[iQue] Match gzip/zlib decompression (#2416)

* [iQue] Match gzip/zlib decompression

Co-authored-by: Anghelo Carvajal <angheloalf95@gmail.com>

* Update missed renames in disassembly

* Fix some formatting

---------

Co-authored-by: Anghelo Carvajal <angheloalf95@gmail.com>

7 files changed, 1039 insertions, 6 deletions

diff --git a/Makefile b/Makefile
index 046fc6802..47f82a7c2 100644
--- a/Makefile
+++ b/Makefile
@@ -569,9 +569,9 @@ ifeq ($(PLATFORM),IQUE)
 # Some files are compiled with EGCS on iQue
 EGCS_O_FILES += $(BUILD_DIR)/src/boot/boot_main.o
 EGCS_O_FILES += $(BUILD_DIR)/src/boot/idle.o
+EGCS_O_FILES += $(BUILD_DIR)/src/boot/inflate.o
 EGCS_O_FILES += $(BUILD_DIR)/src/boot/z_locale.o
 EGCS_O_FILES += $(BUILD_DIR)/src/boot/z_std_dma.o
-EGCS_O_FILES += $(BUILD_DIR)/src/boot/zlib.o
 # EGCS_O_FILES += $(BUILD_DIR)/src/code/z_actor.o
 EGCS_O_FILES += $(BUILD_DIR)/src/code/z_common_data.o
 EGCS_O_FILES += $(BUILD_DIR)/src/code/z_construct.o
diff --git a/include/functions.h b/include/functions.h
index 7a114f73c..092616bce 100644
--- a/include/functions.h
+++ b/include/functions.h
@@ -12,7 +12,11 @@ void ViConfig_UpdateBlack(void);
 void* Yaz0_FirstDMA(void);
 void* Yaz0_NextDMA(u8* curSrcPos);
 void Yaz0_DecompressImpl(u8* src, u8* dst);
+#if !PLATFORM_IQUE
 void Yaz0_Decompress(uintptr_t romStart, u8* dst, size_t size);
+#else
+void gzip_decompress(uintptr_t romStart, u8* dst, size_t size);
+#endif
 void Locale_Init(void);
 void Locale_ResetRegion(void);
 #if DEBUG_FEATURES
diff --git a/spec b/spec
index 4260c5001..f68610d9e 100644
--- a/spec
+++ b/spec
@@ -23,7 +23,11 @@ beginseg
 #endif
     include "$(BUILD_DIR)/src/boot/carthandle.o"
     include "$(BUILD_DIR)/src/boot/z_std_dma.o"
+#if !PLATFORM_IQUE
     include "$(BUILD_DIR)/src/boot/yaz0.o"
+#else
+    include "$(BUILD_DIR)/src/boot/inflate.o"
+#endif
     include "$(BUILD_DIR)/src/boot/z_locale.o"
 #if PLATFORM_N64
     include "$(BUILD_DIR)/src/boot/cic6105.o"
diff --git a/src/boot/inflate.c b/src/boot/inflate.c
new file mode 100644
index 000000000..c0467dd38
--- /dev/null
+++ b/src/boot/inflate.c
@@ -0,0 +1,1003 @@
+/* Not copyrighted 1992 by Mark Adler
+   version c10p1, 10 January 1993 */
+
+/* You can do whatever you like with this source file, though I would
+   prefer that if you modify it and redistribute it that you include
+   comments to that effect with your name and the date.  Thank you.
+   [The history has been moved to the file ChangeLog.]
+ */
+
+/*
+   Inflate deflated (PKZIP's method 8 compressed) data.  The compression
+   method searches for as much of the current string of bytes (up to a
+   length of 258) in the previous 32K bytes.  If it doesn't find any
+   matches (of at least length 3), it codes the next byte.  Otherwise, it
+   codes the length of the matched string and its distance backwards from
+   the current position.  There is a single Huffman code that codes both
+   single bytes (called "literals") and match lengths.  A second Huffman
+   code codes the distance information, which follows a length code.  Each
+   length or distance code actually represents a base value and a number
+   of "extra" (sometimes zero) bits to get to add to the base value.  At
+   the end of each deflated block is a special end-of-block (EOB) literal/
+   length code.  The decoding process is basically: get a literal/length
+   code; if EOB then done; if a literal, emit the decoded byte; if a
+   length then get the distance and emit the referred-to bytes from the
+   sliding window of previously emitted data.
+
+   There are (currently) three kinds of inflate blocks: stored, fixed, and
+   dynamic.  The compressor deals with some chunk of data at a time, and
+   decides which method to use on a chunk-by-chunk basis.  A chunk might
+   typically be 32K or 64K.  If the chunk is uncompressible, then the
+   "stored" method is used.  In this case, the bytes are simply stored as
+   is, eight bits per byte, with none of the above coding.  The bytes are
+   preceded by a count, since there is no longer an EOB code.
+
+   If the data is compressible, then either the fixed or dynamic methods
+   are used.  In the dynamic method, the compressed data is preceded by
+   an encoding of the literal/length and distance Huffman codes that are
+   to be used to decode this block.  The representation is itself Huffman
+   coded, and so is preceded by a description of that code.  These code
+   descriptions take up a little space, and so for small blocks, there is
+   a predefined set of codes, called the fixed codes.  The fixed method is
+   used if the block codes up smaller that way (usually for quite small
+   chunks), otherwise the dynamic method is used.  In the latter case, the
+   codes are customized to the probabilities in the current block, and so
+   can code it much better than the pre-determined fixed codes.
+
+   The Huffman codes themselves are decoded using a multi-level table
+   lookup, in order to maximize the speed of decoding plus the speed of
+   building the decoding tables.  See the comments below that precede the
+   lbits and dbits tuning parameters.
+ */
+
+/*
+   Notes beyond the 1.93a appnote.txt:
+
+   1. Distance pointers never point before the beginning of the output
+      stream.
+   2. Distance pointers can point back across blocks, up to 32k away.
+   3. There is an implied maximum of 7 bits for the bit length table and
+      15 bits for the actual data.
+   4. If only one code exists, then it is encoded using one bit.  (Zero
+      would be more efficient, but perhaps a little confusing.)  If two
+      codes exist, they are coded using one bit each (0 and 1).
+   5. There is no way of sending zero distance codes--a dummy must be
+      sent if there are none.  (History: a pre 2.0 version of PKZIP would
+      store blocks with no distance codes, but this was discovered to be
+      too harsh a criterion.)  Valid only for 1.93a.  2.04c does allow
+      zero distance codes, which is sent as one code of zero bits in
+      length.
+   6. There are up to 286 literal/length codes.  Code 256 represents the
+      end-of-block.  Note however that the static length tree defines
+      288 codes just to fill out the Huffman codes.  Codes 286 and 287
+      cannot be used though, since there is no length base or extra bits
+      defined for them.  Similarly, there are up to 30 distance codes.
+      However, static trees define 32 codes (all 5 bits) to fill out the
+      Huffman codes, but the last two had better not show up in the data.
+   7. Unzip can check dynamic Huffman blocks for complete code sets.
+      The exception is that a single code would not be complete (see #4).
+   8. The five bits following the block type is really the number of
+      literal codes sent minus 257.
+   9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits
+      (1+6+6).  Therefore, to output three times the length, you output
+      three codes (1+1+1), whereas to output four times the same length,
+      you only need two codes (1+3).  Hmm.
+  10. In the tree reconstruction algorithm, Code = Code + Increment
+      only if BitLength(i) is not zero.  (Pretty obvious.)
+  11. Correction: 4 Bits: # of Bit Length codes - 4     (4 - 19)
+  12. Note: length code 284 can represent 227-258, but length code 285
+      really is 258.  The last length deserves its own, short code
+      since it gets used a lot in very redundant files.  The length
+      258 is special since 258 - 3 (the min match length) is 255.
+  13. The literal/length and distance code bit lengths are read as a
+      single stream of lengths.  It is possible (and advantageous) for
+      a repeat code (16, 17, or 18) to go across the boundary between
+      the two sets of lengths.
+ */
+
+#include "ultra64/ultratypes.h"
+#include "libc/stddef.h"
+#include "libc/stdint.h"
+#include "alignment.h"
+#include "attributes.h"
+#include "z64dma.h"
+
+typedef u8 uch;
+typedef u16 ush;
+typedef u32 ulg;
+
+#define Trace(x)
+#define Tracev(x)
+#define Tracevv(x)
+#define Tracecv(c, x)
+
+#define EOF -1
+
+#define WSIZE 0x8000
+#define INBUFSIZ 0x1000
+
+typedef struct GzipFileDescriptor {
+    uintptr_t addr;
+    s32 size;
+} GzipFileDescriptor;
+
+GzipFileDescriptor ifd;
+
+unsigned insize;
+unsigned inptr;
+unsigned outcnt;
+
+static u8 inbuf[INBUFSIZ];
+static u8* output_ptr;
+
+int fill_inbuf(int eof_ok);
+void flush_window(void);
+
+/* Huffman code lookup table entry--this entry is four bytes for machines
+   that have 16-bit pointers (e.g. PC's in the small or medium model).
+   Valid extra bits are 0..13.  e == 15 is EOB (end of block), e == 16
+   means that v is a literal, 16 < e < 32 means that v is a pointer to
+   the next table, which codes e - 16 bits, and lastly e == 99 indicates
+   an unused code.  If a code with e == 99 is looked up, this implies an
+   error in the data. */
+struct huft {
+    uch e; /* number of extra bits or operation */
+    uch b; /* number of bits in this code or subcode */
+    union {
+        ush n;          /* literal, length base, or distance base */
+        struct huft* t; /* pointer to next level of table */
+    } v;
+};
+
+/* Function prototypes */
+int huft_free(struct huft*);
+
+/* The inflate algorithm uses a sliding 32K byte window on the uncompressed
+   stream to find repeated byte strings.  This is implemented here as a
+   circular buffer.  The index is updated simply by incrementing and then
+   and'ing with 0x7fff (32K-1). */
+/* It is left to other modules to supply the 32K area.  It is assumed
+   to be usable as if it were declared "uch slide[32768];" or as just
+   "uch *slide;" and then malloc'ed in the latter case.  The definition
+   must be in unzip.h, included above. */
+/* unsigned wp;             current position in slide */
+#define wp outcnt
+#define flush_output(w) (wp = (w), flush_window())
+
+/* Tables for deflate from PKZIP's appnote.txt. */
+static unsigned border[] = { /* Order of the bit length code lengths */
+                             16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15
+};
+static ush cplens[] = { /* Copy lengths for literal codes 257..285 */
+                        3,  4,  5,  6,  7,  8,  9,  10,  11,  13,  15,  17,  19,  23, 27, 31,
+                        35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0,  0
+};
+/* note: see note #13 above about the 258 in this list. */
+static ush cplext[] = { /* Extra bits for literal codes 257..285 */
+                        0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99
+};                      /* 99==invalid */
+static ush cpdist[] = { /* Copy offsets for distance codes 0..29 */
+                        1,   2,   3,   4,   5,   7,    9,    13,   17,   25,   33,   49,   65,    97,    129,
+                        193, 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, 8193, 12289, 16385, 24577
+};
+static ush cpdext[] = { /* Extra bits for distance codes */
+                        0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13
+};
+
+/* Macros for inflate() bit peeking and grabbing.
+   The usage is:
+
+        NEEDBITS(j)
+        x = b & mask_bits[j];
+        DUMPBITS(j)
+
+   where NEEDBITS makes sure that b has at least j bits in it, and
+   DUMPBITS removes the bits from b.  The macros use the variable k
+   for the number of bits in b.  Normally, b and k are register
+   variables for speed, and are initialized at the beginning of a
+   routine that uses these macros from a global bit buffer and count.
+   The macros also use the variable w, which is a cached copy of wp.
+
+   If we assume that EOB will be the longest code, then we will never
+   ask for bits with NEEDBITS that are beyond the end of the stream.
+   So, NEEDBITS should not read any more bytes than are needed to
+   meet the request.  Then no bytes need to be "returned" to the buffer
+   at the end of the last block.
+
+   However, this assumption is not true for fixed blocks--the EOB code
+   is 7 bits, but the other literal/length codes can be 8 or 9 bits.
+   (The EOB code is shorter than other codes because fixed blocks are
+   generally short.  So, while a block always has an EOB, many other
+   literal/length codes have a significantly lower probability of
+   showing up at all.)  However, by making the first table have a
+   lookup of seven bits, the EOB code will be found in that first
+   lookup, and so will not require that too many bits be pulled from
+   the stream.
+ */
+
+ulg bb;      /* bit buffer */
+unsigned bk; /* bits in bit buffer */
+
+static ush mask_bits[] = { 0x0000, 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff,
+                           0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff };
+
+#define GETBYTE() (inptr < insize ? inbuf[inptr++] : fill_inbuf(0))
+
+#define NEXTBYTE() (uch) GETBYTE()
+#define NEEDBITS(n)                      \
+    {                                    \
+        while (k < (n)) {                \
+            b |= ((ulg)NEXTBYTE()) << k; \
+            k += 8;                      \
+        }                                \
+    }
+#define DUMPBITS(n) \
+    {               \
+        b >>= (n);  \
+        k -= (n);   \
+    }
+
+/*
+   Huffman code decoding is performed using a multi-level table lookup.
+   The fastest way to decode is to simply build a lookup table whose
+   size is determined by the longest code.  However, the time it takes
+   to build this table can also be a factor if the data being decoded
+   is not very long.  The most common codes are necessarily the
+   shortest codes, so those codes dominate the decoding time, and hence
+   the speed.  The idea is you can have a shorter table that decodes the
+   shorter, more probable codes, and then point to subsidiary tables for
+   the longer codes.  The time it costs to decode the longer codes is
+   then traded against the time it takes to make longer tables.
+
+   This results of this trade are in the variables lbits and dbits
+   below.  lbits is the number of bits the first level table for literal/
+   length codes can decode in one step, and dbits is the same thing for
+   the distance codes.  Subsequent tables are also less than or equal to
+   those sizes.  These values may be adjusted either when all of the
+   codes are shorter than that, in which case the longest code length in
+   bits is used, or when the shortest code is *longer* than the requested
+   table size, in which case the length of the shortest code in bits is
+   used.
+
+   There are two different values for the two tables, since they code a
+   different number of possibilities each.  The literal/length table
+   codes 286 possible values, or in a flat code, a little over eight
+   bits.  The distance table codes 30 possible values, or a little less
+   than five bits, flat.  The optimum values for speed end up being
+   about one bit more than those, so lbits is 8+1 and dbits is 5+1.
+   The optimum values may differ though from machine to machine, and
+   possibly even between compilers.  Your mileage may vary.
+ */
+
+static int lbits = 9; /* bits in base literal/length lookup table */
+static int dbits = 6; /* bits in base distance lookup table */
+
+/* If BMAX needs to be larger than 16, then h and x[] should be ulg. */
+#define BMAX 16   /* maximum bit length of any code (16 for explode) */
+#define N_MAX 288 /* maximum number of codes in any set */
+
+unsigned hufts; /* track memory usage */
+
+#define MEMBUFSIZ 0x2000
+
+static u8 gzip_mem_buff[MEMBUFSIZ];
+void* gzip_malloc_addr = gzip_mem_buff;
+s32 gzip_malloc_tmp = 0;
+
+void* gzip_malloc(size_t size) {
+    void* ret;
+
+    gzip_malloc_tmp += size;
+    if (gzip_malloc_tmp > MEMBUFSIZ) {
+        return NULL;
+    }
+
+    ret = gzip_malloc_addr;
+    gzip_malloc_addr = (void*)(((uintptr_t)gzip_malloc_addr) + size);
+    return ret;
+}
+
+void gzip_free(void* ptr) {
+    gzip_malloc_tmp = 0;
+    gzip_malloc_addr = gzip_mem_buff;
+}
+
+/* Given a list of code lengths and a maximum table size, make a set of
+   tables to decode that set of codes.  Return zero on success, one if
+   the given code set is incomplete (the tables are still built in this
+   case), two if the input is invalid (all zero length codes or an
+   oversubscribed set of lengths), and three if not enough memory. */
+int huft_build(unsigned* b,     /* code lengths in bits (all assumed <= BMAX) */
+               unsigned n,      /* number of codes (assumed <= N_MAX) */
+               unsigned s,      /* number of simple-valued codes (0..s-1) */
+               ush* d,          /* list of base values for non-simple codes */
+               ush* e,          /* list of extra bits for non-simple codes */
+               struct huft** t, /* result: starting table */
+               int* m           /* maximum lookup bits, returns actual */
+) {
+    unsigned a;               /* counter for codes of length k */
+    unsigned c[BMAX + 1];     /* bit length count table */
+    unsigned f;               /* i repeats in table every f entries */
+    int g;                    /* maximum code length */
+    int h;                    /* table level */
+    register unsigned i;      /* counter, current code */
+    register unsigned j;      /* counter */
+    register int k;           /* number of bits in current code */
+    int l;                    /* bits per table (returned in m) */
+    register unsigned* p;     /* pointer into c[], b[], or v[] */
+    register struct huft* q;  /* points to current table */
+    struct huft r;            /* table entry for structure assignment */
+    struct huft* u[BMAX];     /* table stack */
+    static unsigned v[N_MAX]; /* values in order of bit length */
+    register int w;           /* bits before this table == (l * h) */
+    unsigned x[BMAX + 1];     /* bit offsets, then code stack */
+    unsigned* xp;             /* pointer into x */
+    int y;                    /* number of dummy codes added */
+    unsigned z;               /* number of entries in current table */
+
+    /* Generate counts for each bit length */
+    for (j = 0; j < BMAX + 1; j++) {
+        c[j] = 0;
+    }
+
+    p = b;
+    i = n;
+    do {
+        Tracecv(*p, (stderr, (n - i >= ' ' && n - i <= '~' ? "%c %d\n" : "0x%x %d\n"), n - i, *p));
+        c[*p]++; /* assume all entries <= BMAX */
+        p++;     /* Can't combine with above line (Solaris bug) */
+    } while (--i);
+    if (c[0] == n) { /* null input--all zero length codes */
+        *t = NULL;
+        *m = 0;
+        return 0;
+    }
+
+    /* Find minimum and maximum length, bound *m by those */
+    l = *m;
+    for (j = 1; j <= BMAX; j++) {
+        if (c[j]) {
+            break;
+        }
+    }
+    k = j; /* minimum code length */
+    if ((unsigned)l < j) {
+        l = j;
+    }
+    for (i = BMAX; i; i--) {
+        if (c[i]) {
+            break;
+        }
+    }
+    g = i; /* maximum code length */
+    if ((unsigned)l > i) {
+        l = i;
+    }
+    *m = l;
+
+    /* Adjust last length count to fill out codes, if needed */
+    for (y = 1 << j; j < i; j++, y <<= 1) {
+        if ((y -= c[j]) < 0) {
+            return 2; /* bad input: more codes than bits */
+        }
+    }
+    if ((y -= c[i]) < 0) {
+        return 2;
+    }
+    c[i] += y;
+
+    /* Generate starting offsets into the value table for each length */
+    x[1] = j = 0;
+    p = c + 1;
+    xp = x + 2;
+    while (--i) { /* note that i == g from above */
+        *xp++ = (j += *p++);
+    }
+
+    /* Make a table of values in order of bit lengths */
+    p = b;
+    i = 0;
+    do {
+        if ((j = *p++) != 0) {
+            v[x[j]++] = i;
+        }
+    } while (++i < n);
+
+    /* Generate the Huffman codes and for each, make the table entries */
+    x[0] = i = 0;              /* first Huffman code is zero */
+    p = v;                     /* grab values in bit order */
+    h = -1;                    /* no tables yet--level -1 */
+    w = -l;                    /* bits decoded == (l * h) */
+    u[0] = (struct huft*)NULL; /* just to keep compilers happy */
+    q = (struct huft*)NULL;    /* ditto */
+    z = 0;                     /* ditto */
+
+    /* go through the bit lengths (k already is bits in shortest code) */
+    for (; k <= g; k++) {
+        a = c[k];
+        while (a--) {
+            /* here i is the Huffman code of length k bits for value *p */
+            /* make tables up to required level */
+            while (k > w + l) {
+                h++;
+                w += l; /* previous table always l bits */
+
+                /* compute minimum size table less than or equal to l bits */
+                z = (z = g - w) > (unsigned)l ? l : z; /* upper limit on table size */
+                if ((f = 1 << (j = k - w)) > a + 1) {  /* try a k-w bit table */
+                                                       /* too few codes for k-w bit table */
+                    f -= a + 1;                        /* deduct codes from patterns left */
+                    xp = c + k;
+                    while (++j < z) { /* try smaller tables up to z bits */
+                        if ((f <<= 1) <= *++xp) {
+                            break; /* enough codes to use up j bits */
+                        }
+                        f -= *xp; /* else deduct codes from patterns */
+                    }
+                }
+                z = 1 << j; /* table entries for j-bit table */
+
+                /* allocate and link in new table */
+                if ((q = (struct huft*)gzip_malloc((z + 1) * sizeof(struct huft))) == (struct huft*)NULL) {
+                    if (h) {
+                        huft_free(u[0]);
+                    }
+                    return 3; /* not enough memory */
+                }
+                hufts += z + 1; /* track memory usage */
+                *t = q + 1;     /* link to list for huft_free() */
+                *(t = &(q->v.t)) = (struct huft*)NULL;
+                u[h] = ++q; /* table starts after link */
+
+                /* connect to last table, if there is one */
+                if (h) {
+                    x[h] = i;            /* save pattern for backing up */
+                    r.b = (uch)l;        /* bits to dump before this table */
+                    r.e = (uch)(16 + j); /* bits in this table */
+                    r.v.t = q;           /* pointer to this table */
+                    j = i >> (w - l);    /* (get around Turbo C bug) */
+                    u[h - 1][j] = r;     /* connect to last table */
+                }
+            }
+
+            /* set up table entry in r */
+            r.b = (uch)(k - w);
+            if (p >= v + n) {
+                r.e = 99; /* out of values--invalid code */
+            } else if (*p < s) {
+                r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */
+                r.v.n = (ush)(*p);               /* simple code is just the value */
+                p++;                             /* one compiler does not like *p++ */
+            } else {
+                r.e = (uch)e[*p - s]; /* non-simple--look up in lists */
+                r.v.n = d[*p++ - s];
+            }
+
+            /* fill code-like entries with r */
+            f = 1 << (k - w);
+            for (j = i >> w; j < z; j += f) {
+                q[j] = r;
+            }
+
+            /* backwards increment the k-bit code i */
+            for (j = 1 << (k - 1); i & j; j >>= 1) {
+                i ^= j;
+            }
+            i ^= j;
+
+            /* backup over finished tables */
+            while ((i & ((1 << w) - 1)) != x[h]) {
+                h--; /* don't need to update q */
+                w -= l;
+            }
+        }
+    }
+
+    /* Return true (1) if we were given an incomplete table */
+    return y != 0 && g != 1;
+}
+
+/* Free the malloc'ed tables T built by huft_build(), which makes a linked
+   list of the tables it made, with the links in a dummy first entry of
+   each table. */
+int huft_free(struct huft* t) {
+    register struct huft *p, *q;
+
+    /* Go through linked list, freeing from the malloced (t[-1]) address. */
+    p = t;
+    while (p != (struct huft*)NULL) {
+        q = (--p)->v.t;
+        gzip_free(p);
+        p = q;
+    }
+    return 0;
+}
+
+/* tl, td:   literal/length and distance decoder tables */
+/* bl, bd:   number of bits decoded by tl[] and td[] */
+/* inflate (decompress) the codes in a deflated (compressed) block.
+   Return an error code or zero if it all goes ok. */
+int inflate_codes(struct huft* tl, struct huft* td, int bl, int bd) {
+    register unsigned e; /* table entry flag/number of extra bits */
+    unsigned n, d;       /* length and index for copy */
+    unsigned w;          /* current window position */
+    struct huft* t;      /* pointer to table entry */
+    unsigned ml, md;     /* masks for bl and bd bits */
+    register ulg b;      /* bit buffer */
+    register unsigned k; /* number of bits in bit buffer */
+    unsigned char* p;
+
+    /* make local copies of globals */
+    b = bb; /* initialize bit buffer */
+    k = bk;
+    w = wp; /* initialize window position */
+
+    /* inflate the coded data */
+    ml = mask_bits[bl]; /* precompute masks for speed */
+    md = mask_bits[bd];
+    for (;;) { /* do until end of block */
+        NEEDBITS((unsigned)bl)
+        if ((e = (t = tl + ((unsigned)b & ml))->e) > 16) {
+            do {
+                if (e == 99) {
+                    return 1;
+                }
+                DUMPBITS(t->b)
+                e -= 16;
+                NEEDBITS(e)
+            } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16);
+        }
+        DUMPBITS(t->b)
+        if (e == 16) { /* then it's a literal */
+            *output_ptr++ = (uch)t->v.n;
+            w++;
+            if (w == WSIZE) {
+                flush_output(w);
+                w = 0;
+            }
+        } else { /* it's an EOB or a length */
+            /* exit if end of block */
+            if (e == 15) {
+                break;
+            }
+
+            /* get length of block to copy */
+            NEEDBITS(e)
+            n = t->v.n + ((unsigned)b & mask_bits[e]);
+            DUMPBITS(e);
+
+            /* decode distance of block to copy */
+            NEEDBITS((unsigned)bd)
+            if ((e = (t = td + ((unsigned)b & md))->e) > 16) {
+                do {
+                    if (e == 99) {
+                        return 1;
+                    }
+                    DUMPBITS(t->b)
+                    e -= 16;
+                    NEEDBITS(e)
+                } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16);
+            }
+            DUMPBITS(t->b)
+            NEEDBITS(e)
+            d = w - t->v.n - ((unsigned)b & mask_bits[e]);
+            DUMPBITS(e)
+            Tracevv((stderr, "\\[%d,%d]", w - d, n));
+
+            /* do the copy */
+            p = output_ptr + d - w;
+            do {
+                *output_ptr++ = *p++;
+                w++;
+                if (w == WSIZE) {
+                    flush_output(w);
+                    w = 0;
+                }
+                d++;
+                n--;
+            } while (n != 0);
+        }
+    }
+
+    /* restore the globals from the locals */
+    wp = w; /* restore global window pointer */
+    bb = b; /* restore global bit buffer */
+    bk = k;
+
+    /* done */
+    return 0;
+}
+
+/* "decompress" an inflated type 0 (stored) block. */
+int inflate_stored(void) {
+    unsigned n;          /* number of bytes in block */
+    unsigned w;          /* current window position */
+    register ulg b;      /* bit buffer */
+    register unsigned k; /* number of bits in bit buffer */
+
+    /* make local copies of globals */
+    b = bb; /* initialize bit buffer */
+    k = bk;
+    w = wp; /* initialize window position */
+
+    /* go to byte boundary */
+    n = k & 7;
+    DUMPBITS(n);
+
+    /* get the length and its complement */
+    NEEDBITS(16)
+    n = ((unsigned)b & 0xffff);
+    DUMPBITS(16)
+    NEEDBITS(16)
+    if (n != (unsigned)((~b) & 0xffff)) {
+        return 1; /* error in compressed data */
+    }
+    DUMPBITS(16)
+
+    /* read and output the compressed data */
+    while (n--) {
+        NEEDBITS(8)
+        *output_ptr++ = (uch)b;
+        w++;
+        if (w == WSIZE) {
+            flush_output(w);
+            w = 0;
+        }
+        DUMPBITS(8)
+    }
+
+    /* restore the globals from the locals */
+    wp = w; /* restore global window pointer */
+    bb = b; /* restore global bit buffer */
+    bk = k;
+    return 0;
+}
+
+/* decompress an inflated type 1 (fixed Huffman codes) block.  We should
+   either replace this with a custom decoder, or at least precompute the
+   Huffman tables. */
+int inflate_fixed(void) {
+    int i;                  /* temporary variable */
+    struct huft* tl;        /* literal/length code table */
+    struct huft* td;        /* distance code table */
+    int bl;                 /* lookup bits for tl */
+    int bd;                 /* lookup bits for td */
+    static unsigned l[288]; /* length list for huft_build */
+
+    /* set up literal table */
+    for (i = 0; i < 144; i++) {
+        l[i] = 8;
+    }
+    for (; i < 256; i++) {
+        l[i] = 9;
+    }
+    for (; i < 280; i++) {
+        l[i] = 7;
+    }
+    for (; i < 288; i++) { /* make a complete, but wrong code set */
+        l[i] = 8;
+    }
+    bl = 7;
+    if ((i = huft_build(l, 288, 257, cplens, cplext, &tl, &bl)) != 0) {
+        return i;
+    }
+
+    /* set up distance table */
+    for (i = 0; i < 30; i++) { /* make an incomplete code set */
+        l[i] = 5;
+    }
+    bd = 5;
+    if ((i = huft_build(l, 30, 0, cpdist, cpdext, &td, &bd)) > 1) {
+        huft_free(tl);
+        return i;
+    }
+
+    /* decompress until an end-of-block code */
+    if (inflate_codes(tl, td, bl, bd)) {
+        return 1;
+    }
+
+    /* free the decoding tables, return */
+    huft_free(td);
+    huft_free(tl);
+    return 0;
+}
+
+/* decompress an inflated type 2 (dynamic Huffman codes) block. */
+int inflate_dynamic(void) {
+    int i; /* temporary variables */
+    unsigned j;
+    unsigned l;                   /* last length */
+    unsigned m;                   /* mask for bit lengths table */
+    unsigned n;                   /* number of lengths to get */
+    UNUSED unsigned w;            /* current window position */
+    struct huft* tl;              /* literal/length code table */
+    struct huft* td;              /* distance code table */
+    int bl;                       /* lookup bits for tl */
+    int bd;                       /* lookup bits for td */
+    unsigned nb;                  /* number of bit length codes */
+    unsigned nl;                  /* number of literal/length codes */
+    unsigned nd;                  /* number of distance codes */
+    static unsigned ll[288 + 32]; /* literal/length and distance code lengths */
+    register ulg b;               /* bit buffer */
+    register unsigned k;          /* number of bits in bit buffer */
+
+    /* make local bit buffer */
+    b = bb;
+    k = bk;
+    w = wp;
+
+    /* read in table lengths */
+    NEEDBITS(5)
+    nl = 257 + ((unsigned)b & 0x1f); /* number of literal/length codes */
+    DUMPBITS(5)
+    NEEDBITS(5)
+    nd = 1 + ((unsigned)b & 0x1f); /* number of distance codes */
+    DUMPBITS(5)
+    NEEDBITS(4)
+    nb = 4 + ((unsigned)b & 0xf); /* number of bit length codes */
+    DUMPBITS(4)
+    if (nl > 288 || nd > 32) {
+        return 1; /* bad lengths */
+    }
+
+    /* read in bit-length-code lengths */
+    for (j = 0; j < nb; j++) {
+        NEEDBITS(3)
+        ll[border[j]] = (unsigned)b & 7;
+        DUMPBITS(3)
+    }
+    for (; j < 19; j++) {
+        ll[border[j]] = 0;
+    }
+
+    /* build decoding table for trees--single level, 7 bit lookup */
+    bl = 7;
+    if ((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl)) != 0) {
+        if (i == 1) {
+            huft_free(tl);
+        }
+        return i; /* incomplete code set */
+    }
+
+    /* read in literal and distance code lengths */
+    n = nl + nd;
+    m = mask_bits[bl];
+    i = l = 0;
+    while ((unsigned)i < n) {
+        NEEDBITS((unsigned)bl)
+        j = (td = tl + ((unsigned)b & m))->b;
+        DUMPBITS(j)
+        j = td->v.n;
+        if (j < 16) {         /* length of code in bits (0..15) */
+            ll[i++] = l = j;  /* save last length in l */
+        } else if (j == 16) { /* repeat last length 3 to 6 times */
+            NEEDBITS(2)
+            j = 3 + ((unsigned)b & 3);
+            DUMPBITS(2)
+            if ((unsigned)i + j > n) {
+                return 1;
+            }
+            while (j--) {
+                ll[i++] = l;
+            }
+        } else if (j == 17) { /* 3 to 10 zero length codes */
+            NEEDBITS(3)
+            j = 3 + ((unsigned)b & 7);
+            DUMPBITS(3)
+            if ((unsigned)i + j > n) {
+                return 1;
+            }
+            while (j--) {
+                ll[i++] = 0;
+            }
+            l = 0;
+        } else { /* j == 18: 11 to 138 zero length codes */
+            NEEDBITS(7)
+            j = 11 + ((unsigned)b & 0x7f);
+            DUMPBITS(7)
+            if ((unsigned)i + j > n) {
+                return 1;
+            }
+            while (j--) {
+                ll[i++] = 0;
+            }
+            l = 0;
+        }
+    }
+
+    /* free decoding table for trees */
+    huft_free(tl);
+
+    /* restore the global bit buffer */
+    bb = b;
+    bk = k;
+
+    /* build the decoding tables for literal/length and distance codes */
+    bl = lbits;
+    if ((i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl)) != 0) {
+        if (i == 1) {
+            Trace((stderr, " incomplete literal tree\n"));
+            huft_free(tl);
+        }
+        return i; /* incomplete code set */
+    }
+    bd = dbits;
+    if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0) {
+        if (i == 1) {
+            Trace((stderr, " incomplete distance tree\n"));
+            i = 0;
+        }
+    }
+
+    /* decompress until an end-of-block code */
+    if (inflate_codes(tl, td, bl, bd) != 0) {
+        return 1;
+    }
+
+    /* free the decoding tables */
+    huft_free(td);
+    huft_free(tl);
+
+    return 0;
+}
+
+/* decompress an inflated block */
+/* E is the last block flag */
+int inflate_block(int* e) {
+    unsigned t;          /* block type */
+    UNUSED unsigned w;   /* current window position */
+    register ulg b;      /* bit buffer */
+    register unsigned k; /* number of bits in bit buffer */
+
+    /* make local bit buffer */
+    b = bb;
+    k = bk;
+    w = wp;
+
+    /* read in last block bit */
+    NEEDBITS(1)
+    *e = (int)b & 1;
+    DUMPBITS(1)
+
+    /* read in block type */
+    NEEDBITS(2)
+    t = (unsigned)b & 3;
+    DUMPBITS(2)
+
+    /* restore the global bit buffer */
+    bb = b;
+    bk = k;
+
+    /* inflate that block type */
+    if (t == 2) {
+        return inflate_dynamic();
+    }
+    if (t == 0) {
+        return inflate_stored();
+    }
+    if (t == 1) {
+        return inflate_fixed();
+    }
+
+    /* bad block type */
+    return 2;
+}
+
+/* decompress an inflated entry */
+int inflate(void) {
+    int e;      /* last block flag */
+    int r;      /* result code */
+    unsigned h; /* maximum struct huft's malloc'ed */
+
+    /* initialize window, bit buffer */
+    wp = 0;
+    bk = 0;
+    bb = 0;
+
+    gzip_malloc_tmp = 0;
+    gzip_malloc_addr = gzip_mem_buff;
+
+    /* decompress until the last block */
+    h = 0;
+    do {
+        hufts = 0;
+        if ((r = inflate_block(&e)) != 0) {
+            return r;
+        }
+        if (hufts > h) {
+            h = hufts;
+        }
+    } while (!e);
+
+    /* Undo too much lookahead. The next read will be byte aligned so we
+     * can discard unused bits in the last meaningful byte.
+     */
+    while (bk >= 8) {
+        bk -= 8;
+        inptr--;
+    }
+
+    /* flush out slide */
+    flush_output(wp);
+
+    /* return success */
+    Trace((stderr, "<%u> ", h));
+    return 0;
+}
+
+size_t gzip_read(GzipFileDescriptor* romInput, void* dst, size_t blockSize) {
+    size_t alignedSize;
+
+    if (blockSize > (size_t)romInput->size) {
+        blockSize = romInput->size;
+    }
+
+    alignedSize = ALIGN8(blockSize);
+    if (alignedSize > 0) {
+        DmaMgr_DmaRomToRam(romInput->addr, dst, alignedSize);
+    }
+
+    romInput->size -= alignedSize;
+    romInput->addr += alignedSize;
+    if (romInput->size < 0) {
+        romInput->size = 0;
+    }
+
+    return blockSize;
+}
+
+int unzip(void) {
+    int ret = inflate();
+
+    if (ret == 3) {
+        return -1;
+    }
+
+    if (ret != 0) {
+        return -1;
+    }
+
+    return 0;
+}
+
+void clear_bufs(void) {
+    insize = inptr = 0;
+}
+
+int fill_inbuf(int eof_ok) {
+    int len;
+
+    /* Read as much as possible */
+    insize = 0;
+    do {
+        len = gzip_read(&ifd, (char*)inbuf + insize, INBUFSIZ - insize);
+        if (len == 0 || len == -1) {
+            break;
+        }
+        insize += len;
+    } while (insize < INBUFSIZ);
+
+    if (insize == 0) {
+        if (eof_ok) {
+            return EOF;
+        }
+    }
+
+    inptr = 1;
+    return inbuf[0];
+}
+
+void flush_window(void) {
+    outcnt = 0;
+}
+
+void gzip_decompress(uintptr_t romStart, u8* dst, size_t size) {
+    ifd.addr = romStart;
+    ifd.size = size;
+
+    output_ptr = dst;
+
+    clear_bufs();
+    unzip();
+}
diff --git a/src/boot/z_std_dma.c b/src/boot/z_std_dma.c
index b05b188c6..ea934a497 100644
--- a/src/boot/z_std_dma.c
+++ b/src/boot/z_std_dma.c
@@ -441,7 +441,13 @@ void DmaMgr_ProcessRequest(DmaRequest* req) {
                 // Reduce the thread priority and decompress the file, the decompression routine handles the DMA
                 // in chunks. Restores the thread priority when done.
                 osSetThreadPri(NULL, THREAD_PRI_DMAMGR_LOW);
+
+#if !PLATFORM_IQUE
                 Yaz0_Decompress(romStart, ram, romSize);
+#else
+                gzip_decompress(romStart, ram, romSize);
+#endif
+
                 osSetThreadPri(NULL, THREAD_PRI_DMAMGR);
                 found = true;
 
diff --git a/tools/disasm/ique-cn/files_boot.csv b/tools/disasm/ique-cn/files_boot.csv
index da3d146a1..e4d69b501 100644
--- a/tools/disasm/ique-cn/files_boot.csv
+++ b/tools/disasm/ique-cn/files_boot.csv
@@ -3,7 +3,7 @@ offset,vram,.text
 140,80000590,src/boot/idle
 390,800007E0,src/boot/viconfig
 4D0,80000920,src/boot/z_std_dma
-B50,80000FA0,src/boot/zlib
+B50,80000FA0,src/boot/inflate
 2830,80002C80,src/boot/z_locale
 2870,80002CC0,src/boot/is_debug
 2890,80002CE0,src/boot/driverominit
@@ -96,7 +96,7 @@ offset,vram,.data
 98F0,80009D40,src/boot/viconfig
 9910,80009D60,src/boot/carthandle
 9920,80009D70,src/boot/z_std_dma
-9930,80009D80,src/boot/zlib
+9930,80009D80,src/boot/inflate
 9AB0,80009F00,src/boot/z_locale
 9AC0,80009F10,src/boot/driverominit
 9AD0,80009F20,src/libu64/stackcheck
@@ -133,7 +133,7 @@ A750,8000ABA0,data/boot_common_8000ABA0
 A7A0,8000ABF0,src/boot/boot_main
 B190,8000B5E0,src/boot/idle
 BD90,8000C1E0,src/boot/z_std_dma
-C500,8000C950,src/boot/zlib
+C500,8000C950,src/boot/inflate
 10310,80010760,src/boot/driverominit
 10390,800107E0,src/libultra/io/vimgr
 115B0,80011A00,src/libultra/io/pimgr
diff --git a/tools/disasm/ique-cn/functions.txt b/tools/disasm/ique-cn/functions.txt
index b10ad3873..41abd66a7 100644
--- a/tools/disasm/ique-cn/functions.txt
+++ b/tools/disasm/ique-cn/functions.txt
@@ -15,6 +15,22 @@ DmaMgr_ThreadEntry = 0x80000D60; // type:func
 DmaMgr_RequestAsync = 0x80000DC4; // type:func
 DmaMgr_RequestSync = 0x80000E14; // type:func
 DmaMgr_Init = 0x80000EAC; // type:func
+gzip_malloc = 0x80000FA0; // type:func
+gzip_free = 0x80000FE8; // type:func
+huft_build = 0x80001004; // type:func
+huft_free = 0x800015E8; // type:func
+inflate_codes = 0x8000162C; // type:func
+inflate_stored = 0x80001BCC; // type:func
+inflate_fixed = 0x80001E4C; // type:func
+inflate_dynamic = 0x80002018; // type:func
+inflate_block = 0x80002808; // type:func
+inflate = 0x800029B0; // type:func
+gzip_read = 0x80002A88; // type:func
+unzip = 0x80002B14; // type:func
+clear_bufs = 0x80002B50; // type:func
+fill_inbuf = 0x80002B68; // type:func
+flush_window = 0x80002C2C; // type:func
+gzip_decompress = 0x80002C3C; // type:func
 Locale_Init = 0x80002C80; // type:func
 Locale_ResetRegion = 0x80002CB4; // type:func
 osSyncPrintfUnused = 0x80002CC0; // type:func
@@ -10285,7 +10301,7 @@ EnGe1_Init = 0x80A8EFD0; // type:func
 EnGe1_Destroy = 0x80A8F294; // type:func
 EnGe1_SetTalkAction = 0x80A8F2C0; // type:func
 EnGe1_SetAnimationIdle = 0x80A8F3A0; // type:func
-EnGe1_CheckCarpentersFreed = 0x80A8F424; // type:func
+EnGe1_CheckAllCarpentersRescued = 0x80A8F424; // type:func
 EnGe1_KickPlayer = 0x80A8F460; // type:func
 EnGe1_SpotPlayer = 0x80A8F540; // type:func
 EnGe1_WatchForPlayerFrontOnly = 0x80A8F5A0; // type:func
@@ -11822,7 +11838,7 @@ EnGe2_Init = 0x80B25578; // type:func
 EnGe2_Destroy = 0x80B25790; // type:func
 Ge2_DetectPlayerInAction = 0x80B257BC; // type:func
 Ge2_DetectPlayerInUpdate = 0x80B25868; // type:func
-EnGe2_CheckCarpentersFreed = 0x80B25998; // type:func
+EnGe2_CheckAllCarpentersRescued = 0x80B25998; // type:func
 EnGe2_CaptureClose = 0x80B259C4; // type:func
 EnGe2_CaptureCharge = 0x80B25A98; // type:func
 EnGe2_CaptureTurn = 0x80B25BCC; // type:func