From: pwpiwi Date: Wed, 15 Apr 2015 17:16:00 +0000 (+0200) Subject: add: compress fpga images during compile, uncompress at run time X-Git-Tag: v2.2.0~10^2~10 X-Git-Url: http://git.zerfleddert.de/cgi-bin/gitweb.cgi/proxmark3-svn/commitdiff_plain/add4d470469b74bb2495431a7963e39eb80d17ab add: compress fpga images during compile, uncompress at run time --- diff --git a/.gitignore b/.gitignore index 07669e14..51dcefc5 100644 --- a/.gitignore +++ b/.gitignore @@ -12,6 +12,7 @@ *.bin *.dll *.moc.cpp +*.gz *.exe proxmark proxmark3 diff --git a/Makefile b/Makefile index b558da2d..dfcbaecf 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,5 @@ include common/Makefile.common -GZIP=gzip FLASH_PORT=/dev/ttyACM0 all clean: %: bootrom/% armsrc/% client/% recovery/% diff --git a/armsrc/Makefile b/armsrc/Makefile index 3fd93ac3..c7d85f1a 100644 --- a/armsrc/Makefile +++ b/armsrc/Makefile @@ -10,7 +10,7 @@ APP_INCLUDES = apps.h #remove one of the following defines and comment out the relevant line #in the next section to remove that particular feature from compilation -APP_CFLAGS = -DWITH_LF -DWITH_ISO15693 -DWITH_ISO14443a -DWITH_ISO14443b -DWITH_ICLASS -DWITH_LEGICRF -DWITH_HITAG -DWITH_CRC -DON_DEVICE -fno-strict-aliasing -ffunction-sections -fdata-sections +APP_CFLAGS = -DWITH_LF -DWITH_ISO15693 -DWITH_ISO14443a -DWITH_ISO14443b -DWITH_ICLASS -DWITH_LEGICRF -DWITH_HITAG -DWITH_CRC -DON_DEVICE -DZ_SOLO -fno-strict-aliasing -ffunction-sections -fdata-sections #-DWITH_LCD #SRC_LCD = fonts.c LCD.c @@ -31,7 +31,11 @@ THUMBSRC = start.c \ string.c \ usb_cdc.c \ cmd.c \ - inflate.c + inflate.c \ + zutil.c \ + adler32.c \ + inftrees.c \ + inffast.c # These are to be compiled in ARM mode ARMSRC = fpgaloader.c \ @@ -57,11 +61,14 @@ OBJS = $(OBJDIR)/osimage.s19 all: $(OBJS) -$(OBJDIR)/fpga_lf.o: fpga_lf.bit - $(OBJCOPY) -O elf32-littlearm -I binary -B arm --redefine-sym _binary____fpga_fpga_lf_bit_start=_binary_fpga_lf_bit_start --redefine-sym _binary____fpga_fpga_lf_bit_end=_binary_fpga_lf_bit_end --prefix-sections=fpga_lf_bit $^ $@ +$(OBJDIR)/fpga_lf.o: $(OBJDIR)/fpga_lf.bit.gz + $(OBJCOPY) -O elf32-littlearm -I binary -B arm --redefine-sym _binary_obj_fpga_lf_bit_gz_start=_binary_fpga_lf_bit_start --redefine-sym _binary_obj_fpga_lf_bit_gz_end=_binary_fpga_lf_bit_end --prefix-sections=fpga_lf_bit $^ $@ -$(OBJDIR)/fpga_hf.o: fpga_hf.bit - $(OBJCOPY) -O elf32-littlearm -I binary -B arm --redefine-sym _binary____fpga_fpga_hf_bit_start=_binary_fpga_hf_bit_start --redefine-sym _binary____fpga_fpga_hf_bit_end=_binary_fpga_hf_bit_end --prefix-sections=fpga_hf_bit $^ $@ +$(OBJDIR)/fpga_hf.o: $(OBJDIR)/fpga_hf.bit.gz + $(OBJCOPY) -O elf32-littlearm -I binary -B arm --redefine-sym _binary_obj_fpga_hf_bit_gz_start=_binary_fpga_hf_bit_start --redefine-sym _binary_obj_fpga_hf_bit_gz_end=_binary_fpga_hf_bit_end --prefix-sections=fpga_hf_bit $^ $@ + +$(OBJDIR)/%.bit.gz: %.bit + $(GZIP) --best -c $^ >$@ $(OBJDIR)/fullimage.elf: $(VERSIONOBJ) $(OBJDIR)/fpga_lf.o $(OBJDIR)/fpga_hf.o $(THUMBOBJ) $(ARMOBJ) $(CC) $(LDFLAGS) -Wl,-T,ldscript,-Map,$(patsubst %.elf,%.map,$@) -o $@ $^ $(LIBS) @@ -82,6 +89,7 @@ clean: $(DELETE) $(OBJDIR)$(PATHSEP)*.s19 $(DELETE) $(OBJDIR)$(PATHSEP)*.map $(DELETE) $(OBJDIR)$(PATHSEP)*.d + $(DELETE) $(OBJDIR)$(PATHSEP)*.gz $(DELETE) version.c .PHONY: all clean help diff --git a/armsrc/adler32.c b/armsrc/adler32.c new file mode 100644 index 00000000..a868f073 --- /dev/null +++ b/armsrc/adler32.c @@ -0,0 +1,179 @@ +/* adler32.c -- compute the Adler-32 checksum of a data stream + * Copyright (C) 1995-2011 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* @(#) $Id$ */ + +#include "zutil.h" + +#define local static + +local uLong adler32_combine_ OF((uLong adler1, uLong adler2, z_off64_t len2)); + +#define BASE 65521 /* largest prime smaller than 65536 */ +#define NMAX 5552 +/* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */ + +#define DO1(buf,i) {adler += (buf)[i]; sum2 += adler;} +#define DO2(buf,i) DO1(buf,i); DO1(buf,i+1); +#define DO4(buf,i) DO2(buf,i); DO2(buf,i+2); +#define DO8(buf,i) DO4(buf,i); DO4(buf,i+4); +#define DO16(buf) DO8(buf,0); DO8(buf,8); + +/* use NO_DIVIDE if your processor does not do division in hardware -- + try it both ways to see which is faster */ +#ifdef NO_DIVIDE +/* note that this assumes BASE is 65521, where 65536 % 65521 == 15 + (thank you to John Reiser for pointing this out) */ +# define CHOP(a) \ + do { \ + unsigned long tmp = a >> 16; \ + a &= 0xffffUL; \ + a += (tmp << 4) - tmp; \ + } while (0) +# define MOD28(a) \ + do { \ + CHOP(a); \ + if (a >= BASE) a -= BASE; \ + } while (0) +# define MOD(a) \ + do { \ + CHOP(a); \ + MOD28(a); \ + } while (0) +# define MOD63(a) \ + do { /* this assumes a is not negative */ \ + z_off64_t tmp = a >> 32; \ + a &= 0xffffffffL; \ + a += (tmp << 8) - (tmp << 5) + tmp; \ + tmp = a >> 16; \ + a &= 0xffffL; \ + a += (tmp << 4) - tmp; \ + tmp = a >> 16; \ + a &= 0xffffL; \ + a += (tmp << 4) - tmp; \ + if (a >= BASE) a -= BASE; \ + } while (0) +#else +# define MOD(a) a %= BASE +# define MOD28(a) a %= BASE +# define MOD63(a) a %= BASE +#endif + +/* ========================================================================= */ +uLong ZEXPORT adler32(adler, buf, len) + uLong adler; + const Bytef *buf; + uInt len; +{ + unsigned long sum2; + unsigned n; + + /* split Adler-32 into component sums */ + sum2 = (adler >> 16) & 0xffff; + adler &= 0xffff; + + /* in case user likes doing a byte at a time, keep it fast */ + if (len == 1) { + adler += buf[0]; + if (adler >= BASE) + adler -= BASE; + sum2 += adler; + if (sum2 >= BASE) + sum2 -= BASE; + return adler | (sum2 << 16); + } + + /* initial Adler-32 value (deferred check for len == 1 speed) */ + if (buf == Z_NULL) + return 1L; + + /* in case short lengths are provided, keep it somewhat fast */ + if (len < 16) { + while (len--) { + adler += *buf++; + sum2 += adler; + } + if (adler >= BASE) + adler -= BASE; + MOD28(sum2); /* only added so many BASE's */ + return adler | (sum2 << 16); + } + + /* do length NMAX blocks -- requires just one modulo operation */ + while (len >= NMAX) { + len -= NMAX; + n = NMAX / 16; /* NMAX is divisible by 16 */ + do { + DO16(buf); /* 16 sums unrolled */ + buf += 16; + } while (--n); + MOD(adler); + MOD(sum2); + } + + /* do remaining bytes (less than NMAX, still just one modulo) */ + if (len) { /* avoid modulos if none remaining */ + while (len >= 16) { + len -= 16; + DO16(buf); + buf += 16; + } + while (len--) { + adler += *buf++; + sum2 += adler; + } + MOD(adler); + MOD(sum2); + } + + /* return recombined sums */ + return adler | (sum2 << 16); +} + +/* ========================================================================= */ +local uLong adler32_combine_(adler1, adler2, len2) + uLong adler1; + uLong adler2; + z_off64_t len2; +{ + unsigned long sum1; + unsigned long sum2; + unsigned rem; + + /* for negative len, return invalid adler32 as a clue for debugging */ + if (len2 < 0) + return 0xffffffffUL; + + /* the derivation of this formula is left as an exercise for the reader */ + MOD63(len2); /* assumes len2 >= 0 */ + rem = (unsigned)len2; + sum1 = adler1 & 0xffff; + sum2 = rem * sum1; + MOD(sum2); + sum1 += (adler2 & 0xffff) + BASE - 1; + sum2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - rem; + if (sum1 >= BASE) sum1 -= BASE; + if (sum1 >= BASE) sum1 -= BASE; + if (sum2 >= (BASE << 1)) sum2 -= (BASE << 1); + if (sum2 >= BASE) sum2 -= BASE; + return sum1 | (sum2 << 16); +} + +/* ========================================================================= */ +uLong ZEXPORT adler32_combine(adler1, adler2, len2) + uLong adler1; + uLong adler2; + z_off_t len2; +{ + return adler32_combine_(adler1, adler2, len2); +} + +uLong ZEXPORT adler32_combine64(adler1, adler2, len2) + uLong adler1; + uLong adler2; + z_off64_t len2; +{ + return adler32_combine_(adler1, adler2, len2); +} diff --git a/armsrc/apps.h b/armsrc/apps.h index fa081d21..98be05a3 100644 --- a/armsrc/apps.h +++ b/armsrc/apps.h @@ -19,6 +19,7 @@ #include "mifare.h" #include "../common/crc32.h" #include "BigBuf.h" +#include "fpgaloader.h" extern const uint8_t OddByteParity[256]; extern int rsamples; // = 0; @@ -50,60 +51,6 @@ void ListenReaderField(int limit); extern int ToSendMax; extern uint8_t ToSend[]; -/// fpga.h -void FpgaSendCommand(uint16_t cmd, uint16_t v); -void FpgaWriteConfWord(uint8_t v); -void FpgaDownloadAndGo(int bitstream_version); -int FpgaGatherBitstreamVersion(); -void FpgaGatherVersion(int bitstream_version, char *dst, int len); -void FpgaSetupSsc(void); -void SetupSpi(int mode); -bool FpgaSetupSscDma(uint8_t *buf, int len); -#define FpgaDisableSscDma(void) AT91C_BASE_PDC_SSC->PDC_PTCR = AT91C_PDC_RXTDIS; -#define FpgaEnableSscDma(void) AT91C_BASE_PDC_SSC->PDC_PTCR = AT91C_PDC_RXTEN; -void SetAdcMuxFor(uint32_t whichGpio); - -// Definitions for the FPGA commands. -#define FPGA_CMD_SET_CONFREG (1<<12) -#define FPGA_CMD_SET_DIVISOR (2<<12) -#define FPGA_CMD_SET_USER_BYTE1 (3<<12) -// Definitions for the FPGA configuration word. -// LF -#define FPGA_MAJOR_MODE_LF_ADC (0<<5) -#define FPGA_MAJOR_MODE_LF_EDGE_DETECT (1<<5) -#define FPGA_MAJOR_MODE_LF_PASSTHRU (2<<5) -// HF -#define FPGA_MAJOR_MODE_HF_READER_TX (0<<5) -#define FPGA_MAJOR_MODE_HF_READER_RX_XCORR (1<<5) -#define FPGA_MAJOR_MODE_HF_SIMULATOR (2<<5) -#define FPGA_MAJOR_MODE_HF_ISO14443A (3<<5) -// BOTH -#define FPGA_MAJOR_MODE_OFF (7<<5) -// Options for LF_ADC -#define FPGA_LF_ADC_READER_FIELD (1<<0) -// Options for LF_EDGE_DETECT -#define FPGA_CMD_SET_EDGE_DETECT_THRESHOLD FPGA_CMD_SET_USER_BYTE1 -#define FPGA_LF_EDGE_DETECT_READER_FIELD (1<<0) -#define FPGA_LF_EDGE_DETECT_TOGGLE_MODE (1<<1) -// Options for the HF reader, tx to tag -#define FPGA_HF_READER_TX_SHALLOW_MOD (1<<0) -// Options for the HF reader, correlating against rx from tag -#define FPGA_HF_READER_RX_XCORR_848_KHZ (1<<0) -#define FPGA_HF_READER_RX_XCORR_SNOOP (1<<1) -#define FPGA_HF_READER_RX_XCORR_QUARTER_FREQ (1<<2) -// Options for the HF simulated tag, how to modulate -#define FPGA_HF_SIMULATOR_NO_MODULATION (0<<0) -#define FPGA_HF_SIMULATOR_MODULATE_BPSK (1<<0) -#define FPGA_HF_SIMULATOR_MODULATE_212K (2<<0) -#define FPGA_HF_SIMULATOR_MODULATE_424K (4<<0) -#define FPGA_HF_SIMULATOR_MODULATE_424K_8BIT 0x5//101 - -// Options for ISO14443A -#define FPGA_HF_ISO14443A_SNIFFER (0<<0) -#define FPGA_HF_ISO14443A_TAGSIM_LISTEN (1<<0) -#define FPGA_HF_ISO14443A_TAGSIM_MOD (2<<0) -#define FPGA_HF_ISO14443A_READER_LISTEN (3<<0) -#define FPGA_HF_ISO14443A_READER_MOD (4<<0) /// lfops.h extern uint8_t decimation; diff --git a/armsrc/fpga_hf.bit.gz b/armsrc/fpga_hf.bit.gz deleted file mode 100644 index 0cbb214d..00000000 Binary files a/armsrc/fpga_hf.bit.gz and /dev/null differ diff --git a/armsrc/fpga_lf.bit.gz b/armsrc/fpga_lf.bit.gz deleted file mode 100644 index d736beed..00000000 Binary files a/armsrc/fpga_lf.bit.gz and /dev/null differ diff --git a/armsrc/fpgaloader.c b/armsrc/fpgaloader.c index 7e6845fd..26e512af 100644 --- a/armsrc/fpgaloader.c +++ b/armsrc/fpgaloader.c @@ -9,10 +9,18 @@ // Routines to load the FPGA image, and then to configure the FPGA's major // mode once it is configured. //----------------------------------------------------------------------------- + +#include +#include +#include +#include "fpgaloader.h" #include "proxmark3.h" -#include "apps.h" #include "util.h" #include "string.h" +#include "BigBuf.h" +#include "zlib.h" + +extern void Dbprintf(const char *fmt, ...); // remember which version of the bitstream we have already downloaded to the FPGA static int downloaded_bitstream = FPGA_BITSTREAM_ERR; @@ -23,9 +31,8 @@ extern uint8_t _binary_fpga_hf_bit_start, _binary_fpga_hf_bit_end; static uint8_t *fpga_image_ptr = NULL; static const uint8_t _bitparse_fixed_header[] = {0x00, 0x09, 0x0f, 0xf0, 0x0f, 0xf0, 0x0f, 0xf0, 0x0f, 0xf0, 0x00, 0x00, 0x01}; -static const uint8_t _gzip_header[] = {0x1f, 0x8b, 0x08}; // including compression method 0x08 (deflate) -#define GZIP_HEADER_SIZE sizeof(_gzip_header) #define FPGA_BITSTREAM_FIXED_HEADER_SIZE sizeof(_bitparse_fixed_header) +#define OUTPUT_BUFFER_LEN 80 //----------------------------------------------------------------------------- // Set up the Serial Peripheral Interface as master @@ -164,15 +171,86 @@ bool FpgaSetupSscDma(uint8_t *buf, int len) } -void reset_fpga_stream(uint8_t *image_start) +uint8_t get_from_fpga_stream(z_streamp compressed_fpga_stream, uint8_t *output_buffer) { - fpga_image_ptr = image_start; + if (fpga_image_ptr == compressed_fpga_stream->next_out) { // need more data + compressed_fpga_stream->next_out = output_buffer; + compressed_fpga_stream->avail_out = OUTPUT_BUFFER_LEN; + fpga_image_ptr = output_buffer; + int res = inflate(compressed_fpga_stream, Z_SYNC_FLUSH); + // if (res != Z_OK && res != Z_STREAM_END) { + Dbprintf("inflate returned: %d, %s", res, compressed_fpga_stream->msg); + // } + } + + Dbprintf("get_from_fpga_stream() returns %02x", *fpga_image_ptr); + return *fpga_image_ptr++; } -uint8_t get_from_fpga_stream(void) +static voidpf fpga_inflate_malloc(voidpf opaque, uInt items, uInt size) { - return *fpga_image_ptr++; + Dbprintf("zlib requested %d bytes", items*size); + return BigBuf_malloc(items*size); +} + + +static void fpga_inflate_free(voidpf opaque, voidpf address) +{ + Dbprintf("zlib wants to free memory"); + BigBuf_free_keep_EM(); +} + + +void init_fpga_inflate(z_streamp compressed_fpga_stream, uint8_t *fpga_image_start, uint32_t fpga_image_size, uint8_t *output_buffer) +{ + // initialize z_stream structure for inflate: + compressed_fpga_stream->next_in = fpga_image_start; + compressed_fpga_stream->avail_in = fpga_image_size; + compressed_fpga_stream->next_out = output_buffer; + compressed_fpga_stream->avail_out = OUTPUT_BUFFER_LEN; + compressed_fpga_stream->zalloc = &fpga_inflate_malloc; + compressed_fpga_stream->zfree = &fpga_inflate_free; + + // initialize inflate to automatically detect header: + int res = inflateInit2(compressed_fpga_stream, 15+32); + + fpga_image_ptr = output_buffer; + + Dbprintf("InflateInit returned %d", res); + Dbprintf("fpga_image_ptr pointing at %02x %02x %02x %02x", fpga_image_ptr[0], fpga_image_ptr[1], fpga_image_ptr[2], fpga_image_ptr[3]); + Dbprintf("zstream->next_in pointing at %02x %02x %02x %02x", compressed_fpga_stream->next_in[0], compressed_fpga_stream->next_in[1], compressed_fpga_stream->next_in[2], compressed_fpga_stream->next_in[3]); +} + + +bool reset_fpga_stream(int bitstream_version, z_streamp compressed_fpga_stream, uint8_t *output_buffer) +{ + uint8_t header[FPGA_BITSTREAM_FIXED_HEADER_SIZE]; + uint8_t *fpga_image_start; + uint32_t fpga_image_size; + + if (bitstream_version == FPGA_BITSTREAM_LF) { + fpga_image_start = &_binary_fpga_lf_bit_start; + fpga_image_size = (uint32_t)&_binary_fpga_lf_bit_end - (uint32_t)&_binary_fpga_lf_bit_start; + } else if (bitstream_version == FPGA_BITSTREAM_HF) { + fpga_image_start = &_binary_fpga_hf_bit_start; + fpga_image_size = (uint32_t)&_binary_fpga_hf_bit_end - (uint32_t)&_binary_fpga_hf_bit_start; + } else { + return false; + } + + init_fpga_inflate(compressed_fpga_stream, fpga_image_start, fpga_image_size, output_buffer); + + for (uint16_t i = 0; i < FPGA_BITSTREAM_FIXED_HEADER_SIZE; i++) { + header[i] = get_from_fpga_stream(compressed_fpga_stream, output_buffer); + } + + // Check for a valid .bit file (starts with _bitparse_fixed_header) + if(memcmp(_bitparse_fixed_header, header, FPGA_BITSTREAM_FIXED_HEADER_SIZE) == 0) { + return true; + } else { + return false; + } } @@ -190,8 +268,11 @@ static void DownloadFPGA_byte(unsigned char w) } // Download the fpga image starting at current stream position with length FpgaImageLen bytes -static void DownloadFPGA(int FpgaImageLen) +static void DownloadFPGA(int FpgaImageLen, z_streamp compressed_fpga_stream, uint8_t *output_buffer) { + Dbprintf("Would have loaded FPGA"); + return; + int i=0; AT91C_BASE_PIOA->PIO_OER = GPIO_FPGA_ON; @@ -244,7 +325,7 @@ static void DownloadFPGA(int FpgaImageLen) } while(FpgaImageLen-->0) { - DownloadFPGA_byte(get_from_fpga_stream()); + DownloadFPGA_byte(get_from_fpga_stream(compressed_fpga_stream, output_buffer)); } // continue to clock FPGA until ready signal goes high @@ -269,13 +350,13 @@ static void DownloadFPGA(int FpgaImageLen) * (big endian), bytes content. Except for section 'e' which has 4 bytes * length. */ -int bitparse_find_section(char section_name, unsigned int *section_length) +int bitparse_find_section(char section_name, unsigned int *section_length, z_streamp compressed_fpga_stream, uint8_t *output_buffer) { int result = 0; #define MAX_FPGA_BIT_STREAM_HEADER_SEARCH 100 // maximum number of bytes to search for the requested section uint16_t numbytes = 0; while(numbytes < MAX_FPGA_BIT_STREAM_HEADER_SEARCH) { - char current_name = get_from_fpga_stream(); + char current_name = get_from_fpga_stream(compressed_fpga_stream, output_buffer); numbytes++; unsigned int current_length = 0; if(current_name < 'a' || current_name > 'e') { @@ -286,12 +367,12 @@ int bitparse_find_section(char section_name, unsigned int *section_length) switch(current_name) { case 'e': /* Four byte length field */ - current_length += get_from_fpga_stream() << 24; - current_length += get_from_fpga_stream() << 16; + current_length += get_from_fpga_stream(compressed_fpga_stream, output_buffer) << 24; + current_length += get_from_fpga_stream(compressed_fpga_stream, output_buffer) << 16; numbytes += 2; default: /* Fall through, two byte length field */ - current_length += get_from_fpga_stream() << 8; - current_length += get_from_fpga_stream() << 0; + current_length += get_from_fpga_stream(compressed_fpga_stream, output_buffer) << 8; + current_length += get_from_fpga_stream(compressed_fpga_stream, output_buffer) << 0; numbytes += 2; } @@ -308,7 +389,7 @@ int bitparse_find_section(char section_name, unsigned int *section_length) } for (uint16_t i = 0; i < current_length && numbytes < MAX_FPGA_BIT_STREAM_HEADER_SEARCH; i++) { - get_from_fpga_stream(); + get_from_fpga_stream(compressed_fpga_stream, output_buffer); numbytes++; } } @@ -316,11 +397,6 @@ int bitparse_find_section(char section_name, unsigned int *section_length) return result; } -void init_fpga_inflate(void) -{ - // initialize zlib for inflate -} - //----------------------------------------------------------------------------- // Find out which FPGA image format is stored in flash, then call DownloadFPGA @@ -328,71 +404,42 @@ void init_fpga_inflate(void) //----------------------------------------------------------------------------- void FpgaDownloadAndGo(int bitstream_version) { - uint8_t header[FPGA_BITSTREAM_FIXED_HEADER_SIZE]; + z_stream compressed_fpga_stream; + uint8_t output_buffer[OUTPUT_BUFFER_LEN]; // check whether or not the bitstream is already loaded if (downloaded_bitstream == bitstream_version) return; - if (bitstream_version == FPGA_BITSTREAM_LF) { - reset_fpga_stream(&_binary_fpga_lf_bit_start); - } else if (bitstream_version == FPGA_BITSTREAM_HF) { - reset_fpga_stream(&_binary_fpga_hf_bit_start); - } else + if (!reset_fpga_stream(bitstream_version, &compressed_fpga_stream, output_buffer)) { return; - - uint16_t i = 0; - for (; i < GZIP_HEADER_SIZE; i++) { - header[i] = get_from_fpga_stream(); } - // Check for compressed new flash image format (starts with gzip header) - if(memcmp(_gzip_header, header, GZIP_HEADER_SIZE) == 0) { - init_fpga_inflate(); - } - - for (; i < FPGA_BITSTREAM_FIXED_HEADER_SIZE; i++) { - header[i] = get_from_fpga_stream(); - } - - // Check for the new flash image format: Should have the .bit file at &_binary_fpga_bit_start - if(memcmp(_bitparse_fixed_header, header, FPGA_BITSTREAM_FIXED_HEADER_SIZE) == 0) { - unsigned int bitstream_length; - if(bitparse_find_section('e', &bitstream_length)) { - DownloadFPGA(bitstream_length); - downloaded_bitstream = bitstream_version; - return; /* All done */ - } + unsigned int bitstream_length; + if(bitparse_find_section('e', &bitstream_length, &compressed_fpga_stream, output_buffer)) { + DownloadFPGA(bitstream_length, &compressed_fpga_stream, output_buffer); + downloaded_bitstream = bitstream_version; + return; /* All done */ } } -int FpgaGatherBitstreamVersion() -{ - return downloaded_bitstream; -} void FpgaGatherVersion(int bitstream_version, char *dst, int len) { unsigned int fpga_info_len; char tempstr[40]; + z_stream compressed_fpga_stream; + uint8_t output_buffer[OUTPUT_BUFFER_LEN]; dst[0] = '\0'; - if (bitstream_version == FPGA_BITSTREAM_LF) { - reset_fpga_stream(&_binary_fpga_lf_bit_start); - } else if (bitstream_version == FPGA_BITSTREAM_HF) { - reset_fpga_stream(&_binary_fpga_hf_bit_start); - } else + if (!reset_fpga_stream(bitstream_version, &compressed_fpga_stream, output_buffer)) { return; - - - for (uint16_t i = 0; i < FPGA_BITSTREAM_FIXED_HEADER_SIZE; i++) { - get_from_fpga_stream(); } - if(bitparse_find_section('a', &fpga_info_len)) { + if(bitparse_find_section('a', &fpga_info_len, &compressed_fpga_stream, output_buffer)) { for (uint16_t i = 0; i < fpga_info_len; i++) { - char c = (char)get_from_fpga_stream(); + char c = (char)get_from_fpga_stream(&compressed_fpga_stream, output_buffer); if (i < sizeof(tempstr)) { tempstr[i] = c; } @@ -403,30 +450,30 @@ void FpgaGatherVersion(int bitstream_version, char *dst, int len) strncat(dst, "HF ", len-1); } strncat(dst, "FPGA image built", len-1); - if(bitparse_find_section('b', &fpga_info_len)) { + if(bitparse_find_section('b', &fpga_info_len, &compressed_fpga_stream, output_buffer)) { strncat(dst, " for ", len-1); for (uint16_t i = 0; i < fpga_info_len; i++) { - char c = (char)get_from_fpga_stream(); + char c = (char)get_from_fpga_stream(&compressed_fpga_stream, output_buffer); if (i < sizeof(tempstr)) { tempstr[i] = c; } } strncat(dst, tempstr, len-1); } - if(bitparse_find_section('c', &fpga_info_len)) { + if(bitparse_find_section('c', &fpga_info_len, &compressed_fpga_stream, output_buffer)) { strncat(dst, " on ", len-1); for (uint16_t i = 0; i < fpga_info_len; i++) { - char c = (char)get_from_fpga_stream(); + char c = (char)get_from_fpga_stream(&compressed_fpga_stream, output_buffer); if (i < sizeof(tempstr)) { tempstr[i] = c; } } strncat(dst, tempstr, len-1); } - if(bitparse_find_section('d', &fpga_info_len)) { + if(bitparse_find_section('d', &fpga_info_len, &compressed_fpga_stream, output_buffer)) { strncat(dst, " at ", len-1); for (uint16_t i = 0; i < fpga_info_len; i++) { - char c = (char)get_from_fpga_stream(); + char c = (char)get_from_fpga_stream(&compressed_fpga_stream, output_buffer); if (i < sizeof(tempstr)) { tempstr[i] = c; } @@ -435,6 +482,7 @@ void FpgaGatherVersion(int bitstream_version, char *dst, int len) } } + //----------------------------------------------------------------------------- // Send a 16 bit command/data pair to the FPGA. // The bit format is: C3 C2 C1 C0 D11 D10 D9 D8 D7 D6 D5 D4 D3 D2 D1 D0 diff --git a/armsrc/fpgaloader.h b/armsrc/fpgaloader.h new file mode 100644 index 00000000..6981b216 --- /dev/null +++ b/armsrc/fpgaloader.h @@ -0,0 +1,64 @@ +//----------------------------------------------------------------------------- +// Jonathan Westhues, April 2006 +// iZsh , 2014 +// +// This code is licensed to you under the terms of the GNU GPL, version 2 or, +// at your option, any later version. See the LICENSE.txt file for the text of +// the license. +//----------------------------------------------------------------------------- +// Routines to load the FPGA image, and then to configure the FPGA's major +// mode once it is configured. +//----------------------------------------------------------------------------- + +void FpgaSendCommand(uint16_t cmd, uint16_t v); +void FpgaWriteConfWord(uint8_t v); +void FpgaDownloadAndGo(int bitstream_version); +void FpgaGatherVersion(int bitstream_version, char *dst, int len); +void FpgaSetupSsc(void); +void SetupSpi(int mode); +bool FpgaSetupSscDma(uint8_t *buf, int len); +#define FpgaDisableSscDma(void) AT91C_BASE_PDC_SSC->PDC_PTCR = AT91C_PDC_RXTDIS; +#define FpgaEnableSscDma(void) AT91C_BASE_PDC_SSC->PDC_PTCR = AT91C_PDC_RXTEN; +void SetAdcMuxFor(uint32_t whichGpio); + +// Definitions for the FPGA commands. +#define FPGA_CMD_SET_CONFREG (1<<12) +#define FPGA_CMD_SET_DIVISOR (2<<12) +#define FPGA_CMD_SET_USER_BYTE1 (3<<12) +// Definitions for the FPGA configuration word. +// LF +#define FPGA_MAJOR_MODE_LF_ADC (0<<5) +#define FPGA_MAJOR_MODE_LF_EDGE_DETECT (1<<5) +#define FPGA_MAJOR_MODE_LF_PASSTHRU (2<<5) +// HF +#define FPGA_MAJOR_MODE_HF_READER_TX (0<<5) +#define FPGA_MAJOR_MODE_HF_READER_RX_XCORR (1<<5) +#define FPGA_MAJOR_MODE_HF_SIMULATOR (2<<5) +#define FPGA_MAJOR_MODE_HF_ISO14443A (3<<5) +// BOTH +#define FPGA_MAJOR_MODE_OFF (7<<5) +// Options for LF_ADC +#define FPGA_LF_ADC_READER_FIELD (1<<0) +// Options for LF_EDGE_DETECT +#define FPGA_CMD_SET_EDGE_DETECT_THRESHOLD FPGA_CMD_SET_USER_BYTE1 +#define FPGA_LF_EDGE_DETECT_READER_FIELD (1<<0) +#define FPGA_LF_EDGE_DETECT_TOGGLE_MODE (1<<1) +// Options for the HF reader, tx to tag +#define FPGA_HF_READER_TX_SHALLOW_MOD (1<<0) +// Options for the HF reader, correlating against rx from tag +#define FPGA_HF_READER_RX_XCORR_848_KHZ (1<<0) +#define FPGA_HF_READER_RX_XCORR_SNOOP (1<<1) +#define FPGA_HF_READER_RX_XCORR_QUARTER_FREQ (1<<2) +// Options for the HF simulated tag, how to modulate +#define FPGA_HF_SIMULATOR_NO_MODULATION (0<<0) +#define FPGA_HF_SIMULATOR_MODULATE_BPSK (1<<0) +#define FPGA_HF_SIMULATOR_MODULATE_212K (2<<0) +#define FPGA_HF_SIMULATOR_MODULATE_424K (4<<0) +#define FPGA_HF_SIMULATOR_MODULATE_424K_8BIT 0x5//101 + +// Options for ISO14443A +#define FPGA_HF_ISO14443A_SNIFFER (0<<0) +#define FPGA_HF_ISO14443A_TAGSIM_LISTEN (1<<0) +#define FPGA_HF_ISO14443A_TAGSIM_MOD (2<<0) +#define FPGA_HF_ISO14443A_READER_LISTEN (3<<0) +#define FPGA_HF_ISO14443A_READER_MOD (4<<0) diff --git a/armsrc/inffast.c b/armsrc/inffast.c new file mode 100644 index 00000000..bda59ceb --- /dev/null +++ b/armsrc/inffast.c @@ -0,0 +1,340 @@ +/* inffast.c -- fast decoding + * Copyright (C) 1995-2008, 2010, 2013 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "inftrees.h" +#include "inflate.h" +#include "inffast.h" + +#ifndef ASMINF + +/* Allow machine dependent optimization for post-increment or pre-increment. + Based on testing to date, + Pre-increment preferred for: + - PowerPC G3 (Adler) + - MIPS R5000 (Randers-Pehrson) + Post-increment preferred for: + - none + No measurable difference: + - Pentium III (Anderson) + - M68060 (Nikl) + */ +#ifdef POSTINC +# define OFF 0 +# define PUP(a) *(a)++ +#else +# define OFF 1 +# define PUP(a) *++(a) +#endif + +/* + Decode literal, length, and distance codes and write out the resulting + literal and match bytes until either not enough input or output is + available, an end-of-block is encountered, or a data error is encountered. + When large enough input and output buffers are supplied to inflate(), for + example, a 16K input buffer and a 64K output buffer, more than 95% of the + inflate execution time is spent in this routine. + + Entry assumptions: + + state->mode == LEN + strm->avail_in >= 6 + strm->avail_out >= 258 + start >= strm->avail_out + state->bits < 8 + + On return, state->mode is one of: + + LEN -- ran out of enough output space or enough available input + TYPE -- reached end of block code, inflate() to interpret next block + BAD -- error in block data + + Notes: + + - The maximum input bits used by a length/distance pair is 15 bits for the + length code, 5 bits for the length extra, 15 bits for the distance code, + and 13 bits for the distance extra. This totals 48 bits, or six bytes. + Therefore if strm->avail_in >= 6, then there is enough input to avoid + checking for available input while decoding. + + - The maximum bytes that a single length/distance pair can output is 258 + bytes, which is the maximum length that can be coded. inflate_fast() + requires strm->avail_out >= 258 for each loop to avoid checking for + output space. + */ +void ZLIB_INTERNAL inflate_fast(strm, start) +z_streamp strm; +unsigned start; /* inflate()'s starting value for strm->avail_out */ +{ + struct inflate_state FAR *state; + z_const unsigned char FAR *in; /* local strm->next_in */ + z_const unsigned char FAR *last; /* have enough input while in < last */ + unsigned char FAR *out; /* local strm->next_out */ + unsigned char FAR *beg; /* inflate()'s initial strm->next_out */ + unsigned char FAR *end; /* while out < end, enough space available */ +#ifdef INFLATE_STRICT + unsigned dmax; /* maximum distance from zlib header */ +#endif + unsigned wsize; /* window size or zero if not using window */ + unsigned whave; /* valid bytes in the window */ + unsigned wnext; /* window write index */ + unsigned char FAR *window; /* allocated sliding window, if wsize != 0 */ + unsigned long hold; /* local strm->hold */ + unsigned bits; /* local strm->bits */ + code const FAR *lcode; /* local strm->lencode */ + code const FAR *dcode; /* local strm->distcode */ + unsigned lmask; /* mask for first level of length codes */ + unsigned dmask; /* mask for first level of distance codes */ + code here; /* retrieved table entry */ + unsigned op; /* code bits, operation, extra bits, or */ + /* window position, window bytes to copy */ + unsigned len; /* match length, unused bytes */ + unsigned dist; /* match distance */ + unsigned char FAR *from; /* where to copy match from */ + + /* copy state to local variables */ + state = (struct inflate_state FAR *)strm->state; + in = strm->next_in - OFF; + last = in + (strm->avail_in - 5); + out = strm->next_out - OFF; + beg = out - (start - strm->avail_out); + end = out + (strm->avail_out - 257); +#ifdef INFLATE_STRICT + dmax = state->dmax; +#endif + wsize = state->wsize; + whave = state->whave; + wnext = state->wnext; + window = state->window; + hold = state->hold; + bits = state->bits; + lcode = state->lencode; + dcode = state->distcode; + lmask = (1U << state->lenbits) - 1; + dmask = (1U << state->distbits) - 1; + + /* decode literals and length/distances until end-of-block or not enough + input data or output space */ + do { + if (bits < 15) { + hold += (unsigned long)(PUP(in)) << bits; + bits += 8; + hold += (unsigned long)(PUP(in)) << bits; + bits += 8; + } + here = lcode[hold & lmask]; + dolen: + op = (unsigned)(here.bits); + hold >>= op; + bits -= op; + op = (unsigned)(here.op); + if (op == 0) { /* literal */ + Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? + "inflate: literal '%c'\n" : + "inflate: literal 0x%02x\n", here.val)); + PUP(out) = (unsigned char)(here.val); + } + else if (op & 16) { /* length base */ + len = (unsigned)(here.val); + op &= 15; /* number of extra bits */ + if (op) { + if (bits < op) { + hold += (unsigned long)(PUP(in)) << bits; + bits += 8; + } + len += (unsigned)hold & ((1U << op) - 1); + hold >>= op; + bits -= op; + } + Tracevv((stderr, "inflate: length %u\n", len)); + if (bits < 15) { + hold += (unsigned long)(PUP(in)) << bits; + bits += 8; + hold += (unsigned long)(PUP(in)) << bits; + bits += 8; + } + here = dcode[hold & dmask]; + dodist: + op = (unsigned)(here.bits); + hold >>= op; + bits -= op; + op = (unsigned)(here.op); + if (op & 16) { /* distance base */ + dist = (unsigned)(here.val); + op &= 15; /* number of extra bits */ + if (bits < op) { + hold += (unsigned long)(PUP(in)) << bits; + bits += 8; + if (bits < op) { + hold += (unsigned long)(PUP(in)) << bits; + bits += 8; + } + } + dist += (unsigned)hold & ((1U << op) - 1); +#ifdef INFLATE_STRICT + if (dist > dmax) { + strm->msg = (char *)"invalid distance too far back"; + state->mode = BAD; + break; + } +#endif + hold >>= op; + bits -= op; + Tracevv((stderr, "inflate: distance %u\n", dist)); + op = (unsigned)(out - beg); /* max distance in output */ + if (dist > op) { /* see if copy from window */ + op = dist - op; /* distance back in window */ + if (op > whave) { + if (state->sane) { + strm->msg = + (char *)"invalid distance too far back"; + state->mode = BAD; + break; + } +#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR + if (len <= op - whave) { + do { + PUP(out) = 0; + } while (--len); + continue; + } + len -= op - whave; + do { + PUP(out) = 0; + } while (--op > whave); + if (op == 0) { + from = out - dist; + do { + PUP(out) = PUP(from); + } while (--len); + continue; + } +#endif + } + from = window - OFF; + if (wnext == 0) { /* very common case */ + from += wsize - op; + if (op < len) { /* some from window */ + len -= op; + do { + PUP(out) = PUP(from); + } while (--op); + from = out - dist; /* rest from output */ + } + } + else if (wnext < op) { /* wrap around window */ + from += wsize + wnext - op; + op -= wnext; + if (op < len) { /* some from end of window */ + len -= op; + do { + PUP(out) = PUP(from); + } while (--op); + from = window - OFF; + if (wnext < len) { /* some from start of window */ + op = wnext; + len -= op; + do { + PUP(out) = PUP(from); + } while (--op); + from = out - dist; /* rest from output */ + } + } + } + else { /* contiguous in window */ + from += wnext - op; + if (op < len) { /* some from window */ + len -= op; + do { + PUP(out) = PUP(from); + } while (--op); + from = out - dist; /* rest from output */ + } + } + while (len > 2) { + PUP(out) = PUP(from); + PUP(out) = PUP(from); + PUP(out) = PUP(from); + len -= 3; + } + if (len) { + PUP(out) = PUP(from); + if (len > 1) + PUP(out) = PUP(from); + } + } + else { + from = out - dist; /* copy direct from output */ + do { /* minimum length is three */ + PUP(out) = PUP(from); + PUP(out) = PUP(from); + PUP(out) = PUP(from); + len -= 3; + } while (len > 2); + if (len) { + PUP(out) = PUP(from); + if (len > 1) + PUP(out) = PUP(from); + } + } + } + else if ((op & 64) == 0) { /* 2nd level distance code */ + here = dcode[here.val + (hold & ((1U << op) - 1))]; + goto dodist; + } + else { + strm->msg = (char *)"invalid distance code"; + state->mode = BAD; + break; + } + } + else if ((op & 64) == 0) { /* 2nd level length code */ + here = lcode[here.val + (hold & ((1U << op) - 1))]; + goto dolen; + } + else if (op & 32) { /* end-of-block */ + Tracevv((stderr, "inflate: end of block\n")); + state->mode = TYPE; + break; + } + else { + strm->msg = (char *)"invalid literal/length code"; + state->mode = BAD; + break; + } + } while (in < last && out < end); + + /* return unused bytes (on entry, bits < 8, so in won't go too far back) */ + len = bits >> 3; + in -= len; + bits -= len << 3; + hold &= (1U << bits) - 1; + + /* update state and return */ + strm->next_in = in + OFF; + strm->next_out = out + OFF; + strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last)); + strm->avail_out = (unsigned)(out < end ? + 257 + (end - out) : 257 - (out - end)); + state->hold = hold; + state->bits = bits; + return; +} + +/* + inflate_fast() speedups that turned out slower (on a PowerPC G3 750CXe): + - Using bit fields for code structure + - Different op definition to avoid & for extra bits (do & for table bits) + - Three separate decoding do-loops for direct, window, and wnext == 0 + - Special case for distance > 1 copies to do overlapped load and store copy + - Explicit branch predictions (based on measured branch probabilities) + - Deferring match copy and interspersed it with decoding subsequent codes + - Swapping literal/length else + - Swapping window/direct else + - Larger unrolled copy loops (three is about right) + - Moving len -= 3 statement into middle of loop + */ + +#endif /* !ASMINF */ diff --git a/armsrc/inftrees.c b/armsrc/inftrees.c new file mode 100644 index 00000000..d8c53250 --- /dev/null +++ b/armsrc/inftrees.c @@ -0,0 +1,302 @@ +/* inftrees.c -- generate Huffman trees for efficient decoding + * Copyright (C) 1995-2013 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "zutil.h" +#include "inftrees.h" + +#define MAXBITS 15 + +const char inflate_copyright[] = + " inflate 1.2.8 Copyright 1995-2013 Mark Adler "; +/* + If you use the zlib library in a product, an acknowledgment is welcome + in the documentation of your product. If for some reason you cannot + include such an acknowledgment, I would appreciate that you keep this + copyright string in the executable of your product. + */ + +/* + Build a set of tables to decode the provided canonical Huffman code. + The code lengths are lens[0..codes-1]. The result starts at *table, + whose indices are 0..2^bits-1. work is a writable array of at least + lens shorts, which is used as a work area. type is the type of code + to be generated, CODES, LENS, or DISTS. On return, zero is success, + -1 is an invalid code, and +1 means that ENOUGH isn't enough. table + on return points to the next available entry's address. bits is the + requested root table index bits, and on return it is the actual root + table index bits. It will differ if the request is greater than the + longest code or if it is less than the shortest code. + */ +int ZLIB_INTERNAL inflate_table(codetype type, unsigned short FAR *lens, + unsigned codes, code FAR * FAR *table, + unsigned FAR *bits, unsigned short FAR *work) +{ + unsigned len; /* a code's length in bits */ + unsigned sym; /* index of code symbols */ + unsigned min, max; /* minimum and maximum code lengths */ + unsigned root; /* number of index bits for root table */ + unsigned curr; /* number of index bits for current table */ + unsigned drop; /* code bits to drop for sub-table */ + int left; /* number of prefix codes available */ + unsigned used; /* code entries in table used */ + unsigned huff; /* Huffman code */ + unsigned incr; /* for incrementing code, index */ + unsigned fill; /* index for replicating entries */ + unsigned low; /* low bits for current root entry */ + unsigned mask; /* mask for low root bits */ + code here; /* table entry for duplication */ + code FAR *next; /* next available space in table */ + const unsigned short FAR *base; /* base value table to use */ + const unsigned short FAR *extra; /* extra bits table to use */ + int end; /* use base and extra for symbol > end */ + unsigned short count[MAXBITS+1]; /* number of codes of each length */ + unsigned short offs[MAXBITS+1]; /* offsets in table for each length */ + static const unsigned short lbase[31] = { /* Length codes 257..285 base */ + 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, + 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; + static const unsigned short lext[31] = { /* Length codes 257..285 extra */ + 16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 18, 18, 18, 18, + 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 72, 78}; + static const unsigned short dbase[32] = { /* Distance codes 0..29 base */ + 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, + 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, + 8193, 12289, 16385, 24577, 0, 0}; + static const unsigned short dext[32] = { /* Distance codes 0..29 extra */ + 16, 16, 16, 16, 17, 17, 18, 18, 19, 19, 20, 20, 21, 21, 22, 22, + 23, 23, 24, 24, 25, 25, 26, 26, 27, 27, + 28, 28, 29, 29, 64, 64}; + + /* + Process a set of code lengths to create a canonical Huffman code. The + code lengths are lens[0..codes-1]. Each length corresponds to the + symbols 0..codes-1. The Huffman code is generated by first sorting the + symbols by length from short to long, and retaining the symbol order + for codes with equal lengths. Then the code starts with all zero bits + for the first code of the shortest length, and the codes are integer + increments for the same length, and zeros are appended as the length + increases. For the deflate format, these bits are stored backwards + from their more natural integer increment ordering, and so when the + decoding tables are built in the large loop below, the integer codes + are incremented backwards. + + This routine assumes, but does not check, that all of the entries in + lens[] are in the range 0..MAXBITS. The caller must assure this. + 1..MAXBITS is interpreted as that code length. zero means that that + symbol does not occur in this code. + + The codes are sorted by computing a count of codes for each length, + creating from that a table of starting indices for each length in the + sorted table, and then entering the symbols in order in the sorted + table. The sorted table is work[], with that space being provided by + the caller. + + The length counts are used for other purposes as well, i.e. finding + the minimum and maximum length codes, determining if there are any + codes at all, checking for a valid set of lengths, and looking ahead + at length counts to determine sub-table sizes when building the + decoding tables. + */ + + /* accumulate lengths for codes (assumes lens[] all in 0..MAXBITS) */ + for (len = 0; len <= MAXBITS; len++) + count[len] = 0; + for (sym = 0; sym < codes; sym++) + count[lens[sym]]++; + + /* bound code lengths, force root to be within code lengths */ + root = *bits; + for (max = MAXBITS; max >= 1; max--) + if (count[max] != 0) break; + if (root > max) root = max; + if (max == 0) { /* no symbols to code at all */ + here.op = (unsigned char)64; /* invalid code marker */ + here.bits = (unsigned char)1; + here.val = (unsigned short)0; + *(*table)++ = here; /* make a table to force an error */ + *(*table)++ = here; + *bits = 1; + return 0; /* no symbols, but wait for decoding to report error */ + } + for (min = 1; min < max; min++) + if (count[min] != 0) break; + if (root < min) root = min; + + /* check for an over-subscribed or incomplete set of lengths */ + left = 1; + for (len = 1; len <= MAXBITS; len++) { + left <<= 1; + left -= count[len]; + if (left < 0) return -1; /* over-subscribed */ + } + if (left > 0 && (type == CODES || max != 1)) + return -1; /* incomplete set */ + + /* generate offsets into symbol table for each length for sorting */ + offs[1] = 0; + for (len = 1; len < MAXBITS; len++) + offs[len + 1] = offs[len] + count[len]; + + /* sort symbols by length, by symbol order within each length */ + for (sym = 0; sym < codes; sym++) + if (lens[sym] != 0) work[offs[lens[sym]]++] = (unsigned short)sym; + + /* + Create and fill in decoding tables. In this loop, the table being + filled is at next and has curr index bits. The code being used is huff + with length len. That code is converted to an index by dropping drop + bits off of the bottom. For codes where len is less than drop + curr, + those top drop + curr - len bits are incremented through all values to + fill the table with replicated entries. + + root is the number of index bits for the root table. When len exceeds + root, sub-tables are created pointed to by the root entry with an index + of the low root bits of huff. This is saved in low to check for when a + new sub-table should be started. drop is zero when the root table is + being filled, and drop is root when sub-tables are being filled. + + When a new sub-table is needed, it is necessary to look ahead in the + code lengths to determine what size sub-table is needed. The length + counts are used for this, and so count[] is decremented as codes are + entered in the tables. + + used keeps track of how many table entries have been allocated from the + provided *table space. It is checked for LENS and DIST tables against + the constants ENOUGH_LENS and ENOUGH_DISTS to guard against changes in + the initial root table size constants. See the comments in inftrees.h + for more information. + + sym increments through all symbols, and the loop terminates when + all codes of length max, i.e. all codes, have been processed. This + routine permits incomplete codes, so another loop after this one fills + in the rest of the decoding tables with invalid code markers. + */ + + /* set up for code type */ + switch (type) { + case CODES: + base = extra = work; /* dummy value--not used */ + end = 19; + break; + case LENS: + base = lbase; + base -= 257; + extra = lext; + extra -= 257; + end = 256; + break; + default: /* DISTS */ + base = dbase; + extra = dext; + end = -1; + } + + /* initialize state for loop */ + huff = 0; /* starting code */ + sym = 0; /* starting code symbol */ + len = min; /* starting code length */ + next = *table; /* current table to fill in */ + curr = root; /* current table index bits */ + drop = 0; /* current bits to drop from code for index */ + low = (unsigned)(-1); /* trigger new sub-table when len > root */ + used = 1U << root; /* use root table entries */ + mask = used - 1; /* mask for comparing low */ + + /* check available table space */ + if ((type == LENS && used > ENOUGH_LENS) || + (type == DISTS && used > ENOUGH_DISTS)) + return 1; + + /* process all codes and make table entries */ + for (;;) { + /* create table entry */ + here.bits = (unsigned char)(len - drop); + if ((int)(work[sym]) < end) { + here.op = (unsigned char)0; + here.val = work[sym]; + } + else if ((int)(work[sym]) > end) { + here.op = (unsigned char)(extra[work[sym]]); + here.val = base[work[sym]]; + } + else { + here.op = (unsigned char)(32 + 64); /* end of block */ + here.val = 0; + } + + /* replicate for those indices with low len bits equal to huff */ + incr = 1U << (len - drop); + fill = 1U << curr; + min = fill; /* save offset to next table */ + do { + fill -= incr; + next[(huff >> drop) + fill] = here; + } while (fill != 0); + + /* backwards increment the len-bit code huff */ + incr = 1U << (len - 1); + while (huff & incr) + incr >>= 1; + if (incr != 0) { + huff &= incr - 1; + huff += incr; + } + else + huff = 0; + + /* go to next symbol, update count, len */ + sym++; + if (--(count[len]) == 0) { + if (len == max) break; + len = lens[work[sym]]; + } + + /* create new sub-table if needed */ + if (len > root && (huff & mask) != low) { + /* if first time, transition to sub-tables */ + if (drop == 0) + drop = root; + + /* increment past last table */ + next += min; /* here min is 1 << curr */ + + /* determine length of next table */ + curr = len - drop; + left = (int)(1 << curr); + while (curr + drop < max) { + left -= count[curr + drop]; + if (left <= 0) break; + curr++; + left <<= 1; + } + + /* check for enough space */ + used += 1U << curr; + if ((type == LENS && used > ENOUGH_LENS) || + (type == DISTS && used > ENOUGH_DISTS)) + return 1; + + /* point entry in root table to sub-table */ + low = huff & mask; + (*table)[low].op = (unsigned char)curr; + (*table)[low].bits = (unsigned char)root; + (*table)[low].val = (unsigned short)(next - *table); + } + } + + /* fill in remaining table entry if code is incomplete (guaranteed to have + at most one remaining entry, since if the code is incomplete, the + maximum code length that was allowed to get this far is one bit) */ + if (huff != 0) { + here.op = (unsigned char)64; /* invalid code marker */ + here.bits = (unsigned char)(len - drop); + here.val = (unsigned short)0; + next[huff] = here; + } + + /* set return parameters */ + *table += used; + *bits = root; + return 0; +} diff --git a/armsrc/zutil.c b/armsrc/zutil.c new file mode 100644 index 00000000..23d2ebef --- /dev/null +++ b/armsrc/zutil.c @@ -0,0 +1,324 @@ +/* zutil.c -- target dependent utility functions for the compression library + * Copyright (C) 1995-2005, 2010, 2011, 2012 Jean-loup Gailly. + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +/* @(#) $Id$ */ + +#include "zutil.h" +#ifndef Z_SOLO +# include "gzguts.h" +#endif + +#ifndef NO_DUMMY_DECL +struct internal_state {int dummy;}; /* for buggy compilers */ +#endif + +z_const char * const z_errmsg[10] = { +"need dictionary", /* Z_NEED_DICT 2 */ +"stream end", /* Z_STREAM_END 1 */ +"", /* Z_OK 0 */ +"file error", /* Z_ERRNO (-1) */ +"stream error", /* Z_STREAM_ERROR (-2) */ +"data error", /* Z_DATA_ERROR (-3) */ +"insufficient memory", /* Z_MEM_ERROR (-4) */ +"buffer error", /* Z_BUF_ERROR (-5) */ +"incompatible version",/* Z_VERSION_ERROR (-6) */ +""}; + + +const char * ZEXPORT zlibVersion() +{ + return ZLIB_VERSION; +} + +uLong ZEXPORT zlibCompileFlags() +{ + uLong flags; + + flags = 0; + switch ((int)(sizeof(uInt))) { + case 2: break; + case 4: flags += 1; break; + case 8: flags += 2; break; + default: flags += 3; + } + switch ((int)(sizeof(uLong))) { + case 2: break; + case 4: flags += 1 << 2; break; + case 8: flags += 2 << 2; break; + default: flags += 3 << 2; + } + switch ((int)(sizeof(voidpf))) { + case 2: break; + case 4: flags += 1 << 4; break; + case 8: flags += 2 << 4; break; + default: flags += 3 << 4; + } + switch ((int)(sizeof(z_off_t))) { + case 2: break; + case 4: flags += 1 << 6; break; + case 8: flags += 2 << 6; break; + default: flags += 3 << 6; + } +#ifdef DEBUG + flags += 1 << 8; +#endif +#if defined(ASMV) || defined(ASMINF) + flags += 1 << 9; +#endif +#ifdef ZLIB_WINAPI + flags += 1 << 10; +#endif +#ifdef BUILDFIXED + flags += 1 << 12; +#endif +#ifdef DYNAMIC_CRC_TABLE + flags += 1 << 13; +#endif +#ifdef NO_GZCOMPRESS + flags += 1L << 16; +#endif +#ifdef NO_GZIP + flags += 1L << 17; +#endif +#ifdef PKZIP_BUG_WORKAROUND + flags += 1L << 20; +#endif +#ifdef FASTEST + flags += 1L << 21; +#endif +#if defined(STDC) || defined(Z_HAVE_STDARG_H) +# ifdef NO_vsnprintf + flags += 1L << 25; +# ifdef HAS_vsprintf_void + flags += 1L << 26; +# endif +# else +# ifdef HAS_vsnprintf_void + flags += 1L << 26; +# endif +# endif +#else + flags += 1L << 24; +# ifdef NO_snprintf + flags += 1L << 25; +# ifdef HAS_sprintf_void + flags += 1L << 26; +# endif +# else +# ifdef HAS_snprintf_void + flags += 1L << 26; +# endif +# endif +#endif + return flags; +} + +#ifdef DEBUG + +# ifndef verbose +# define verbose 0 +# endif +int ZLIB_INTERNAL z_verbose = verbose; + +void ZLIB_INTERNAL z_error (m) + char *m; +{ + fprintf(stderr, "%s\n", m); + exit(1); +} +#endif + +/* exported to allow conversion of error code to string for compress() and + * uncompress() + */ +const char * ZEXPORT zError(err) + int err; +{ + return ERR_MSG(err); +} + +#if defined(_WIN32_WCE) + /* The Microsoft C Run-Time Library for Windows CE doesn't have + * errno. We define it as a global variable to simplify porting. + * Its value is always 0 and should not be used. + */ + int errno = 0; +#endif + +#ifndef HAVE_MEMCPY + +void ZLIB_INTERNAL zmemcpy(dest, source, len) + Bytef* dest; + const Bytef* source; + uInt len; +{ + if (len == 0) return; + do { + *dest++ = *source++; /* ??? to be unrolled */ + } while (--len != 0); +} + +int ZLIB_INTERNAL zmemcmp(s1, s2, len) + const Bytef* s1; + const Bytef* s2; + uInt len; +{ + uInt j; + + for (j = 0; j < len; j++) { + if (s1[j] != s2[j]) return 2*(s1[j] > s2[j])-1; + } + return 0; +} + +void ZLIB_INTERNAL zmemzero(dest, len) + Bytef* dest; + uInt len; +{ + if (len == 0) return; + do { + *dest++ = 0; /* ??? to be unrolled */ + } while (--len != 0); +} +#endif + +#ifndef Z_SOLO + +#ifdef SYS16BIT + +#ifdef __TURBOC__ +/* Turbo C in 16-bit mode */ + +# define MY_ZCALLOC + +/* Turbo C malloc() does not allow dynamic allocation of 64K bytes + * and farmalloc(64K) returns a pointer with an offset of 8, so we + * must fix the pointer. Warning: the pointer must be put back to its + * original form in order to free it, use zcfree(). + */ + +#define MAX_PTR 10 +/* 10*64K = 640K */ + +local int next_ptr = 0; + +typedef struct ptr_table_s { + voidpf org_ptr; + voidpf new_ptr; +} ptr_table; + +local ptr_table table[MAX_PTR]; +/* This table is used to remember the original form of pointers + * to large buffers (64K). Such pointers are normalized with a zero offset. + * Since MSDOS is not a preemptive multitasking OS, this table is not + * protected from concurrent access. This hack doesn't work anyway on + * a protected system like OS/2. Use Microsoft C instead. + */ + +voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, unsigned items, unsigned size) +{ + voidpf buf = opaque; /* just to make some compilers happy */ + ulg bsize = (ulg)items*size; + + /* If we allocate less than 65520 bytes, we assume that farmalloc + * will return a usable pointer which doesn't have to be normalized. + */ + if (bsize < 65520L) { + buf = farmalloc(bsize); + if (*(ush*)&buf != 0) return buf; + } else { + buf = farmalloc(bsize + 16L); + } + if (buf == NULL || next_ptr >= MAX_PTR) return NULL; + table[next_ptr].org_ptr = buf; + + /* Normalize the pointer to seg:0 */ + *((ush*)&buf+1) += ((ush)((uch*)buf-0) + 15) >> 4; + *(ush*)&buf = 0; + table[next_ptr++].new_ptr = buf; + return buf; +} + +void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr) +{ + int n; + if (*(ush*)&ptr != 0) { /* object < 64K */ + farfree(ptr); + return; + } + /* Find the original pointer */ + for (n = 0; n < next_ptr; n++) { + if (ptr != table[n].new_ptr) continue; + + farfree(table[n].org_ptr); + while (++n < next_ptr) { + table[n-1] = table[n]; + } + next_ptr--; + return; + } + ptr = opaque; /* just to make some compilers happy */ + Assert(0, "zcfree: ptr not found"); +} + +#endif /* __TURBOC__ */ + + +#ifdef M_I86 +/* Microsoft C in 16-bit mode */ + +# define MY_ZCALLOC + +#if (!defined(_MSC_VER) || (_MSC_VER <= 600)) +# define _halloc halloc +# define _hfree hfree +#endif + +voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, uInt items, uInt size) +{ + if (opaque) opaque = 0; /* to make compiler happy */ + return _halloc((long)items, size); +} + +void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr) +{ + if (opaque) opaque = 0; /* to make compiler happy */ + _hfree(ptr); +} + +#endif /* M_I86 */ + +#endif /* SYS16BIT */ + + +#ifndef MY_ZCALLOC /* Any system without a special alloc function */ + +#ifndef STDC +extern voidp malloc OF((uInt size)); +extern voidp calloc OF((uInt items, uInt size)); +extern void free OF((voidpf ptr)); +#endif + +voidpf ZLIB_INTERNAL zcalloc (opaque, items, size) + voidpf opaque; + unsigned items; + unsigned size; +{ + if (opaque) items += size - size; /* make compiler happy */ + return sizeof(uInt) > 2 ? (voidpf)malloc(items * size) : + (voidpf)calloc(items, size); +} + +void ZLIB_INTERNAL zcfree (opaque, ptr) + voidpf opaque; + voidpf ptr; +{ + free(ptr); + if (opaque) return; /* make compiler happy */ +} + +#endif /* MY_ZCALLOC */ + +#endif /* !Z_SOLO */ diff --git a/common/Makefile.common b/common/Makefile.common index 2b2bb2fb..d7e3457f 100644 --- a/common/Makefile.common +++ b/common/Makefile.common @@ -25,6 +25,7 @@ CC = $(CROSS)gcc AS = $(CROSS)as LD = $(CROSS)ld OBJCOPY = $(CROSS)objcopy +GZIP=gzip OBJDIR = obj