Browse Source

zlib: backport security fix for a reproducible crash in compressor

Tavis has just reported, that he was recently trying to track down a
reproducible crash in a compressor. Believe it or not, it really was a
bug in zlib-1.2.11 when compressing (not decompressing!) certain inputs.

Tavis has reported it upstream, but it turns out the issue has been
public since 2018, but the patch never made it into a release. As far as
he knows, nobody ever assigned it a CVE.

Runtime tested on ipq40xx/glinet-b1300 and mvebu/turris-omnia.

Suggested-by: Tavis Ormandy <taviso@gmail.com>
References: https://www.openwall.com/lists/oss-security/2022/03/24/1
Signed-off-by: Petr Štetiar <ynezz@true.cz>
(cherry picked from commit b3aa2909a79aeff20d594160b207a89dc807c033)
(cherry picked from commit 3965dda0fa70dc9408f1a2e55a3ddefde78bd50e)
(cherry picked from commit f65edc9b990c2bcc10c9e9fca29253adc6fe316d)
Petr Štetiar 2 years ago
parent
commit
3e106e312a

+ 1 - 1
package/libs/zlib/Makefile

@@ -9,7 +9,7 @@ include $(TOPDIR)/rules.mk
 
 PKG_NAME:=zlib
 PKG_VERSION:=1.2.11
-PKG_RELEASE:=3
+PKG_RELEASE:=4
 
 PKG_SOURCE:=$(PKG_NAME)-$(PKG_VERSION).tar.xz
 PKG_SOURCE_URL:=@SF/libpng http://www.zlib.net

+ 343 - 0
package/libs/zlib/patches/006-fix-compressor-crash-on-certain-inputs.patch

@@ -0,0 +1,343 @@
+From 5c44459c3b28a9bd3283aaceab7c615f8020c531 Mon Sep 17 00:00:00 2001
+From: Mark Adler <madler@alumni.caltech.edu>
+Date: Tue, 17 Apr 2018 22:09:22 -0700
+Subject: [PATCH] Fix a bug that can crash deflate on some input when using
+ Z_FIXED.
+
+This bug was reported by Danilo Ramos of Eideticom, Inc. It has
+lain in wait 13 years before being found! The bug was introduced
+in zlib 1.2.2.2, with the addition of the Z_FIXED option. That
+option forces the use of fixed Huffman codes. For rare inputs with
+a large number of distant matches, the pending buffer into which
+the compressed data is written can overwrite the distance symbol
+table which it overlays. That results in corrupted output due to
+invalid distances, and can result in out-of-bound accesses,
+crashing the application.
+
+The fix here combines the distance buffer and literal/length
+buffers into a single symbol buffer. Now three bytes of pending
+buffer space are opened up for each literal or length/distance
+pair consumed, instead of the previous two bytes. This assures
+that the pending buffer cannot overwrite the symbol table, since
+the maximum fixed code compressed length/distance is 31 bits, and
+since there are four bytes of pending space for every three bytes
+of symbol space.
+---
+ deflate.c | 74 ++++++++++++++++++++++++++++++++++++++++---------------
+ deflate.h | 25 +++++++++----------
+ trees.c   | 50 +++++++++++--------------------------
+ 3 files changed, 79 insertions(+), 70 deletions(-)
+
+diff --git a/deflate.c b/deflate.c
+index 425babc00..19cba873a 100644
+--- a/deflate.c
++++ b/deflate.c
+@@ -255,11 +255,6 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+     int wrap = 1;
+     static const char my_version[] = ZLIB_VERSION;
+ 
+-    ushf *overlay;
+-    /* We overlay pending_buf and d_buf+l_buf. This works since the average
+-     * output size for (length,distance) codes is <= 24 bits.
+-     */
+-
+     if (version == Z_NULL || version[0] != my_version[0] ||
+         stream_size != sizeof(z_stream)) {
+         return Z_VERSION_ERROR;
+@@ -329,9 +324,47 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+ 
+     s->lit_bufsize = 1 << (memLevel + 6); /* 16K elements by default */
+ 
+-    overlay = (ushf *) ZALLOC(strm, s->lit_bufsize, sizeof(ush)+2);
+-    s->pending_buf = (uchf *) overlay;
+-    s->pending_buf_size = (ulg)s->lit_bufsize * (sizeof(ush)+2L);
++    /* We overlay pending_buf and sym_buf. This works since the average size
++     * for length/distance pairs over any compressed block is assured to be 31
++     * bits or less.
++     *
++     * Analysis: The longest fixed codes are a length code of 8 bits plus 5
++     * extra bits, for lengths 131 to 257. The longest fixed distance codes are
++     * 5 bits plus 13 extra bits, for distances 16385 to 32768. The longest
++     * possible fixed-codes length/distance pair is then 31 bits total.
++     *
++     * sym_buf starts one-fourth of the way into pending_buf. So there are
++     * three bytes in sym_buf for every four bytes in pending_buf. Each symbol
++     * in sym_buf is three bytes -- two for the distance and one for the
++     * literal/length. As each symbol is consumed, the pointer to the next
++     * sym_buf value to read moves forward three bytes. From that symbol, up to
++     * 31 bits are written to pending_buf. The closest the written pending_buf
++     * bits gets to the next sym_buf symbol to read is just before the last
++     * code is written. At that time, 31*(n-2) bits have been written, just
++     * after 24*(n-2) bits have been consumed from sym_buf. sym_buf starts at
++     * 8*n bits into pending_buf. (Note that the symbol buffer fills when n-1
++     * symbols are written.) The closest the writing gets to what is unread is
++     * then n+14 bits. Here n is lit_bufsize, which is 16384 by default, and
++     * can range from 128 to 32768.
++     *
++     * Therefore, at a minimum, there are 142 bits of space between what is
++     * written and what is read in the overlain buffers, so the symbols cannot
++     * be overwritten by the compressed data. That space is actually 139 bits,
++     * due to the three-bit fixed-code block header.
++     *
++     * That covers the case where either Z_FIXED is specified, forcing fixed
++     * codes, or when the use of fixed codes is chosen, because that choice
++     * results in a smaller compressed block than dynamic codes. That latter
++     * condition then assures that the above analysis also covers all dynamic
++     * blocks. A dynamic-code block will only be chosen to be emitted if it has
++     * fewer bits than a fixed-code block would for the same set of symbols.
++     * Therefore its average symbol length is assured to be less than 31. So
++     * the compressed data for a dynamic block also cannot overwrite the
++     * symbols from which it is being constructed.
++     */
++
++    s->pending_buf = (uchf *) ZALLOC(strm, s->lit_bufsize, 4);
++    s->pending_buf_size = (ulg)s->lit_bufsize * 4;
+ 
+     if (s->window == Z_NULL || s->prev == Z_NULL || s->head == Z_NULL ||
+         s->pending_buf == Z_NULL) {
+@@ -340,8 +373,12 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+         deflateEnd (strm);
+         return Z_MEM_ERROR;
+     }
+-    s->d_buf = overlay + s->lit_bufsize/sizeof(ush);
+-    s->l_buf = s->pending_buf + (1+sizeof(ush))*s->lit_bufsize;
++    s->sym_buf = s->pending_buf + s->lit_bufsize;
++    s->sym_end = (s->lit_bufsize - 1) * 3;
++    /* We avoid equality with lit_bufsize*3 because of wraparound at 64K
++     * on 16 bit machines and because stored blocks are restricted to
++     * 64K-1 bytes.
++     */
+ 
+     s->level = level;
+     s->strategy = strategy;
+@@ -552,7 +589,7 @@ int ZEXPORT deflatePrime (strm, bits, value)
+ 
+     if (deflateStateCheck(strm)) return Z_STREAM_ERROR;
+     s = strm->state;
+-    if ((Bytef *)(s->d_buf) < s->pending_out + ((Buf_size + 7) >> 3))
++    if (s->sym_buf < s->pending_out + ((Buf_size + 7) >> 3))
+         return Z_BUF_ERROR;
+     do {
+         put = Buf_size - s->bi_valid;
+@@ -1113,7 +1150,6 @@ int ZEXPORT deflateCopy (dest, source)
+ #else
+     deflate_state *ds;
+     deflate_state *ss;
+-    ushf *overlay;
+ 
+ 
+     if (deflateStateCheck(source) || dest == Z_NULL) {
+@@ -1133,8 +1169,7 @@ int ZEXPORT deflateCopy (dest, source)
+     ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte));
+     ds->prev   = (Posf *)  ZALLOC(dest, ds->w_size, sizeof(Pos));
+     ds->head   = (Posf *)  ZALLOC(dest, ds->hash_size, sizeof(Pos));
+-    overlay = (ushf *) ZALLOC(dest, ds->lit_bufsize, sizeof(ush)+2);
+-    ds->pending_buf = (uchf *) overlay;
++    ds->pending_buf = (uchf *) ZALLOC(dest, ds->lit_bufsize, 4);
+ 
+     if (ds->window == Z_NULL || ds->prev == Z_NULL || ds->head == Z_NULL ||
+         ds->pending_buf == Z_NULL) {
+@@ -1148,8 +1183,7 @@ int ZEXPORT deflateCopy (dest, source)
+     zmemcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size);
+ 
+     ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf);
+-    ds->d_buf = overlay + ds->lit_bufsize/sizeof(ush);
+-    ds->l_buf = ds->pending_buf + (1+sizeof(ush))*ds->lit_bufsize;
++    ds->sym_buf = ds->pending_buf + ds->lit_bufsize;
+ 
+     ds->l_desc.dyn_tree = ds->dyn_ltree;
+     ds->d_desc.dyn_tree = ds->dyn_dtree;
+@@ -1925,7 +1959,7 @@ local block_state deflate_fast(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+@@ -2056,7 +2090,7 @@ local block_state deflate_slow(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+@@ -2131,7 +2165,7 @@ local block_state deflate_rle(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+@@ -2170,7 +2204,7 @@ local block_state deflate_huff(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+diff --git a/deflate.h b/deflate.h
+index 23ecdd312..d4cf1a98b 100644
+--- a/deflate.h
++++ b/deflate.h
+@@ -217,7 +217,7 @@ typedef struct internal_state {
+     /* Depth of each subtree used as tie breaker for trees of equal frequency
+      */
+ 
+-    uchf *l_buf;          /* buffer for literals or lengths */
++    uchf *sym_buf;        /* buffer for distances and literals/lengths */
+ 
+     uInt  lit_bufsize;
+     /* Size of match buffer for literals/lengths.  There are 4 reasons for
+@@ -239,13 +239,8 @@ typedef struct internal_state {
+      *   - I can't count above 4
+      */
+ 
+-    uInt last_lit;      /* running index in l_buf */
+-
+-    ushf *d_buf;
+-    /* Buffer for distances. To simplify the code, d_buf and l_buf have
+-     * the same number of elements. To use different lengths, an extra flag
+-     * array would be necessary.
+-     */
++    uInt sym_next;      /* running index in sym_buf */
++    uInt sym_end;       /* symbol table full when sym_next reaches this */
+ 
+     ulg opt_len;        /* bit length of current block with optimal trees */
+     ulg static_len;     /* bit length of current block with static trees */
+@@ -325,20 +320,22 @@ void ZLIB_INTERNAL _tr_stored_block OF((deflate_state *s, charf *buf,
+ 
+ # define _tr_tally_lit(s, c, flush) \
+   { uch cc = (c); \
+-    s->d_buf[s->last_lit] = 0; \
+-    s->l_buf[s->last_lit++] = cc; \
++    s->sym_buf[s->sym_next++] = 0; \
++    s->sym_buf[s->sym_next++] = 0; \
++    s->sym_buf[s->sym_next++] = cc; \
+     s->dyn_ltree[cc].Freq++; \
+-    flush = (s->last_lit == s->lit_bufsize-1); \
++    flush = (s->sym_next == s->sym_end); \
+    }
+ # define _tr_tally_dist(s, distance, length, flush) \
+   { uch len = (uch)(length); \
+     ush dist = (ush)(distance); \
+-    s->d_buf[s->last_lit] = dist; \
+-    s->l_buf[s->last_lit++] = len; \
++    s->sym_buf[s->sym_next++] = dist; \
++    s->sym_buf[s->sym_next++] = dist >> 8; \
++    s->sym_buf[s->sym_next++] = len; \
+     dist--; \
+     s->dyn_ltree[_length_code[len]+LITERALS+1].Freq++; \
+     s->dyn_dtree[d_code(dist)].Freq++; \
+-    flush = (s->last_lit == s->lit_bufsize-1); \
++    flush = (s->sym_next == s->sym_end); \
+   }
+ #else
+ # define _tr_tally_lit(s, c, flush) flush = _tr_tally(s, 0, c)
+diff --git a/trees.c b/trees.c
+index 4f4a65011..decaeb7c3 100644
+--- a/trees.c
++++ b/trees.c
+@@ -416,7 +416,7 @@ local void init_block(s)
+ 
+     s->dyn_ltree[END_BLOCK].Freq = 1;
+     s->opt_len = s->static_len = 0L;
+-    s->last_lit = s->matches = 0;
++    s->sym_next = s->matches = 0;
+ }
+ 
+ #define SMALLEST 1
+@@ -948,7 +948,7 @@ void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last)
+ 
+         Tracev((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u ",
+                 opt_lenb, s->opt_len, static_lenb, s->static_len, stored_len,
+-                s->last_lit));
++                s->sym_next / 3));
+ 
+         if (static_lenb <= opt_lenb) opt_lenb = static_lenb;
+ 
+@@ -1017,8 +1017,9 @@ int ZLIB_INTERNAL _tr_tally (s, dist, lc)
+     unsigned dist;  /* distance of matched string */
+     unsigned lc;    /* match length-MIN_MATCH or unmatched char (if dist==0) */
+ {
+-    s->d_buf[s->last_lit] = (ush)dist;
+-    s->l_buf[s->last_lit++] = (uch)lc;
++    s->sym_buf[s->sym_next++] = dist;
++    s->sym_buf[s->sym_next++] = dist >> 8;
++    s->sym_buf[s->sym_next++] = lc;
+     if (dist == 0) {
+         /* lc is the unmatched char */
+         s->dyn_ltree[lc].Freq++;
+@@ -1033,30 +1034,7 @@ int ZLIB_INTERNAL _tr_tally (s, dist, lc)
+         s->dyn_ltree[_length_code[lc]+LITERALS+1].Freq++;
+         s->dyn_dtree[d_code(dist)].Freq++;
+     }
+-
+-#ifdef TRUNCATE_BLOCK
+-    /* Try to guess if it is profitable to stop the current block here */
+-    if ((s->last_lit & 0x1fff) == 0 && s->level > 2) {
+-        /* Compute an upper bound for the compressed length */
+-        ulg out_length = (ulg)s->last_lit*8L;
+-        ulg in_length = (ulg)((long)s->strstart - s->block_start);
+-        int dcode;
+-        for (dcode = 0; dcode < D_CODES; dcode++) {
+-            out_length += (ulg)s->dyn_dtree[dcode].Freq *
+-                (5L+extra_dbits[dcode]);
+-        }
+-        out_length >>= 3;
+-        Tracev((stderr,"\nlast_lit %u, in %ld, out ~%ld(%ld%%) ",
+-               s->last_lit, in_length, out_length,
+-               100L - out_length*100L/in_length));
+-        if (s->matches < s->last_lit/2 && out_length < in_length/2) return 1;
+-    }
+-#endif
+-    return (s->last_lit == s->lit_bufsize-1);
+-    /* We avoid equality with lit_bufsize because of wraparound at 64K
+-     * on 16 bit machines and because stored blocks are restricted to
+-     * 64K-1 bytes.
+-     */
++    return (s->sym_next == s->sym_end);
+ }
+ 
+ /* ===========================================================================
+@@ -1069,13 +1047,14 @@ local void compress_block(s, ltree, dtree)
+ {
+     unsigned dist;      /* distance of matched string */
+     int lc;             /* match length or unmatched char (if dist == 0) */
+-    unsigned lx = 0;    /* running index in l_buf */
++    unsigned sx = 0;    /* running index in sym_buf */
+     unsigned code;      /* the code to send */
+     int extra;          /* number of extra bits to send */
+ 
+-    if (s->last_lit != 0) do {
+-        dist = s->d_buf[lx];
+-        lc = s->l_buf[lx++];
++    if (s->sym_next != 0) do {
++        dist = s->sym_buf[sx++] & 0xff;
++        dist += (unsigned)(s->sym_buf[sx++] & 0xff) << 8;
++        lc = s->sym_buf[sx++];
+         if (dist == 0) {
+             send_code(s, lc, ltree); /* send a literal byte */
+             Tracecv(isgraph(lc), (stderr," '%c' ", lc));
+@@ -1100,11 +1079,10 @@ local void compress_block(s, ltree, dtree)
+             }
+         } /* literal or match pair ? */
+ 
+-        /* Check that the overlay between pending_buf and d_buf+l_buf is ok: */
+-        Assert((uInt)(s->pending) < s->lit_bufsize + 2*lx,
+-               "pendingBuf overflow");
++        /* Check that the overlay between pending_buf and sym_buf is ok: */
++        Assert(s->pending < s->lit_bufsize + sx, "pendingBuf overflow");
+ 
+-    } while (lx < s->last_lit);
++    } while (sx < s->sym_next);
+ 
+     send_code(s, END_BLOCK, ltree);
+ }

+ 1 - 1
tools/zlib/Makefile

@@ -9,7 +9,7 @@ include $(TOPDIR)/rules.mk
 
 PKG_NAME:=zlib
 PKG_VERSION:=1.2.11
-PKG_RELEASE:=1
+PKG_RELEASE:=2
 
 PKG_SOURCE:=$(PKG_NAME)-$(PKG_VERSION).tar.xz
 PKG_SOURCE_URL:=@SF/libpng http://www.zlib.net

+ 343 - 0
tools/zlib/patches/006-fix-compressor-crash-on-certain-inputs.patch

@@ -0,0 +1,343 @@
+From 5c44459c3b28a9bd3283aaceab7c615f8020c531 Mon Sep 17 00:00:00 2001
+From: Mark Adler <madler@alumni.caltech.edu>
+Date: Tue, 17 Apr 2018 22:09:22 -0700
+Subject: [PATCH] Fix a bug that can crash deflate on some input when using
+ Z_FIXED.
+
+This bug was reported by Danilo Ramos of Eideticom, Inc. It has
+lain in wait 13 years before being found! The bug was introduced
+in zlib 1.2.2.2, with the addition of the Z_FIXED option. That
+option forces the use of fixed Huffman codes. For rare inputs with
+a large number of distant matches, the pending buffer into which
+the compressed data is written can overwrite the distance symbol
+table which it overlays. That results in corrupted output due to
+invalid distances, and can result in out-of-bound accesses,
+crashing the application.
+
+The fix here combines the distance buffer and literal/length
+buffers into a single symbol buffer. Now three bytes of pending
+buffer space are opened up for each literal or length/distance
+pair consumed, instead of the previous two bytes. This assures
+that the pending buffer cannot overwrite the symbol table, since
+the maximum fixed code compressed length/distance is 31 bits, and
+since there are four bytes of pending space for every three bytes
+of symbol space.
+---
+ deflate.c | 74 ++++++++++++++++++++++++++++++++++++++++---------------
+ deflate.h | 25 +++++++++----------
+ trees.c   | 50 +++++++++++--------------------------
+ 3 files changed, 79 insertions(+), 70 deletions(-)
+
+diff --git a/deflate.c b/deflate.c
+index 425babc00..19cba873a 100644
+--- a/deflate.c
++++ b/deflate.c
+@@ -255,11 +255,6 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+     int wrap = 1;
+     static const char my_version[] = ZLIB_VERSION;
+ 
+-    ushf *overlay;
+-    /* We overlay pending_buf and d_buf+l_buf. This works since the average
+-     * output size for (length,distance) codes is <= 24 bits.
+-     */
+-
+     if (version == Z_NULL || version[0] != my_version[0] ||
+         stream_size != sizeof(z_stream)) {
+         return Z_VERSION_ERROR;
+@@ -329,9 +324,47 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+ 
+     s->lit_bufsize = 1 << (memLevel + 6); /* 16K elements by default */
+ 
+-    overlay = (ushf *) ZALLOC(strm, s->lit_bufsize, sizeof(ush)+2);
+-    s->pending_buf = (uchf *) overlay;
+-    s->pending_buf_size = (ulg)s->lit_bufsize * (sizeof(ush)+2L);
++    /* We overlay pending_buf and sym_buf. This works since the average size
++     * for length/distance pairs over any compressed block is assured to be 31
++     * bits or less.
++     *
++     * Analysis: The longest fixed codes are a length code of 8 bits plus 5
++     * extra bits, for lengths 131 to 257. The longest fixed distance codes are
++     * 5 bits plus 13 extra bits, for distances 16385 to 32768. The longest
++     * possible fixed-codes length/distance pair is then 31 bits total.
++     *
++     * sym_buf starts one-fourth of the way into pending_buf. So there are
++     * three bytes in sym_buf for every four bytes in pending_buf. Each symbol
++     * in sym_buf is three bytes -- two for the distance and one for the
++     * literal/length. As each symbol is consumed, the pointer to the next
++     * sym_buf value to read moves forward three bytes. From that symbol, up to
++     * 31 bits are written to pending_buf. The closest the written pending_buf
++     * bits gets to the next sym_buf symbol to read is just before the last
++     * code is written. At that time, 31*(n-2) bits have been written, just
++     * after 24*(n-2) bits have been consumed from sym_buf. sym_buf starts at
++     * 8*n bits into pending_buf. (Note that the symbol buffer fills when n-1
++     * symbols are written.) The closest the writing gets to what is unread is
++     * then n+14 bits. Here n is lit_bufsize, which is 16384 by default, and
++     * can range from 128 to 32768.
++     *
++     * Therefore, at a minimum, there are 142 bits of space between what is
++     * written and what is read in the overlain buffers, so the symbols cannot
++     * be overwritten by the compressed data. That space is actually 139 bits,
++     * due to the three-bit fixed-code block header.
++     *
++     * That covers the case where either Z_FIXED is specified, forcing fixed
++     * codes, or when the use of fixed codes is chosen, because that choice
++     * results in a smaller compressed block than dynamic codes. That latter
++     * condition then assures that the above analysis also covers all dynamic
++     * blocks. A dynamic-code block will only be chosen to be emitted if it has
++     * fewer bits than a fixed-code block would for the same set of symbols.
++     * Therefore its average symbol length is assured to be less than 31. So
++     * the compressed data for a dynamic block also cannot overwrite the
++     * symbols from which it is being constructed.
++     */
++
++    s->pending_buf = (uchf *) ZALLOC(strm, s->lit_bufsize, 4);
++    s->pending_buf_size = (ulg)s->lit_bufsize * 4;
+ 
+     if (s->window == Z_NULL || s->prev == Z_NULL || s->head == Z_NULL ||
+         s->pending_buf == Z_NULL) {
+@@ -340,8 +373,12 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy,
+         deflateEnd (strm);
+         return Z_MEM_ERROR;
+     }
+-    s->d_buf = overlay + s->lit_bufsize/sizeof(ush);
+-    s->l_buf = s->pending_buf + (1+sizeof(ush))*s->lit_bufsize;
++    s->sym_buf = s->pending_buf + s->lit_bufsize;
++    s->sym_end = (s->lit_bufsize - 1) * 3;
++    /* We avoid equality with lit_bufsize*3 because of wraparound at 64K
++     * on 16 bit machines and because stored blocks are restricted to
++     * 64K-1 bytes.
++     */
+ 
+     s->level = level;
+     s->strategy = strategy;
+@@ -552,7 +589,7 @@ int ZEXPORT deflatePrime (strm, bits, value)
+ 
+     if (deflateStateCheck(strm)) return Z_STREAM_ERROR;
+     s = strm->state;
+-    if ((Bytef *)(s->d_buf) < s->pending_out + ((Buf_size + 7) >> 3))
++    if (s->sym_buf < s->pending_out + ((Buf_size + 7) >> 3))
+         return Z_BUF_ERROR;
+     do {
+         put = Buf_size - s->bi_valid;
+@@ -1113,7 +1150,6 @@ int ZEXPORT deflateCopy (dest, source)
+ #else
+     deflate_state *ds;
+     deflate_state *ss;
+-    ushf *overlay;
+ 
+ 
+     if (deflateStateCheck(source) || dest == Z_NULL) {
+@@ -1133,8 +1169,7 @@ int ZEXPORT deflateCopy (dest, source)
+     ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte));
+     ds->prev   = (Posf *)  ZALLOC(dest, ds->w_size, sizeof(Pos));
+     ds->head   = (Posf *)  ZALLOC(dest, ds->hash_size, sizeof(Pos));
+-    overlay = (ushf *) ZALLOC(dest, ds->lit_bufsize, sizeof(ush)+2);
+-    ds->pending_buf = (uchf *) overlay;
++    ds->pending_buf = (uchf *) ZALLOC(dest, ds->lit_bufsize, 4);
+ 
+     if (ds->window == Z_NULL || ds->prev == Z_NULL || ds->head == Z_NULL ||
+         ds->pending_buf == Z_NULL) {
+@@ -1148,8 +1183,7 @@ int ZEXPORT deflateCopy (dest, source)
+     zmemcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size);
+ 
+     ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf);
+-    ds->d_buf = overlay + ds->lit_bufsize/sizeof(ush);
+-    ds->l_buf = ds->pending_buf + (1+sizeof(ush))*ds->lit_bufsize;
++    ds->sym_buf = ds->pending_buf + ds->lit_bufsize;
+ 
+     ds->l_desc.dyn_tree = ds->dyn_ltree;
+     ds->d_desc.dyn_tree = ds->dyn_dtree;
+@@ -1925,7 +1959,7 @@ local block_state deflate_fast(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+@@ -2056,7 +2090,7 @@ local block_state deflate_slow(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+@@ -2131,7 +2165,7 @@ local block_state deflate_rle(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+@@ -2170,7 +2204,7 @@ local block_state deflate_huff(s, flush)
+         FLUSH_BLOCK(s, 1);
+         return finish_done;
+     }
+-    if (s->last_lit)
++    if (s->sym_next)
+         FLUSH_BLOCK(s, 0);
+     return block_done;
+ }
+diff --git a/deflate.h b/deflate.h
+index 23ecdd312..d4cf1a98b 100644
+--- a/deflate.h
++++ b/deflate.h
+@@ -217,7 +217,7 @@ typedef struct internal_state {
+     /* Depth of each subtree used as tie breaker for trees of equal frequency
+      */
+ 
+-    uchf *l_buf;          /* buffer for literals or lengths */
++    uchf *sym_buf;        /* buffer for distances and literals/lengths */
+ 
+     uInt  lit_bufsize;
+     /* Size of match buffer for literals/lengths.  There are 4 reasons for
+@@ -239,13 +239,8 @@ typedef struct internal_state {
+      *   - I can't count above 4
+      */
+ 
+-    uInt last_lit;      /* running index in l_buf */
+-
+-    ushf *d_buf;
+-    /* Buffer for distances. To simplify the code, d_buf and l_buf have
+-     * the same number of elements. To use different lengths, an extra flag
+-     * array would be necessary.
+-     */
++    uInt sym_next;      /* running index in sym_buf */
++    uInt sym_end;       /* symbol table full when sym_next reaches this */
+ 
+     ulg opt_len;        /* bit length of current block with optimal trees */
+     ulg static_len;     /* bit length of current block with static trees */
+@@ -325,20 +320,22 @@ void ZLIB_INTERNAL _tr_stored_block OF((deflate_state *s, charf *buf,
+ 
+ # define _tr_tally_lit(s, c, flush) \
+   { uch cc = (c); \
+-    s->d_buf[s->last_lit] = 0; \
+-    s->l_buf[s->last_lit++] = cc; \
++    s->sym_buf[s->sym_next++] = 0; \
++    s->sym_buf[s->sym_next++] = 0; \
++    s->sym_buf[s->sym_next++] = cc; \
+     s->dyn_ltree[cc].Freq++; \
+-    flush = (s->last_lit == s->lit_bufsize-1); \
++    flush = (s->sym_next == s->sym_end); \
+    }
+ # define _tr_tally_dist(s, distance, length, flush) \
+   { uch len = (uch)(length); \
+     ush dist = (ush)(distance); \
+-    s->d_buf[s->last_lit] = dist; \
+-    s->l_buf[s->last_lit++] = len; \
++    s->sym_buf[s->sym_next++] = dist; \
++    s->sym_buf[s->sym_next++] = dist >> 8; \
++    s->sym_buf[s->sym_next++] = len; \
+     dist--; \
+     s->dyn_ltree[_length_code[len]+LITERALS+1].Freq++; \
+     s->dyn_dtree[d_code(dist)].Freq++; \
+-    flush = (s->last_lit == s->lit_bufsize-1); \
++    flush = (s->sym_next == s->sym_end); \
+   }
+ #else
+ # define _tr_tally_lit(s, c, flush) flush = _tr_tally(s, 0, c)
+diff --git a/trees.c b/trees.c
+index 4f4a65011..decaeb7c3 100644
+--- a/trees.c
++++ b/trees.c
+@@ -416,7 +416,7 @@ local void init_block(s)
+ 
+     s->dyn_ltree[END_BLOCK].Freq = 1;
+     s->opt_len = s->static_len = 0L;
+-    s->last_lit = s->matches = 0;
++    s->sym_next = s->matches = 0;
+ }
+ 
+ #define SMALLEST 1
+@@ -948,7 +948,7 @@ void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last)
+ 
+         Tracev((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u ",
+                 opt_lenb, s->opt_len, static_lenb, s->static_len, stored_len,
+-                s->last_lit));
++                s->sym_next / 3));
+ 
+         if (static_lenb <= opt_lenb) opt_lenb = static_lenb;
+ 
+@@ -1017,8 +1017,9 @@ int ZLIB_INTERNAL _tr_tally (s, dist, lc)
+     unsigned dist;  /* distance of matched string */
+     unsigned lc;    /* match length-MIN_MATCH or unmatched char (if dist==0) */
+ {
+-    s->d_buf[s->last_lit] = (ush)dist;
+-    s->l_buf[s->last_lit++] = (uch)lc;
++    s->sym_buf[s->sym_next++] = dist;
++    s->sym_buf[s->sym_next++] = dist >> 8;
++    s->sym_buf[s->sym_next++] = lc;
+     if (dist == 0) {
+         /* lc is the unmatched char */
+         s->dyn_ltree[lc].Freq++;
+@@ -1033,30 +1034,7 @@ int ZLIB_INTERNAL _tr_tally (s, dist, lc)
+         s->dyn_ltree[_length_code[lc]+LITERALS+1].Freq++;
+         s->dyn_dtree[d_code(dist)].Freq++;
+     }
+-
+-#ifdef TRUNCATE_BLOCK
+-    /* Try to guess if it is profitable to stop the current block here */
+-    if ((s->last_lit & 0x1fff) == 0 && s->level > 2) {
+-        /* Compute an upper bound for the compressed length */
+-        ulg out_length = (ulg)s->last_lit*8L;
+-        ulg in_length = (ulg)((long)s->strstart - s->block_start);
+-        int dcode;
+-        for (dcode = 0; dcode < D_CODES; dcode++) {
+-            out_length += (ulg)s->dyn_dtree[dcode].Freq *
+-                (5L+extra_dbits[dcode]);
+-        }
+-        out_length >>= 3;
+-        Tracev((stderr,"\nlast_lit %u, in %ld, out ~%ld(%ld%%) ",
+-               s->last_lit, in_length, out_length,
+-               100L - out_length*100L/in_length));
+-        if (s->matches < s->last_lit/2 && out_length < in_length/2) return 1;
+-    }
+-#endif
+-    return (s->last_lit == s->lit_bufsize-1);
+-    /* We avoid equality with lit_bufsize because of wraparound at 64K
+-     * on 16 bit machines and because stored blocks are restricted to
+-     * 64K-1 bytes.
+-     */
++    return (s->sym_next == s->sym_end);
+ }
+ 
+ /* ===========================================================================
+@@ -1069,13 +1047,14 @@ local void compress_block(s, ltree, dtree)
+ {
+     unsigned dist;      /* distance of matched string */
+     int lc;             /* match length or unmatched char (if dist == 0) */
+-    unsigned lx = 0;    /* running index in l_buf */
++    unsigned sx = 0;    /* running index in sym_buf */
+     unsigned code;      /* the code to send */
+     int extra;          /* number of extra bits to send */
+ 
+-    if (s->last_lit != 0) do {
+-        dist = s->d_buf[lx];
+-        lc = s->l_buf[lx++];
++    if (s->sym_next != 0) do {
++        dist = s->sym_buf[sx++] & 0xff;
++        dist += (unsigned)(s->sym_buf[sx++] & 0xff) << 8;
++        lc = s->sym_buf[sx++];
+         if (dist == 0) {
+             send_code(s, lc, ltree); /* send a literal byte */
+             Tracecv(isgraph(lc), (stderr," '%c' ", lc));
+@@ -1100,11 +1079,10 @@ local void compress_block(s, ltree, dtree)
+             }
+         } /* literal or match pair ? */
+ 
+-        /* Check that the overlay between pending_buf and d_buf+l_buf is ok: */
+-        Assert((uInt)(s->pending) < s->lit_bufsize + 2*lx,
+-               "pendingBuf overflow");
++        /* Check that the overlay between pending_buf and sym_buf is ok: */
++        Assert(s->pending < s->lit_bufsize + sx, "pendingBuf overflow");
+ 
+-    } while (lx < s->last_lit);
++    } while (sx < s->sym_next);
+ 
+     send_code(s, END_BLOCK, ltree);
+ }