

  memcpy(key->ck,pk,8);

// precalculations for stream

  key_schedule_stream(key->ck,key->iA,key->iB);

  for(by=0;by<8;by++){

    for(bi=0;bi<8;bi++){

      key->ck_g[by][bi]=(key->ck[by]&(1<<bi))?FF1():FF0();

    }

  }

  for(by=0;by<8;by++){

    for(bi=0;bi<4;bi++){

      key->iA_g[by][bi]=(key->iA[by]&(1<<bi))?FF1():FF0();

      key->iB_g[by][bi]=(key->iB[by]&(1<<bi))?FF1():FF0();

    }

  }

// precalculations for block

  key_schedule_block(key->ck,key->kk);

  for(i=0;i<56;i++){

    for(j=0;j<BYTES_PER_BATCH;j++){

      *(((unsigned char *)&key->kkmulti[i])+j)=key->kk[i];

    }

  }

}

void set_control_words(void *keys, const unsigned char *ev, const unsigned char *od){

  schedule_key(&((struct csa_keys_t *)keys)->even,ev);

  schedule_key(&((struct csa_keys_t *)keys)->odd,od);

}

void set_even_control_word(void *keys, const unsigned char *pk){

  schedule_key(&((struct csa_keys_t *)keys)->even,pk);

}

void set_odd_control_word(void *keys, const unsigned char *pk){

  schedule_key(&((struct csa_keys_t *)keys)->odd,pk);

}

//-----get control words

void get_control_words(void *keys, unsigned char *even, unsigned char *odd){

  memcpy(even,&((struct csa_keys_t *)keys)->even.ck,8);

  memcpy(odd,&((struct csa_keys_t *)keys)->odd.ck,8);

}

//----- decrypt

int decrypt_packets(void *keys, unsigned char **cluster){

  // statistics, currently unused

  int stat_no_scramble=0;

  int stat_reserved=0;

  int stat_decrypted[2]={0,0};

  int stat_decrypted_mini=0;

  unsigned char **clst;

  unsigned char **clst2;

  int grouped;

  int group_ev_od;

  int advanced;

  int can_advance;

  unsigned char *g_pkt[GROUP_PARALLELISM];

  int g_len[GROUP_PARALLELISM];

  int g_offset[GROUP_PARALLELISM];

  int g_n[GROUP_PARALLELISM];

  int g_residue[GROUP_PARALLELISM];

  unsigned char *pkt;

  int xc0,ev_od,len,offset,n,residue;

  struct csa_key_t* k;

  int i,j,iter,g;

  int t23,tsmall;

  int alive[24];

//icc craziness  int pad1=0; //////////align! FIXME

  unsigned char *encp[GROUP_PARALLELISM];

  MEMALIGN unsigned char stream_in[GROUP_PARALLELISM*8];

  MEMALIGN unsigned char stream_out[GROUP_PARALLELISM*8];

  MEMALIGN unsigned char ib[GROUP_PARALLELISM*8];

  MEMALIGN unsigned char block_out[GROUP_PARALLELISM*8];

#ifdef COPY_UNALIGNED_PKT

  unsigned char *unaligned[GROUP_PARALLELISM];

  MEMALIGN unsigned char alignedBuff[GROUP_PARALLELISM][188];

#endif

  struct stream_regs regs;

//icc craziness  i=(int)&pad1;//////////align!!! FIXME

  // build a list of packets to be processed

  clst=cluster;

  grouped=0;

  advanced=0;

  can_advance=1;

  group_ev_od=-1; // silence incorrect compiler warning

  pkt=*clst;

  do{ // find a new packet

    if(grouped==GROUP_PARALLELISM){

      // full

      break;

    }

    if(pkt==NULL){

      // no more ranges

      break;

    }

    if(pkt>=*(clst+1)){

      // out of this range, try next

      clst++;clst++;

      pkt=*clst;

      continue;

    }

    do{ // handle this packet

      xc0=pkt[3]&0xc0;

      DBG(fprintf(stderr,"   exam pkt=%p, xc0=%02x, can_adv=%i\n",pkt,xc0,can_advance));

      if(xc0==0x00){

        DBG(fprintf(stderr,"skip clear pkt %p (can_advance is %i)\n",pkt,can_advance));

        advanced+=can_advance;

        stat_no_scramble++;

        break;

      }

      if(xc0==0x40){

        DBG(fprintf(stderr,"skip reserved pkt %p (can_advance is %i)\n",pkt,can_advance));

        advanced+=can_advance;

        stat_reserved++;

        break;

      }

      if(xc0==0x80||xc0==0xc0){ // encrypted

        ev_od=(xc0&0x40)>>6; // 0 even, 1 odd

        if(grouped==0) group_ev_od=ev_od; // this group will be all even (or odd)

        if(group_ev_od==ev_od){ // could be added to group

          pkt[3]&=0x3f;  // consider it decrypted now

          if(pkt[3]&0x20){ // incomplete packet

            offset=4+pkt[4]+1;

            len=188-offset;

            n=len>>3;

            residue=len-(n<<3);

            if(n==0){ // decrypted==encrypted!

              DBG(fprintf(stderr,"DECRYPTED MINI! (can_advance is %i)\n",can_advance));

              advanced+=can_advance;

              stat_decrypted_mini++;

              break; // this doesn't need more processing

            }

          }else{

            len=184;

            offset=4;

            n=23;

            residue=0;

          }

          g_pkt[grouped]=pkt;

          g_len[grouped]=len;

          g_offset[grouped]=offset;

          g_n[grouped]=n;

          g_residue[grouped]=residue;

          DBG(fprintf(stderr,"%2i: eo=%i pkt=%p len=%03i n=%2i residue=%i\n",grouped,ev_od,pkt,len,n,residue));

          grouped++;

          advanced+=can_advance;

          stat_decrypted[ev_od]++;

        }

        else{

          can_advance=0;

          DBG(fprintf(stderr,"skip pkt %p and can_advance set to 0\n",pkt));

          break; // skip and go on

        }

      }

    } while(0);

    if(can_advance){

      // move range start forward

      *clst+=188;

    }

    // next packet, if there is one

    pkt+=188;

  } while(1);

  DBG(fprintf(stderr,"-- result: grouped %i pkts, advanced %i pkts\n",grouped,advanced));

  // delete empty ranges and compact list

  clst2=cluster;

  for(clst=cluster;*clst!=NULL;clst+=2){

    // if not empty

    if(*clst<*(clst+1)){

      // it will remain 

      *clst2=*clst;

      *(clst2+1)=*(clst+1);

      clst2+=2;

    }

  }

  *clst2=NULL;

  if(grouped==0){

    // no processing needed

    return advanced;

  }

  //  sort them, longest payload first

  //  we expect many n=23 packets and a few n<23

  DBG(fprintf(stderr,"PRESORTING\n"));

  for(i=0;i<grouped;i++){

    DBG(fprintf(stderr,"%2i of %2i: pkt=%p len=%03i n=%2i residue=%i\n",i,grouped,g_pkt[i],g_len[i],g_n[i],g_residue[i]));

    }

  // grouped is always <= GROUP_PARALLELISM

#define g_swap(a,b) \

    pkt=g_pkt[a]; \

    g_pkt[a]=g_pkt[b]; \

    g_pkt[b]=pkt; \

\

    len=g_len[a]; \

    g_len[a]=g_len[b]; \

    g_len[b]=len; \

\

    offset=g_offset[a]; \

    g_offset[a]=g_offset[b]; \

    g_offset[b]=offset; \

\

    n=g_n[a]; \

    g_n[a]=g_n[b]; \

    g_n[b]=n; \

\

    residue=g_residue[a]; \

    g_residue[a]=g_residue[b]; \

    g_residue[b]=residue;

  // step 1: move n=23 packets before small packets

  t23=0;

  tsmall=grouped-1;

  for(;;){

    for(;t23<grouped;t23++){

      if(g_n[t23]!=23) break;

    }

DBG(fprintf(stderr,"t23 after for =%i\n",t23));

    for(;tsmall>=0;tsmall--){

      if(g_n[tsmall]==23) break;

    }

DBG(fprintf(stderr,"tsmall after for =%i\n",tsmall));

    if(tsmall-t23<1) break;

DBG(fprintf(stderr,"swap t23=%i,tsmall=%i\n",t23,tsmall));

    g_swap(t23,tsmall);

    t23++;

    tsmall--;

DBG(fprintf(stderr,"new t23=%i,tsmall=%i\n\n",t23,tsmall));

  }

  DBG(fprintf(stderr,"packets with n=23, t23=%i   grouped=%i\n",t23,grouped));

  DBG(fprintf(stderr,"MIDSORTING\n"));

  for(i=0;i<grouped;i++){

    DBG(fprintf(stderr,"%2i of %2i: pkt=%p len=%03i n=%2i residue=%i\n",i,grouped,g_pkt[i],g_len[i],g_n[i],g_residue[i]));

    }

  // step 2: sort small packets in decreasing order of n (bubble sort is enough)

  for(i=t23;i<grouped;i++){

    for(j=i+1;j<grouped;j++){

      if(g_n[j]>g_n[i]){

        g_swap(i,j);

      }

    }

  }

  DBG(fprintf(stderr,"POSTSORTING\n"));

  for(i=0;i<grouped;i++){

    DBG(fprintf(stderr,"%2i of %2i: pkt=%p len=%03i n=%2i residue=%i\n",i,grouped,g_pkt[i],g_len[i],g_n[i],g_residue[i]));

    }

  // we need to know how many packets need 23 iterations, how many 22...

  for(i=0;i<=23;i++){

    alive[i]=0;

  }

  // count

  alive[23-1]=t23;

  for(i=t23;i<grouped;i++){

    alive[g_n[i]-1]++;

  }

  // integrate

  for(i=22;i>=0;i--){

    alive[i]+=alive[i+1];

  }

  DBG(fprintf(stderr,"ALIVE\n"));

  for(i=0;i<=23;i++){

    DBG(fprintf(stderr,"alive%2i=%i\n",i,alive[i]));

    }

  // choose key

  if(group_ev_od==0){

    k=&((struct csa_keys_t *)keys)->even;

  }

  else{

    k=&((struct csa_keys_t *)keys)->odd;

  }

  //INIT

//#define INITIALIZE_UNUSED_INPUT

#ifdef INITIALIZE_UNUSED_INPUT

// unnecessary zeroing.

// without this, we operate on uninitialized memory

// when grouped<GROUP_PARALLELISM, but it's not a problem,

// as final results will be discarded.

// random data makes debugging sessions difficult.

  for(j=0;j<GROUP_PARALLELISM*8;j++) stream_in[j]=0;

DBG(fprintf(stderr,"--- WARNING: you could gain speed by not initializing unused memory ---\n"));

#else

DBG(fprintf(stderr,"--- WARNING: DEBUGGING IS MORE DIFFICULT WHEN PROCESSING RANDOM DATA CHANGING AT EVERY RUN! ---\n"));

#endif

  for(g=0;g<grouped;g++){

    encp[g]=g_pkt[g];

    DBG(fprintf(stderr,"header[%i]=%p (%02x)\n",g,encp[g],*(encp[g])));

    encp[g]+=g_offset[g]; // skip header

#ifdef COPY_UNALIGNED_PKT

    if(((int)encp[g])&0x03) {

      memcpy(alignedBuff[g],encp[g],g_len[g]);

      unaligned[g]=encp[g];

      encp[g]=alignedBuff[g];

      }

    else unaligned[g]=0;

#endif

    FFTABLEIN(stream_in,g,encp[g]);

  }

//dump_mem("stream_in",stream_in,GROUP_PARALLELISM*8,BYPG);

  // ITER 0

DBG(fprintf(stderr,">>>>>ITER 0\n"));

  iter=0;

  stream_cypher_group_init(&regs,k->iA_g,k->iB_g,stream_in);

  // fill first ib

  for(g=0;g<alive[iter];g++){

    COPY_8_BY(ib+8*g,encp[g]);

  }

DBG(dump_mem("IB ",ib,8*alive[iter],8));

  // ITER 1..N-1

  for (iter=1;iter<23&&alive[iter-1]>0;iter++){

DBG(fprintf(stderr,">>>>>ITER %i\n",iter));

    // alive and just dead packets: calc block

    block_decypher_group(k->kkmulti,ib,block_out,alive[iter-1]);

DBG(dump_mem("BLO_ib ",block_out,8*alive[iter-1],8));

    // all packets (dead too): calc stream

    stream_cypher_group_normal(&regs,stream_out);

//dump_mem("stream_out",stream_out,GROUP_PARALLELISM*8,BYPG);

    // alive packets: calc ib

    for(g=0;g<alive[iter];g++){

      FFTABLEOUT(ib+8*g,stream_out,g);

DBG(dump_mem("stream_out_ib ",ib+8*g,8,8));

// XOREQ8BY gcc bug? 2x4 ok, 8 ko    UPDATE: result ok but speed 1-2% slower (!!!???)

#if 1

      XOREQ_4_BY(ib+8*g,encp[g]+8);

      XOREQ_4_BY(ib+8*g+4,encp[g]+8+4);

#else

      XOREQ_8_BY(ib+8*g,encp[g]+8);

#endif

DBG(dump_mem("after_stream_xor_ib ",ib+8*g,8,8));

    }

    // alive packets: decrypt data

    for(g=0;g<alive[iter];g++){

DBG(dump_mem("before_ib_decrypt_data ",encp[g],8,8));

      XOR_8_BY(encp[g],ib+8*g,block_out+8*g);

DBG(dump_mem("after_ib_decrypt_data ",encp[g],8,8));

    }

    // just dead packets: write decrypted data

    for(g=alive[iter];g<alive[iter-1];g++){

DBG(dump_mem("jd_before_ib_decrypt_data ",encp[g],8,8));

      COPY_8_BY(encp[g],block_out+8*g);

DBG(dump_mem("jd_after_ib_decrypt_data ",encp[g],8,8));

    }

    // just dead packets: decrypt residue

    for(g=alive[iter];g<alive[iter-1];g++){

DBG(dump_mem("jd_before_decrypt_residue ",encp[g]+8,g_residue[g],g_residue[g]));

      FFTABLEOUTXORNBY(g_residue[g],encp[g]+8,stream_out,g);

DBG(dump_mem("jd_after_decrypt_residue ",encp[g]+8,g_residue[g],g_residue[g]));

    }

    // alive packets: pointers++

    for(g=0;g<alive[iter];g++) encp[g]+=8;

  };

  // ITER N

DBG(fprintf(stderr,">>>>>ITER 23\n"));

  iter=23;

  // calc block

  block_decypher_group(k->kkmulti,ib,block_out,alive[iter-1]);

DBG(dump_mem("23BLO_ib ",block_out,8*alive[iter-1],8));

  // just dead packets: write decrypted data

  for(g=alive[iter];g<alive[iter-1];g++){

DBG(dump_mem("23jd_before_ib_decrypt_data ",encp[g],8,8));

    COPY_8_BY(encp[g],block_out+8*g);

DBG(dump_mem("23jd_after_ib_decrypt_data ",encp[g],8,8));

  }

  // no residue possible

  // so do nothing

  DBG(fprintf(stderr,"returning advanced=%i\n",advanced));

#ifdef COPY_UNALIGNED_PKT

  for(g=0;g<grouped;g++)

    if(unaligned[g]) memcpy(unaligned[g],alignedBuff[g],g_len[g]);

#endif

  M_EMPTY(); // restore CPU multimedia state

  return advanced;

}

/* FFdecsa -- fast decsa algorithm

 *

 * Copyright (C) 2003-2004  fatih89r

 *

 * This program is free software; you can redistribute it and/or modify

 * it under the terms of the GNU General Public License as published by

 * the Free Software Foundation; either version 2 of the License, or

 * (at your option) any later version.

 *

 * This program is distributed in the hope that it will be useful,

 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

 * GNU General Public License for more details.

 *

 * You should have received a copy of the GNU General Public License

 * along with this program; if not, write to the Free Software

 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.

 */

#ifndef FFDECSA_H

#define FFDECSA_H

//----- public interface

// -- how many packets can be decrypted at the same time

// This is an info about internal decryption parallelism.

// You should try to call decrypt_packets with more packets than the number

// returned here for performance reasons (use get_suggested_cluster_size to know

// how many).

int get_internal_parallelism(void);

// -- how many packets you should have in a cluster when calling decrypt_packets

// This is a suggestion to achieve optimal performance; typically a little

// higher than what get_internal_parallelism returns.

// Passing less packets could slow down the decryption.

// Passing more packets is never bad (if you don't spend a lot of time building

// the list).

int get_suggested_cluster_size(void);

// -- alloc & free the key structure

void *get_key_struct(void);

void free_key_struct(void *keys);

// -- set control words, 8 bytes each

void set_control_words(void *keys, const unsigned char *even, const unsigned char *odd);

// -- set even control word, 8 bytes

void set_even_control_word(void *keys, const unsigned char *even);

// -- set odd control word, 8 bytes

void set_odd_control_word(void *keys, const unsigned char *odd);

// -- get control words, 8 bytes each

//void get_control_words(void *keys, unsigned char *even, unsigned char *odd);

// -- decrypt many TS packets

// This interface is a bit complicated because it is designed for maximum speed.

// Please read doc/how_to_use.txt.

int decrypt_packets(void *keys, unsigned char **cluster);

#endif

/* FFdecsa -- fast decsa algorithm

 *

 * Copyright (C) 2007 Dark Avenger

 *               2003-2004  fatih89r

 *

 * This program is free software; you can redistribute it and/or modify

 * it under the terms of the GNU General Public License as published by

 * the Free Software Foundation; either version 2 of the License, or

 * (at your option) any later version.

 *

 * This program is distributed in the hope that it will be useful,

 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

 * GNU General Public License for more details.

 *

 * You should have received a copy of the GNU General Public License

 * along with this program; if not, write to the Free Software

 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.

 */

#ifndef FFTABLE_H

#define FFTABLE_H

inline static void FFTABLEIN(unsigned char *tab, int g, unsigned char *data)

{

#if 0

  *(((int *)tab)+2*g)=*((int *)data);

  *(((int *)tab)+2*g+1)=*(((int *)data)+1);

#else

  *(((long long *)tab)+g)=*((long long *)data);

#endif

}

inline static void FFTABLEOUT(unsigned char *data, unsigned char *tab, int g)

{

#if 1

  *((int *)data)=*(((int *)tab)+2*g);

  *(((int *)data)+1)=*(((int *)tab)+2*g+1);

#else

  *((long long *)data)=*(((long long *)tab)+g);

#endif

}

inline static void FFTABLEOUTXORNBY(int n, unsigned char *data, unsigned char *tab, int g)

{

  int j;

  for(j=0;j<n;j++) *(data+j)^=*(tab+8*g+j);

}

#undef XOREQ_BEST_BY

inline static void XOREQ_BEST_BY(unsigned char *d, unsigned char *s)

{

	XOR_BEST_BY(d, d, s);

}

#endif //FFTABLE_H 

/* FFdecsa -- fast decsa algorithm

 *

 * Copyright (C) 2003-2004  fatih89r

 *

 * This program is free software; you can redistribute it and/or modify

 * it under the terms of the GNU General Public License as published by

 * the Free Software Foundation; either version 2 of the License, or

 * (at your option) any later version.

 *

 * This program is distributed in the hope that it will be useful,

 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

 * GNU General Public License for more details.

 *

 * You should have received a copy of the GNU General Public License

 * along with this program; if not, write to the Free Software

 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.

 */

#include "parallel_std_def.h"

typedef unsigned int group;

#define GROUP_PARALLELISM 32

#define FF0()      0x0

#define FF1()      0xffffffff

/* 64 rows of 32 bits */

inline static void FFTABLEIN(unsigned char *tab, int g, unsigned char *data){

  *(((int *)tab)+g)=*((int *)data);

  *(((int *)tab)+32+g)=*(((int *)data)+1);

}

inline static void FFTABLEOUT(unsigned char *data, unsigned char *tab, int g){

  *((int *)data)=*(((int *)tab)+g);

  *(((int *)data)+1)=*(((int *)tab)+32+g);

}

inline static void FFTABLEOUTXORNBY(int n, unsigned char *data, unsigned char *tab, int g){

  int j;

  for(j=0;j<n;j++){

    *(data+j)^=*(tab+4*(g+(j>=4?32-1:0))+j);

  }

}

typedef unsigned int batch;

#define BYTES_PER_BATCH 4

#define B_FFN_ALL_29() 0x29292929

#define B_FFN_ALL_02() 0x02020202

#define B_FFN_ALL_04() 0x04040404