Merge remote-tracking branch 'github/nasm-2.15.xx'

Resolved Conflicts: version Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
2025-10-10 00:25:06 -04:00 · 2020-06-30 17:14:36 -07:00
parent 367350319b 8877a3ddb0
commit a3db726f02
23 changed files with 515 additions and 245 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1 @@
+/version -merge
--- a/asm/listing.c
+++ b/asm/listing.c
@@ -1,6 +1,6 @@
 /* ----------------------------------------------------------------------- *
 *
- *   Copyright 1996-2019 The NASM Authors - All Rights Reserved
+ *   Copyright 1996-2020 The NASM Authors - All Rights Reserved
 *   See the file AUTHORS included with the NASM distribution for
 *   the specific copyright holders.
 *
@@ -276,8 +276,13 @@ static void list_output(const struct out_data *data)
 	break;
    case OUT_RESERVE:
    {
-        if (size)
+        if (size > 8) {
            list_size(offset, "res", size);
+        } else {
+            memset(q, '?', size << 1);
+            q[size << 1] = '\0';
+            list_out(offset, q);
+        }
 	break;
    }
    default:
--- a/asm/parser.c
+++ b/asm/parser.c
@@ -1,6 +1,6 @@
 /* ----------------------------------------------------------------------- *
 *
- *   Copyright 1996-2019 The NASM Authors - All Rights Reserved
+ *   Copyright 1996-2020 The NASM Authors - All Rights Reserved
 *   See the file AUTHORS included with the NASM distribution for
 *   the specific copyright holders.
 *
@@ -234,7 +234,8 @@ static bool parse_braces(decoflags_t *decoflags)
    }
 }

-static inline const expr *next_expr(const expr *e, const expr **next_list)
+static inline unused
+const expr *next_expr(const expr *e, const expr **next_list)
 {
    e++;
    if (!e->type) {
@@ -830,7 +831,14 @@ restart_parse:
            /* DB et al */
            result->operands = oper_num;
            if (oper_num == 0)
-                nasm_warn(WARN_OTHER, "no operand for data declaration");
+                /*!
+                 *!db-empty [on] no operand for data declaration
+                 *!  warns about a \c{DB}, \c{DW}, etc declaration
+                 *!  with no operands, producing no output.
+                 *!  This is permitted, but often indicative of an error.
+                 *!  See \k{db}.
+                 */
+                nasm_warn(WARN_DB_EMPTY, "no operand for data declaration");
        }
        return result;
    }
--- a/asm/pptok.pl
+++ b/asm/pptok.pl
@@ -223,19 +223,19 @@ if ($what eq 'c') {
    # Put a large value in unused slots.  This makes it extremely unlikely
    # that any combination that involves unused slot will pass the range test.
    # This speeds up rejection of unrecognized tokens, i.e. identifiers.
-    print OUT "#define UNUSED (65535/3)\n";
+    print OUT "#define UNUSED_HASH_ENTRY (65535/3)\n";

    print OUT "    static const int16_t hash1[$n] = {\n";
    for ($i = 0; $i < $n; $i++) {
 	my $h = ${$g}[$i*2+0];
-	print OUT "        ", defined($h) ? $h : 'UNUSED', ",\n";
+	print OUT "        ", defined($h) ? $h : 'UNUSED_HASH_ENTRY', ",\n";
    }
    print OUT "    };\n";

    print OUT "    static const int16_t hash2[$n] = {\n";
    for ($i = 0; $i < $n; $i++) {
 	my $h = ${$g}[$i*2+1];
-	print OUT "        ", defined($h) ? $h : 'UNUSED', ",\n";
+	print OUT "        ", defined($h) ? $h : 'UNUSED_HASH_ENTRY', ",\n";
    }
    print OUT "    };\n";

--- a/asm/preproc.c
+++ b/asm/preproc.c
@@ -345,7 +345,8 @@ static inline bool tok_text_match(const struct Token *a, const struct Token *b)
    return a->len == b->len && !memcmp(tok_text(a), tok_text(b), a->len);
 }

-static inline bool tok_match(const struct Token *a, const struct Token *b)
+static inline unused bool
+tok_match(const struct Token *a, const struct Token *b)
 {
    return a->type == b->type && tok_text_match(a, b);
 }
@@ -763,7 +764,8 @@ static const char *unquote_token_cstr(Token *t)
 * TOK_STRING tokens.
 */
 static Token *quote_any_token(Token *t);
-static inline Token *quote_token(Token *t)
+static inline unused
+Token *quote_token(Token *t)
 {
    if (likely(!tok_is(t, TOK_INTERNAL_STRING)))
 	return t;
@@ -4886,17 +4888,15 @@ static int mmac_rotate(const MMacro *mac, unsigned int n)
 /*
 * expands to a list of tokens from %{x:y}
 */
-static Token *expand_mmac_params_range(MMacro *mac, Token *tline, Token ***last)
+void expand_mmac_params_range(MMacro *mac, Token *tline, Token ***tail)
 {
-    Token *t = tline, **tt, *tm, *head;
-    char *pos;
-    int fst, lst, j, i;
+    Token *t;
+    const char *arg = tok_text(tline) + 1;
+    int fst, lst, incr, n;
+    int parsed;

-    pos = strchr(tok_text(tline), ':');
-    nasm_assert(pos);
-
-    lst = atoi(pos + 1);
-    fst = atoi(tok_text(tline) + 1);
+    parsed = sscanf(arg, "%d:%d", &fst, &lst);
+    nasm_assert(parsed == 2);

    /*
     * only macros params are accounted so
@@ -4914,56 +4914,28 @@ static Token *expand_mmac_params_range(MMacro *mac, Token *tline, Token ***last)
    fst = fst < 0 ? fst + (int)mac->nparam + 1: fst;
    lst = lst < 0 ? lst + (int)mac->nparam + 1: lst;

-    /* count from zero */
-    fst--, lst--;
-
    /*
-     * It will be at least one token. Note we
-     * need to scan params until separator, otherwise
-     * only first token will be passed.
+     * It will be at least one parameter, as we can loop
+     * in either direction.
     */
-    j = (fst + mac->rotate) % mac->nparam;
-    tm = mac->params[j+1];
-    if (!tm)
-        goto err;
-    head = dup_Token(NULL, tm);
-    tt = &head->next, tm = tm->next;
-    while (tok_isnt(tm, ',')) {
-        t = dup_Token(NULL, tm);
-        *tt = t, tt = &t->next, tm = tm->next;
+    incr = (fst < lst) ? 1 : -1;
+
+    while (true) {
+        n = mmac_rotate(mac, fst);
+        dup_tlistn(mac->params[n], mac->paramlen[n], tail);
+        if (fst == lst)
+            break;
+        t = make_tok_char(NULL, ',');
+        **tail = t;
+        *tail = &t->next;
+        fst += incr;
    }

-    if (fst < lst) {
-        for (i = fst + 1; i <= lst; i++) {
-            t = make_tok_char(NULL, ',');
-            *tt = t, tt = &t->next;
-            j = (i + mac->rotate) % mac->nparam;
-            tm = mac->params[j+1];
-            while (tok_isnt(tm, ',')) {
-                t = dup_Token(NULL, tm);
-                *tt = t, tt = &t->next, tm = tm->next;
-            }
-        }
-    } else {
-        for (i = fst - 1; i >= lst; i--) {
-            t = make_tok_char(NULL, ',');
-            *tt = t, tt = &t->next;
-            j = (i + mac->rotate) % mac->nparam;
-            tm = mac->params[j+1];
-            while (!tok_isnt(tm, ',')) {
-                t = dup_Token(NULL, tm);
-                *tt = t, tt = &t->next, tm = tm->next;
-            }
-        }
-    }
-
-    *last = tt;
-    return head;
+    return;

 err:
-    nasm_nonfatal("`%%{%s}': macro parameters out of range",
-		  tok_text(tline) + 1);
-    return NULL;
+    nasm_nonfatal("`%%{%s}': macro parameters out of range", arg);
+    return;
 }

 /*
@@ -5014,16 +4986,9 @@ static Token *expand_mmac_params(Token * tline)
            }

            if (strchr(text, ':')) {
-                /*
-                 * seems we have a parameters range here
-                 */
-                Token *head, **last;
-                head = expand_mmac_params_range(mac, t, &last);
-                if (head) {
-                    *tail = head;
-                    *last = tline;
-                    text = NULL;
-                }
+                /* It is a range */
+                expand_mmac_params_range(mac, t, &tail);
+                text = NULL;
                break;
            }

@@ -5999,7 +5964,7 @@ static MMacro *is_mmacro(Token * tline, int *nparamp, Token ***paramsp)
     *!  The legacy behavior is quite strange and highly context-dependent,
     *!  and can be disabled with:
     *!-
-     *!  \c %pragma preproc sane_empty_expansion true
+     *!  \c      %pragma preproc sane_empty_expansion true
     *!-
     *!  It is highly recommended to use this option in new code.
     */
--- a/asm/stdscan.c
+++ b/asm/stdscan.c
@@ -164,7 +164,7 @@ int stdscan(void *private_data, struct tokenval *tv)
             *!ptr [on] non-NASM keyword used in other assemblers
             *!  warns about keywords used in other assemblers that might
             *!  indicate a mistake in the source code.  Currently only the MASM
-             *!  \c{PTR} keyword is recognized.
+             *!  \c{PTR} keyword is recognized. See also \k{pkg_masm}.
             */
            nasm_warn(WARN_PTR, "`%s' is not a NASM keyword",
                       tv->t_charptr);
--- a/asm/tokhash.pl
+++ b/asm/tokhash.pl
@@ -234,19 +234,19 @@ if ($output eq 'h') {
    # Put a large value in unused slots.  This makes it extremely unlikely
    # that any combination that involves unused slot will pass the range test.
    # This speeds up rejection of unrecognized tokens, i.e. identifiers.
-    print "#define UNUSED (65535/3)\n";
+    print "#define UNUSED_HASH_ENTRY (65535/3)\n";

    print "    static const int16_t hash1[$n] = {\n";
    for ($i = 0; $i < $n; $i++) {
 	my $h = ${$g}[$i*2+0];
-	print "        ", defined($h) ? $h : 'UNUSED', ",\n";
+	print "        ", defined($h) ? $h : 'UNUSED_HASH_ENTRY', ",\n";
    }
    print "    };\n";

    print "    static const int16_t hash2[$n] = {\n";
    for ($i = 0; $i < $n; $i++) {
 	my $h = ${$g}[$i*2+1];
-	print "        ", defined($h) ? $h : 'UNUSED', ",\n";
+	print "        ", defined($h) ? $h : 'UNUSED_HASH_ENTRY', ",\n";
    }
    print "    };\n";

--- a/asm/warnings.pl
+++ b/asm/warnings.pl
@@ -253,7 +253,18 @@ if ($what eq 'c') {
 	} else {
 	    my $docdef = $whatdef{$warn->{def}};

-	    @doc = @{$warn->{doc}};
+	    my $newpara = 0;
+	    foreach my $l (@{$warn->{doc}}) {
+		if ($l =~ /^\s*$/) {
+		    $newpara = 1;
+		} else {
+		    if ($newpara && $l !~ /^\\c\s+/) {
+			$l = '\> ' . $l;
+		    }
+		    $newpara = 0;
+		}
+		push(@doc, $l);
+	    }
 	    if (defined($docdef)) {
 		push(@doc, "\n", "\\> $docdef by default.\n");
 	    }
--- a/config/unconfig.h
+++ b/config/unconfig.h
@@ -60,6 +60,12 @@
 /* Define to 1 if compiled with the `-Wc90-c99-compat' compiler flag */
 /* #undef CFLAGS_WC90_C99_COMPAT */

+/* Define to 1 if compiled with the `-Wc99-compat' compiler flag */
+/* #undef CFLAGS_WC99_COMPAT */
+
+/* Define to 1 if compiled with the `-Wc99-extensions' compiler flag */
+/* #undef CFLAGS_WC99_EXTENSIONS */
+
 /* Define to 1 if compiled with the `-Werror' compiler flag */
 /* #undef CFLAGS_WERROR */

@@ -225,6 +231,10 @@
   functions */
 /* #undef HAVE_FUNC_ATTRIBUTE_SENTINEL */

+/* Define to 1 if your compiler supports __attribute__((unused)) on functions
+   */
+/* #undef HAVE_FUNC_ATTRIBUTE_UNUSED */
+
 /* Define to 1 if your compiler supports __attribute__((alloc_size)) on
   function pointers */
 /* #undef HAVE_FUNC_PTR_ATTRIBUTE1_ALLOC_SIZE */
@@ -265,6 +275,10 @@
   pointers */
 /* #undef HAVE_FUNC_PTR_ATTRIBUTE_SENTINEL */

+/* Define to 1 if your compiler supports __attribute__((unused)) on function
+   pointers */
+/* #undef HAVE_FUNC_PTR_ATTRIBUTE_UNUSED */
+
 /* Define to 1 if you have the `getgid' function. */
 /* #undef HAVE_GETGID */

@@ -714,6 +728,22 @@
 # endif
 #endif

+#ifndef unused_func
+# ifdef HAVE_FUNC_ATTRIBUTE_UNUSED
+#  define unused_func __attribute__((unused))
+# else
+#  define unused_func
+# endif
+#endif
+
+#ifndef unused_func_ptr
+# ifdef HAVE_FUNC_PTR_ATTRIBUTE_UNUSED
+#  define unused_func_ptr __attribute__((unused))
+# else
+#  define unused_func_ptr
+# endif
+#endif
+
 #ifndef never_null
 # ifdef HAVE_FUNC_ATTRIBUTE_RETURNS_NONNULL
 #  define never_null __attribute__((returns_nonnull))
--- a/configure.ac
+++ b/configure.ac
@@ -23,12 +23,6 @@ AC_USE_SYSTEM_EXTENSIONS
 AC_SYS_LARGEFILE
 AC_PROG_CC
 AC_PROG_CC_STDC
-AC_PROG_LN_S
-AC_PROG_MAKE_SET
-AC_PROG_INSTALL
-AC_PROG_MKDIR_P
-
-pa_no_optimize=false

 dnl If the user did not specify a CFLAGS default, change default
 dnl to -O0 for debugging
@@ -36,6 +30,19 @@ PA_ARG_DISABLED([optimization],
 [compile without optimization (-O0) to help debugging],
 [pa_no_optimize=true])

+dnl LLVM doesn't error out on invalid -W options unless this option is
+dnl specified first.  Enable this so this script can actually discover
+dnl which -W options are possible for this compiler.
+PA_ADD_CFLAGS([-Werror=unknown-warning-option])
+
+dnl Other programs
+AC_PROG_LN_S
+AC_PROG_MAKE_SET
+AC_PROG_INSTALL
+AC_PROG_MKDIR_P
+
+pa_no_optimize=false
+
 dnl Compile and link with dwarf debug
 PA_ARG_ENABLED([gdb],
 [disable optimization and compile with extra debug information for GDB debugger],
@@ -282,6 +289,7 @@ PA_FUNC_ATTRIBUTE(format, [printf,1,2], int, [const char *, ...], ["%d",1])
 PA_FUNC_ATTRIBUTE(const)
 PA_FUNC_ATTRIBUTE(pure)
 PA_FUNC_ATTRIBUTE(cold,,,,,unlikely_func)
+PA_FUNC_ATTRIBUTE(unused)
 PA_FUNC_ATTRIBUTE_ERROR

 dnl
@@ -320,22 +328,25 @@ PA_ARG_ENABLED([sanitizer],

 dnl
 dnl Don't make symbols visible, there is no point and it just
-dnl makes the code slower.
+dnl makes the code slower. This mainly affects ELF.
 dnl
 PA_ADD_CFLAGS([-fvisibility=hidden])

-dnl If we have gcc, add appropriate code cleanliness options
+dnl
+dnl If we have gcc, add appropriate code cleanliness options.  Do this
+dnl here at the end, because configure relies on being able to use
+dnl some very, very old C constructs.
+dnl
 PA_ADD_CFLAGS([-Wall])
 PA_ARG_DISABLED([pedantic],
 [disable some extra paranoid compiler warnings],
 [],
 [PA_ADD_CFLAGS([-W])
 PA_ADD_CFLAGS([-pedantic])
- PA_ADD_CFLAGS([-Wc90-c99-compat])])
-dnl LLVM doesn't error out on invalid -W options unless this option is
-dnl specified first.  Enable this so this script can actually discover
-dnl which -W options are possible for this compiler.
-PA_ADD_CFLAGS([-Werror=unknown-warning-option])
+ PA_ADD_CFLAGS([-Wc90-c99-compat])
+ PA_ADD_CFLAGS([-Wc99-compat])
+ PA_ADD_CFLAGS([-Wc99-extensions])
+])
 dnl Suppress format warning on Windows targets due to their <inttypes.h>
 PA_ADD_CFLAGS([-Wpedantic-ms-format],[-Wno-pedantic-ms-format])
 PA_ADD_CFLAGS([-Wlong-long],[-Wno-long-long])
@@ -347,6 +358,7 @@ dnl on compilers with gcc-like command line syntax we pass the -fwrapv
 dnl option for exactly that reason.
 PA_ADD_CFLAGS([-Wshift-negative-value],[-Wno-shift-negative-value])

+dnl Want to turn this on at some point...
 dnl PA_ADD_CFLAGS([-Wwrite-strings])
 PA_ARG_ENABLED([werror],
 [compile with -Werror to error out on any warning],
--- a/doc/changes.src
+++ b/doc/changes.src
@@ -7,6 +7,17 @@
 The NASM 2 series supports x86-64, and is the production version of NASM
 since 2007.

+\S{cl-2.15.02} Version 2.15.02
+
+\b Fix miscompilation when building with \c{clang}.
+
+\b Add \c{db-empty} warning class, see \k{opt-w}.
+
+\b Some documentation improvements and cleanups.
+
+\b Fix the handling of macro parameter ranges (\c{%\{:\}}), including
+with brace-enclosed original arguments.
+
 \S{cl-2.15.01} Version 2.15.01

 \b Fix building the documentation from the release archive. For 2.15,
--- a/doc/genps.pl
+++ b/doc/genps.pl
@@ -1,7 +1,7 @@
 #!/usr/bin/perl
 ## --------------------------------------------------------------------------
 ##
-##   Copyright 1996-2017 The NASM Authors - All Rights Reserved
+##   Copyright 1996-2020 The NASM Authors - All Rights Reserved
 ##   See the file AUTHORS included with the NASM distribution for
 ##   the specific copyright holders.
 ##
@@ -775,7 +775,7 @@ sub ps_break_lines($$) {
 	    my $p;
 	    # Code paragraph; each chunk is a line
 	    foreach $p ( @data ) {
-		push(@ls, [[$ptype,0,undef,\%BodyFont,0,0],[$p]]);
+		push(@ls, [[$ptype,0,undef,\%CodeFont,0,0],[$p]]);
 	    }
 	    $ls[0]->[0]->[1] |= 1;	     # First in para
 	    $ls[-1]->[0]->[1] |= 2;      # Last in para
--- a/doc/head.ps
+++ b/doc/head.ps
@@ -246,10 +246,10 @@
 /norm2 { lmarg exch moveto bfont showstream } def
 /norm3 { lmarg exch moveto bfont showstream } def

-/code0 { lmarg exch moveto bfont showstream } def
-/code1 { lmarg exch moveto bfont showstream } def
-/code2 { lmarg exch moveto bfont showstream } def
-/code3 { lmarg exch moveto bfont showstream } def
+/code0 { lmarg exch moveto xfont showstream } def
+/code1 { lmarg exch moveto xfont showstream } def
+/code2 { lmarg exch moveto xfont showstream } def
+/code3 { lmarg exch moveto xfont showstream } def

 /bull0 { bullmarg exch moveto bfont bwidth showstreamjust } def
 /bull1 { dup lmarg exch moveto bullet bfont showstream
--- a/doc/nasmdoc.css
+++ b/doc/nasmdoc.css
@@ -18,6 +18,7 @@ span.subtitle {
 }
 code, pre {
    font-family: "source code pro", "liberation mono", "monospace";
+    font-size: 80%;
 }
 pre, blockquote {
    margin-left: 4em;
--- a/doc/nasmdoc.src
+++ b/doc/nasmdoc.src
@@ -126,7 +126,13 @@
 \IR{+ modifier} \c{+} modifier
 \IR{- opsubtraction} \c{-} operator, binary
 \IR{- opunary} \c{-} operator, unary
-\IR{! opunary} \c{!} operator, unary
+\IR{! opunary} \c{!} operator
+\IA{A16}{a16}
+\IA{A32}{a32}
+\IA{A64}{a64}
+\IA{O16}{o16}
+\IA{O32}{o32}
+\IA{O64}{o64}
 \IR{alignment, in bin sections} alignment, in \c{bin} sections
 \IR{alignment, in elf sections} alignment, in ELF sections
 \IR{alignment, in win32 sections} alignment, in \c{win32} sections
@@ -152,10 +158,9 @@ variables
 \IA{case-sensitive}{case sensitive}
 \IA{case-insensitive}{case sensitive}
 \IA{character constants}{character constant}
-\IR{codeview} CodeView debugging format
+\IR{codeview debugging format} CodeView debugging format
 \IR{common object file format} Common Object File Format
-\IR{common variables, alignment in elf} common variables, alignment
-in ELF
+\IR{common variables, alignment in elf} common variables, alignment in ELF
 \IR{common, elf extensions to} \c{COMMON}, ELF extensions to
 \IR{common, obj extensions to} \c{COMMON}, \c{obj} extensions to
 \IR{declaring structure} declaring structures
@@ -165,15 +170,12 @@ in ELF
 \IR{dll symbols, exporting} DLL symbols, exporting
 \IR{dll symbols, importing} DLL symbols, importing
 \IR{dos} DOS
-\IR{dos archive} DOS archive
-\IR{dos source archive} DOS source archive
-\IR{dup} \c{DUP}
 \IA{effective address}{effective addresses}
 \IA{effective-address}{effective addresses}
 \IR{elf} ELF
 \IR{elf, 16-bit code} ELF, 16-bit code
 \IR{elf, debug formats} ELF, debug formats
-\IR{elf shared libraries} ELF, shared libraries
+\IR{elf shared library} ELF, shared libraries
 \IR{elf32} \c{elf32}
 \IR{elf64} \c{elf64}
 \IR{elfx32} \c{elfx32}
@@ -186,8 +188,7 @@ in ELF
 \IR{freebsd} FreeBSD
 \IR{freelink} FreeLink
 \IR{functions, c calling convention} functions, C calling convention
-\IR{functions, pascal calling convention} functions, Pascal calling
-convention
+\IR{functions, pascal calling convention} functions, \c{PASCAL} calling convention
 \IR{global, aoutb extensions to} \c{GLOBAL}, \c{aoutb} extensions to
 \IR{global, elf extensions to} \c{GLOBAL}, ELF extensions to
 \IR{global, rdf extensions to} \c{GLOBAL}, \c{rdf} extensions to
@@ -199,9 +200,6 @@ convention
 \IR{linux, elf} Linux, ELF
 \IR{linux, a.out} Linux, \c{a.out}
 \IR{linux, as86} Linux, \c{as86}
-\IR{logical and} logical AND
-\IR{logical or} logical OR
-\IR{logical xor} logical XOR
 \IR{mach object file format} Mach, object file format
 \IA{mach-o}{macho}
 \IR{mach-o} Mach-O, object file format
@@ -215,24 +213,30 @@ convention
 \IA{misc directory}{misc subdirectory}
 \IR{misc subdirectory} \c{misc} subdirectory
 \IR{microsoft omf} Microsoft OMF
-\IR{mmx registers} MMX registers
-\IA{modr/m}{modr/m byte}
-\IR{modr/m byte} ModR/M byte
 \IR{ms-dos} MS-DOS
 \IR{ms-dos device drivers} MS-DOS device drivers
 \IR{multipush} \c{multipush} macro
 \IR{nan} NaN
 \IR{nasm version} NASM version
+\IR{nasm version history} NASM version, history
+\IR{nasm version macros} NASM version, macros
+\IR{nasm version id} NASM version, ID macro
+\IR{nasm version string} NASM version, string macro
+\IR{arithmetic negation} negation, arithmetic
+\IR{bitwise negation} negation, bitwise
+\IR{boolean negation} negation, boolean
+\IR{boolean and} boolean, AND
+\IR{boolean or} boolean, OR
+\IR{boolean xor} boolean, XOR
 \IR{netbsd} NetBSD
 \IR{nsis} NSIS
 \IR{nullsoft scriptable installer} Nullsoft Scriptable Installer
+\IA{.OBJ}{.obj}
 \IR{omf} OMF
 \IR{openbsd} OpenBSD
 \IR{operating system} operating system
 \IR{os/2} OS/2
-\IR{pascal calling convention}Pascal calling convention
-\IR{passes} passes, assembly
-\IR{perl} Perl
+\IR{pascal calling convention} Pascal calling convention
 \IR{pic} PIC
 \IR{pharlap} PharLap
 \IR{plt} PLT
@@ -253,14 +257,16 @@ Object File Format
 \IR{section alignment, in win32} section alignment, in \c{win32}
 \IR{section, elf extensions to} \c{SECTION}, ELF extensions to
 \IR{section, macho extensions to} \c{SECTION}, \c{macho} extensions to
-\IR{section, win32 extensions to} \c{SECTION}, \c{win32} extensions to
+\IR{section, windows extensions to} \c{SECTION}, Windows extensions to
 \IR{segment alignment, in bin} segment alignment, in \c{bin}
 \IR{segment alignment, in obj} segment alignment, in \c{obj}
-\IR{segment, obj extensions to} \c{SEGMENT}, ELF extensions to
+\IR{segment, obj extensions to} \c{SEGMENT}, \c{obj} extensions to
 \IR{segment names, borland pascal} segment names, Borland Pascal
 \IR{shift command} \c{shift} command
-\IA{sib}{sib byte}
-\IR{sib byte} SIB byte
+\IA{string constant}{string constants}
+\IR{string constants} string, constants
+\IR{string length} string, length
+\IR{string manipulation in macros} string, manipulation in macros
 \IR{align, smart} \c{ALIGN}, smart
 \IA{sectalign}{sectalign}
 \IR{solaris x86} Solaris x86
@@ -271,7 +277,9 @@ Object File Format
 \IR{thread local storage in elf} thread local storage, in ELF
 \IR{thread local storage in mach-o} thread local storage, in \c{macho}
 \IR{tlink} \c{TLINK}
+\IR{unconditionally importing symbols} importing symbols, unconditionally
 \IR{underscore, in c symbols} underscore, in C symbols
+\IA{uninitialized storage}{storage, uninitialized}
 \IR{unicode} Unicode
 \IR{unix} Unix
 \IR{utf-8} UTF-8
@@ -279,20 +287,16 @@ Object File Format
 \IR{utf-32} UTF-32
 \IA{sco unix}{unix, sco}
 \IR{unix, sco} Unix, SCO
-\IA{unix source archive}{unix, source archive}
-\IR{unix, source archive} Unix, source archive
 \IA{unix system v}{unix, system v}
 \IR{unix, system v} Unix, System V
 \IR{unixware} UnixWare
 \IR{val} VAL
-\IR{version number of nasm} version number of NASM
+\IA{version number of nasm}{nasm, version}
 \IR{visual c++} Visual C++
-\IR{www page} WWW page
 \IR{win32} Win32
-\IR{win32} Win64
+\IR{win64} Win64
 \IR{windows} Windows
-\IR{windows 95} Windows 95
-\IR{windows nt} Windows NT
+\IR{windows debugging formats} Windows, debugging formats
 \# \IC{program entry point}{entry point, program}
 \# \IC{program entry point}{start point, program}
 \# \IC{MS-DOS device drivers}{device drivers, MS-DOS}
@@ -433,7 +437,7 @@ an intervening space. For example:
 \c nasm -f bin driver.asm -odriver.sys

 Note that this is a small o, and is different from a capital O , which
-is used to specify the number of optimisation passes required. See \k{opt-O}.
+is used to specify the number of optimization passes required. See \k{opt-O}.


 \S{opt-f} The \i\c{-f} Option: Specifying the \i{Output File Format}
@@ -1195,21 +1199,21 @@ defines a symbol called \c{eax}, you can refer to \c{$eax} in NASM
 code to distinguish the symbol from the register. Maximum length of
 an identifier is 4095 characters.

-The instruction field may contain any machine instruction: Pentium
-and P6 instructions, FPU instructions, MMX instructions and even
+The instruction field may contain any machine instruction: Pentium and
+P6 instructions, FPU instructions, MMX instructions and even
 undocumented instructions are all supported. The instruction may be
 prefixed by \c{LOCK}, \c{REP}, \c{REPE}/\c{REPZ}, \c{REPNE}/\c{REPNZ},
-\c{XACQUIRE}/\c{XRELEASE} or \c{BND}/\c{NOBND}, in the usual way. Explicit
-\I{address-size prefixes}address-size and \i{operand-size prefixes} \i\c{A16},
-\i\c{A32}, \i\c{A64}, \i\c{O16} and \i\c{O32}, \i\c{O64} are provided - one example of their use
-is given in \k{mixsize}. You can also use the name of a \I{segment
-override}segment register as an instruction prefix: coding
-\c{es mov [bx],ax} is equivalent to coding \c{mov [es:bx],ax}. We
-recommend the latter syntax, since it is consistent with other
-syntactic features of the language, but for instructions such as
-\c{LODSB}, which has no operands and yet can require a segment
-override, there is no clean syntactic way to proceed apart from
-\c{es lodsb}.
+\c{XACQUIRE}/\c{XRELEASE} or \c{BND}/\c{NOBND}, in the usual
+way. Explicit \I{address-size prefixes}address-size and
+\i{operand-size prefixes} \i\c{A16}, \i\c{A32}, \i\c{A64}, \i\c{O16}
+and \i\c{O32}, \i\c{O64} are provided - one example of their use is
+given in \k{mixsize}. You can also use the name of a \I{segment
+override}segment register as an instruction prefix: coding \c{es mov
+[bx],ax} is equivalent to coding \c{mov [es:bx],ax}. We recommend the
+latter syntax, since it is consistent with other syntactic features of
+the language, but for instructions such as \c{LODSB}, which has no
+operands and yet can require a segment override, there is no clean
+syntactic way to proceed apart from \c{es lodsb}.

 An instruction is not required to use a prefix: prefixes such as
 \c{CS}, \c{A32}, \c{LOCK} or \c{REPE} can appear on a line by
@@ -1250,10 +1254,11 @@ Pseudo-instructions are things which, though not real x86 machine
 instructions, are used in the instruction field anyway because that's
 the most convenient place to put them. The current pseudo-instructions
 are \i\c{DB}, \i\c{DW}, \i\c{DD}, \i\c{DQ}, \i\c{DT}, \i\c{DO},
-\i\c{DY} and \i\c\{DZ}; their \i{uninitialized} counterparts
-\i\c{RESB}, \i\c{RESW}, \i\c{RESD}, \i\c{RESQ}, \i\c{REST},
-\i\c{RESO}, \i\c{RESY} and \i\c\{RESZ}; the \i\c{INCBIN} command, the
-\i\c{EQU} command, and the \i\c{TIMES} prefix.
+\i\c{DY} and \i\c\{DZ}; their \I{storage,
+uninitialized}\i{uninitialized} counterparts \i\c{RESB}, \i\c{RESW},
+\i\c{RESD}, \i\c{RESQ}, \i\c{REST}, \i\c{RESO}, \i\c{RESY} and
+\i\c\{RESZ}; the \i\c{INCBIN} command, the \i\c{EQU} command, and the
+\i\c{TIMES} prefix.


 \S{db} \c{DB} and Friends: Declaring Initialized Data
@@ -1280,12 +1285,12 @@ the output file. They can be invoked in a wide range of ways:
 \c{DT}, \c{DO}, \c{DY} and \c{DZ} do not accept \i{numeric constants}
 as operands.

-\I{masmdb} Starting in NASM 2.15, a the following MASM-like features
+\I{masmdb} Starting in NASM 2.15, a the following \i{MASM}-like features
 have been implemented:

-\b A \I{?db}\c{?} argument to declare uninitialized data:
+\b A \I{?db}\c{?} argument to declare \i{uninitialized storage}:

-\c       db    ?                   ; uninitialized data
+\c       db    ?                   ; uninitialized

 \b A superset of the \i\c{DUP} syntax. The NASM version of this has
 the following syntax specification; capital letters indicate literal
@@ -1308,7 +1313,7 @@ valid:

 \c        db 33
 \c        db (44)		; Integer expression
-\c ;      db (44,55)      	; Invalid - error
+\c      ; db (44,55)		; Invalid - error
 \c        db %(44,55)
 \c        db %('XX','YY')
 \c        db ('AA')		; Integer expression - outputs single byte
@@ -1355,11 +1360,10 @@ the above example could also be written:

 \S{incbin} \i\c{INCBIN}: Including External \i{Binary Files}

-\c{INCBIN} is borrowed from the old Amiga assembler \i{DevPac}: it
-includes a binary file verbatim into the output file. This can be
-handy for (for example) including \i{graphics} and \i{sound} data
-directly into a game executable file. It can be called in one of
-these three ways:
+\c{INCBIN} includes binary file data verbatim into the output
+file. This can be handy for (for example) including \i{graphics} and
+\i{sound} data directly into a game executable file. It can be called
+in one of these three ways:

 \c     incbin  "file.dat"             ; include the whole file
 \c     incbin  "file.dat",1024        ; skip the first 1024 bytes
@@ -1574,7 +1578,7 @@ Some examples (all producing exactly the same code):
 \c         mov     ax,0b1100_1000  ; same binary constant yet again
 \c         mov     ax,0y1100_1000  ; same binary constant yet again

-\S{strings} \I{Strings}\i{Character Strings}
+\S{strings} \I{string}\I{string constants}\i{Character Strings}

 A character string consists of up to eight characters enclosed in
 either single quotes (\c{'...'}), double quotes (\c{"..."}) or
@@ -1884,15 +1888,15 @@ The \c{|} operator gives a bitwise OR, exactly as performed by the
 \S{expshift} \i{Bit Shift} Operators

 \i\c{<<} gives a bit-shift to the left, just as it does in C. So
-\c{5<<3} evaluates to 5 times 8, or 40. \i\c{>>} gives an \e{unsigned}
-(logical) bit-shift to the right; the bits shifted in from the left
-are set to zero.
+\c{5<<3} evaluates to 5 times 8, or 40. \i\c{>>} gives an \I{unsigned,
+bit shift}\e{unsigned} (logical) bit-shift to the right; the bits
+shifted in from the left are set to zero.

 \i\c{<<<} gives a bit-shift to the left, exactly equivalent to the
 \c{<<} operator; it is included for completeness. \i\c{>>>} gives an
-\e{signed} (arithmetic) bit-shift to the right; the bits shifted in
-from the left are filled with copies of the most significant (sign)
-bit.
+\I{signed, bit shift}\e{signed} (arithmetic) bit-shift to the right;
+the bits shifted in from the left are filled with copies of the most
+significant (sign) bit.


 \S{expplmi} \I{+ opaddition}\c{+} and \I{- opsubtraction}\c{-}:
@@ -1906,11 +1910,13 @@ subtraction.

 \i\c{*} is the multiplication operator.

-\i\c{/} and \i\c{//} are both division operators: \c{/} is \i{unsigned
-division} and \c{//} is \i{signed division}.
+\i\c{/} and \i\c{//} are both division operators: \c{/} is
+\I{division, unsigned}\I{unsigned, division}unsigned division and \c{//} is
+\I{division, signed}\I{signed, division}signed division.

-Similarly, \i\c{%} and \i\c{%%} provide \I{unsigned modulo}\I{modulo
-operators} unsigned and \i{signed modulo} operators respectively.
+Similarly, \i\c{%} and \i\c{%%} provide \I{modulo,
+unsigned}\I{unsigned, modulo}unsigned and \I{modulo, signed}\I{signed,
+modulo}signed modulo operators respectively.

 Since the \c{%} character is used extensively by the macro
 \i{preprocessor}, you should ensure that both the signed and unsigned
@@ -1923,22 +1929,27 @@ the signed division operator, such that:
 \c      b * (a // b) + (a %% b) = a       (b != 0)


-\S{expmul} \i{Unary Operators}
+\S{expmul} \I{operators, unary}\i{Unary Operators}

 The highest-priority operators in NASM's expression grammar are those
-which only apply to one argument.  These are \I{+ opunary}\c{+}, \I{-
-opunary}\c{-}, \i\c{~}, \I{! opunary}\c{!}, \i\c{SEG}, and the
-\i{integer functions} operators.
+which only apply to one argument.  These are:

-\c{-} negates its operand, \c{+} does nothing (it's provided for
-symmetry with \c{-}), \c{~} computes the \i{one's complement} of its
-operand, \c{!} is the \i{logical negation} operator.
+\b \I{- opunary}\c{-} \I{arithmetic negation}negates (\i{2's complement}) its
+operand.

-\c{SEG} provides the \i{segment address}
-of its operand (explained in more detail in \k{segwrt}).
+\b \I{+ opunary}\c{+} does nothing; it's provided for symmetry with \c{-}.

-A set of additional operators with leading and trailing double
-underscores are used to implement the integer functions of the
+\b \I{~ opunary}\c{~} computes the \I{negation, bitwise}\i{bitwise
+negation} (\i{1's complement}) of its operand.
+
+\b \I{! opunary}\c{!} is the \I{negation, boolean}\i{boolean negation}
+operator. It evaluates to 1 if the argument is 0, otherwise 0.
+
+\b \c{SEG} provides the \i{segment address} of its operand (explained in
+more detail in \k{segwrt}).
+
+\b A set of additional operators with leading and trailing double
+underscores are used to implement the \c{integer functions} of the
 \c{ifunc} macro package, see \k{pkg_ifunc}.


@@ -2239,7 +2250,7 @@ if the argument is never used. For example:
 A single pair of parentheses is a subcase of a single, unused argument:

 \c    %define myreg() eax
-\c    	mov edx,myreg()
+\c	mov edx,myreg()

 This is similar to the behavior of the C preprocessor.

@@ -4109,10 +4120,9 @@ be assembled with no pre-defined macros, you can use the \i\c{%clear}
 directive to empty the preprocessor of everything but context-local
 preprocessor variables and single-line macros, see \k{clear}.

-Most \i{user-level assembler directives} (see \k{directive}) are
-implemented as macros which invoke primitive directives; these are
-described in \k{directive}. The rest of the standard macro set is
-described here.
+Most \i{user-level directives} (see \k{directive}) are implemented as
+macros which invoke primitive directives; these are described in
+\k{directive}. The rest of the standard macro set is described here.

 For compability with NASM versions before NASM 2.15, most standard
 macros of the form \c{__?foo?__} have aliases of form \c{__foo__} (see
@@ -4120,15 +4130,15 @@ macros of the form \c{__?foo?__} have aliases of form \c{__foo__} (see
 defalias}.


-\H{stdmacver} \i{NASM Version} Macros
+\H{stdmacver} \i{NASM Version Macros}

 The single-line macros \i\c{__?NASM_MAJOR?__}, \i\c{__?NASM_MINOR?__},
-\i\c{__?NASM_SUBMINOR?__} and \i\c{__?_NASM_PATCHLEVEL?__} expand to the
+\i\c{__?NASM_SUBMINOR?__} and \i\c{__?NASM_PATCHLEVEL?__} expand to the
 major, minor, subminor and patch level parts of the \i{version
 number of NASM} being used. So, under NASM 0.98.32p1 for
 example, \c{__?NASM_MAJOR?__} would be defined to be 0, \c{__?NASM_MINOR?__}
 would be defined as 98, \c{__?NASM_SUBMINOR?__} would be defined to 32,
-and \c{__?_NASM_PATCHLEVEL?__} would be defined as 1.
+and \c{__?NASM_PATCHLEVEL?__} would be defined as 1.

 Additionally, the macro \i\c{__?NASM_SNAPSHOT?__} is defined for
 automatically generated snapshot releases \e{only}.
@@ -4139,7 +4149,7 @@ automatically generated snapshot releases \e{only}.
 The single-line macro \c{__?NASM_VERSION_ID?__} expands to a dword integer
 representing the full version number of the version of nasm being used.
 The value is the equivalent to \c{__?NASM_MAJOR?__}, \c{__?NASM_MINOR?__},
-\c{__?NASM_SUBMINOR?__} and \c{__?_NASM_PATCHLEVEL?__} concatenated to
+\c{__?NASM_SUBMINOR?__} and \c{__?NASM_PATCHLEVEL?__} concatenated to
 produce a single doubleword. Hence, for 0.98.32p1, the returned number
 would be equivalent to:

@@ -4154,7 +4164,7 @@ line is used just to give an indication of the order that the separate
 values will be present in memory.


-\S{stdmacverstr} \i\c{__?NASM_VER?__}: \i{NASM Version string}
+\S{stdmacverstr} \i\c{__?NASM_VER?__}: \i{NASM Version String}

 The single-line macro \c{__?NASM_VER?__} expands to a string which defines
 the version number of nasm being used. So, under NASM 0.98.32 for example,
@@ -4650,13 +4660,17 @@ functionality, as intended to be used primarily with machine-generated code.
 It does not include any "programmer-friendly" shortcuts, nor does it in any way
 support ASSUME, symbol typing, or MASM-style structures.

-Currently, the MASM compatibility package emulates only the PTR keyword and
-recognize syntax displacement[index] for memory operations.
-
+Currently, the MASM compatibility package emulates only the PTR
+keyword and recognize syntax displacement[index] for memory
+operations.
 To enable the package, use the directive:

 \c{%use masm}

+In addition, NASM now natively supports the MASM \c{?} and
+\c{DUP} syntax for the \c{DB} etc data declaration directives,
+regardless of if this package is included or not. See \k{db}.
+

 \C{directive} \i{Assembler Directives}

@@ -4949,13 +4963,12 @@ declared as \c{EXTERN} and then defined, it will be treated as
 \c{EXTERN}, it will be treated as \c{COMMON}.


-\H{required} \i\c{REQUIRED}: \i{Importing Symbols} from Other Modules
+\H{required} \i\c{REQUIRED}: \i{Unconditionally Importing Symbols} from Other Modules

-The \c{REQUIRED} keyword is similar to \c{EXTERN} one. The difference is that
-the \c{EXTERN} keyword as of version 2.15 does not generate unknown symbols, as
-this behavior is highly undesirable when using common header files,
-because it might cause the linker to pull in a bunch of unnecessary modules,
-depending on how smart the linker is.
+The \c{REQUIRED} keyword is similar to \c{EXTERN} one. The difference
+is that the \c{EXTERN} keyword as of version 2.15 does not generate
+unknown symbols as that prevents using common header files, as it
+might cause the linker to pull in a bunch of unnecessary modules.

 If the old behavior is required, use \c{REQUIRED} keyword instead.

@@ -5244,7 +5257,7 @@ does. See \k{proborg} for further comments.


 \S{binseg} \c{bin} Extensions to the \c{SECTION}
-Directive\I{SECTION, bin extensions to}
+Directive\I{\c{SECTION}, \c{bin} extensions to}

 The \c{bin} output format extends the \c{SECTION} (or \c{SEGMENT})
 directive to allow you to specify the alignment requirements of
@@ -5557,7 +5570,7 @@ be specified, even if it is the same as the internal name. The
 available attributes are:

 \b \c{resident} indicates that the exported name is to be kept
-resident by the system loader. This is an optimisation for
+resident by the system loader. This is an optimization for
 frequently used symbols imported by name.

 \b \c{nodata} indicates that the exported symbol is a function which
@@ -5701,7 +5714,7 @@ files that Win32 linkers can generate correct output from.


 \S{win32sect} \c{win32} Extensions to the \c{SECTION}
-Directive\I{SECTION, win32 extensions to}
+Directive\I{SECTION, Windows extensions to}

 Like the \c{obj} format, \c{win32} allows you to specify additional
 information on the \c{SECTION} directive line, to control the type
@@ -5847,8 +5860,8 @@ later can still be linked by earlier versions or non-Microsoft linkers.
 \S{codeview} Debugging formats for Windows
 \I{Windows debugging formats}

-The \c{win32} and \c{win64} formats support the Microsoft CodeView
-debugging format.  Currently CodeView version 8 format is supported
+The \c{win32} and \c{win64} formats support the Microsoft \i{CodeView
+debugging format}.  Currently CodeView version 8 format is supported
 (\i\c{cv8}), but newer versions of the CodeView debugger should be
 able to handle this format as well.

@@ -6420,14 +6433,14 @@ of the symbol with code such as:
 \S{elfglob} \c{elf} Extensions to the \c{GLOBAL} Directive\I{GLOBAL,
 elf extensions to}\I{GLOBAL, aoutb extensions to}

-\c{ELF} object files can contain more information about a global symbol
-than just its address: they can contain the \I{symbol sizes,
-specifying}\I{size, of symbols}size of the symbol and its \I{symbol
-types, specifying}\I{type, of symbols}type as well. These are not
-merely debugger conveniences, but are actually necessary when the
-program being written is a \i{shared library}. NASM therefore
-supports some extensions to the \c{GLOBAL} directive, allowing you
-to specify these features.
+\c{ELF} object files can contain more information about a global
+symbol than just its address: they can contain the \I{symbols,
+specifying sizes}\I{size, of symbols}size of the symbol and its
+\I{symbols, specifying types}\I{type, of symbols}type as well. These
+are not merely debugger conveniences, but are actually necessary when
+the program being written is a \I{elf shared library}shared
+library. NASM therefore supports some extensions to the \c{GLOBAL}
+directive, allowing you to specify these features.

 You can specify whether a global variable is a function or a data
 object by suffixing the name with a colon and the word
@@ -6731,7 +6744,7 @@ also, have to be built as \c{.EXE} files, since Windows does not
 support the \c{.COM} format.

 In general, you generate \c{.EXE} files by using the \c{obj} output
-format to produce one or more \i\c{.OBJ} files, and then linking
+format to produce one or more \i\c{.obj} files, and then linking
 them together using a linker. However, NASM also supports the direct
 generation of simple DOS \c{.EXE} files using the \c{bin} output
 format (by using \c{DB} and \c{DW} to construct the \c{.EXE} file
@@ -8060,7 +8073,7 @@ and create \c{library.so.1} as a symbolic link to it.

 This chapter tries to cover some of the issues, largely related to
 unusual forms of addressing and jump instructions, encountered when
-writing operating system code such as protected-mode initialisation
+writing operating system code such as protected-mode initialization
 routines, which require code that operates in mixed segment sizes,
 such as code in a 16-bit segment trying to modify data in a 32-bit
 one, or jumps between different-size segments.
@@ -8571,7 +8584,7 @@ Hence, to disassemble a \c{.COM} file:
 will do the trick.


-\S{ndissync} Code Following Data: Synchronisation
+\S{ndissync} Code Following Data: Synchronization

 Suppose you are disassembling a file which contains some data which
 isn't machine code, and \e{then} contains some machine code. NDISASM
@@ -8590,8 +8603,8 @@ then the correct first instruction in the code section will not be
 seen because the starting point skipped over it. This isn't really
 ideal.

-To avoid this, you can specify a `\i{synchronisation}' point, or indeed
-as many synchronisation points as you like (although NDISASM can
+To avoid this, you can specify a `\i{synchronization}' point, or indeed
+as many synchronization points as you like (although NDISASM can
 only handle 2147483647 sync points internally). The definition of a sync
 point is this: NDISASM guarantees to hit sync points exactly during
 disassembly. If it is thinking about generating an instruction which
@@ -8615,7 +8628,7 @@ As stated above, you can specify multiple sync markers if you need
 to, just by repeating the \c{-s} option.


-\S{ndisisync} Mixed Code and Data: Automatic (Intelligent) Synchronisation
+\S{ndisisync} Mixed Code and Data: Automatic (Intelligent) Synchronization
 \I\c{auto-sync}

 Suppose you are disassembling the boot sector of a \c{DOS} floppy (maybe
@@ -8734,8 +8747,9 @@ the \c{git} distributed source control system.  The link is available
 on the website.  This is recommended only to participate in the
 development of NASM or to assist with testing the development code.

-To build NASM from the \c{git} repository you will need a Perl and, if
-building on a Unix system, GNU autoconf.
+To build NASM from the \c{git} repository you will need a Perl
+interpreter and, if building on a Unix system, GNU autoconf installed
+on your system.

 To build on a Unix system, run:

@@ -8743,6 +8757,14 @@ To build on a Unix system, run:

 to create the \c{configure} script and then build as listed above.

+\H{builddoc} Building the documentation
+
+To build the documentation, you will need a Perl interpreter, a
+Postscript to PDF converter such as Ghostscript, and suitable fonts
+installed on your system. The recommended (and default) fonts are
+Adobe's Source Sans and Source Code fonts, which are freely available
+under the SIL Open Font License.
+
 \A{contact} Contact Information

 \H{website} Website
--- a/doc/psfonts.ph
+++ b/doc/psfonts.ph
@@ -21,33 +21,54 @@ my @QText = ('SourceSansPro-It', 'ClearSans-Italic', 'LiberationSans-Italic',
 	     'Arial-Italic', 'Helvetica-Italic');
 my @QBold = ('SourceSansPro-BoldIt', 'ClearSans-BoldItalic', 'LiberationSans-BoldItalic', 'Arial-Bold', 'Helvetica-BoldItalic');
 my @QCode = ('SourceCodePro-Regular', 'LiberationMono', 'Courier');
+my @XCode = ('SourceCodePro-Regular', 'LiberationMono', 'Courier');

 # The fonts we want to use for various things
 # The order is: <normal> <emphatic> <code>

+my $lf = 1.2;			# Leading scale factor
+my $cf = 0.8;			# Code size scale factor
+
+my $st = 20;
 %TitlFont = (name => 'tfont',
-	     leading => 24,
-	     fonts => [[20, \@TText], [20, \@TItal], [20, \@TCode]]);
+	     leading => $st*$lf,
+	     fonts => [[$st, \@TText], [$st, \@TItal], [$st*$cf, \@TCode]]);
+
+my $sc = 18;
 %ChapFont = (name => 'cfont',
-	     leading => 21.6,
-	     fonts => [[18, \@HText], [18, \@HItal], [18, \@HCode]]);
+	     leading => $sc*$lf,
+	     fonts => [[$sc, \@HText], [$sc, \@HItal], [$sc*$cf, \@HCode]]);
+
+my $sh = 14;
 %HeadFont = (name => 'hfont',
-		leading => 16.8,
-		fonts => [[14, \@HText], [14, \@HItal], [14, \@HCode]]);
+		leading => $sh*$lf,
+		fonts => [[$sh, \@HText], [$sh, \@HItal], [$sh*$cf, \@HCode]]);
+
+my $ss = 12;
 %SubhFont = (name => 'sfont',
-	     leading => 14.4,
-	     fonts => [[12, \@HText], [12, \@HItal], [12, \@HCode]]);
+	     leading => $ss*$lf,
+	     fonts => [[$ss, \@HText], [$ss, \@HItal], [$ss*$cf, \@HCode]]);
+
+my $sb = 10;
 %BodyFont = (name => 'bfont',
-	     leading => 12,
-	     fonts => [[10, \@BText], [10, \@BItal], [10, \@BCode]]);
+	     leading => $sb*$lf,
+	     fonts => [[$sb, \@BText], [$sb, \@BItal], [$sb*$cf, \@BCode]]);
+
+my $sq = 9;
 %BquoFont = (name => 'qfont',
-	     leading => 10.8,
-	     fonts => [[9, \@QText], [9, \@QBold], [9, \@QCode]]);
+	     leading => $sq*$lf,
+	     fonts => [[$sq, \@QText], [$sq, \@QBold], [$sq*$cf, \@QCode]]);
+
+my $sx = $sb*$cf;
+%CodeFont = (name => 'xfont',
+	     leading => $sx*$lf,
+	     fonts => [[$sx, \@XCode], [$sx, \@XCode], [$sx, \@XCode]]);
+
 #
 # List of all fontsets; used to compute the list of fonts needed
 #
@AllFonts = ( \%TitlFont, \%ChapFont, \%HeadFont, \%SubhFont, \%BodyFont,
-    \%BquoFont);
+    \%BquoFont, \%CodeFont );

 # OK
 1;
--- a/include/compiler.h
+++ b/include/compiler.h
@@ -310,6 +310,27 @@ static inline void *mempcpy(void *dst, const void *src, size_t n)
 #define printf_func(fmt, list)     format_func3(printf,fmt,list)
 #define printf_func_ptr(fmt, list) format_func3_ptr(printf,fmt,list)

+/*
+ * A static [inline] function which either is currently unused but
+ * likely to be used in the future, or used only under some #if
+ * combinations.  Mark with this option to suppress compiler
+ * warnings.
+ *
+ * This is better than #if(def) because it still lets the compiler
+ * analyze the function for validity, and it works even for the
+ * conditional use case.
+ *
+ * The macro UNUSED is set to 1 if the unused macro is meaningful,
+ * otherwise 0; this may be useful in some #if statements.
+ */
+#ifdef HAVE_FUNC_ATTRIBUTE_UNUSED
+# define unused __attribute__((unused))
+# define UNUSED 1
+#else
+# define unused
+# define UNUSED 0
+#endif
+
 /* Determine probabilistically if something is a compile-time constant */
 #ifdef HAVE___BUILTIN_CONSTANT_P
 # if defined(__GNUC__) && (__GNUC__ >= 5)
--- a/include/strlist.h
+++ b/include/strlist.h
@@ -1,6 +1,6 @@
 /* ----------------------------------------------------------------------- *
 *
- *   Copyright 1996-2018 The NASM Authors - All Rights Reserved
+ *   Copyright 1996-2020 The NASM Authors - All Rights Reserved
 *   See the file AUTHORS included with the NASM distribution for
 *   the specific copyright holders.
 *
@@ -78,10 +78,10 @@ static inline size_t strlist_size(const struct strlist *list)
 }

 struct strlist safe_alloc *strlist_alloc(bool uniq);
-const struct strlist_entry * never_null strlist_add(struct strlist *list, const char *str);
-const struct strlist_entry * printf_func(2, 3) never_null
+const struct strlist_entry *strlist_add(struct strlist *list, const char *str);
+const struct strlist_entry * printf_func(2, 3)
 	strlist_printf(struct strlist *list, const char *fmt, ...);
-const struct strlist_entry * never_null
+const struct strlist_entry *
 	strlist_vprintf(struct strlist *list, const char *fmt, va_list ap);
 const struct strlist_entry *
 strlist_find(const struct strlist *list, const char *str);
--- a/macros/macros.pl
+++ b/macros/macros.pl
@@ -276,19 +276,19 @@ print OUT "    };\n";
 # Put a large value in unused slots.  This makes it extremely unlikely
 # that any combination that involves unused slot will pass the range test.
 # This speeds up rejection of unrecognized tokens, i.e. identifiers.
-print OUT "#define UNUSED (65535/3)\n";
+print OUT "#define UNUSED_HASH_ENTRY (65535/3)\n";

 print OUT "    static const int16_t hash1[$n] = {\n";
 for ($i = 0; $i < $n; $i++) {
    my $h = ${$g}[$i*2+0];
-    print OUT "        ", defined($h) ? $h : 'UNUSED', ",\n";
+    print OUT "        ", defined($h) ? $h : 'UNUSED_HASH_ENTRY', ",\n";
 }
 print OUT "    };\n";

 print OUT "    static const int16_t hash2[$n] = {\n";
 for ($i = 0; $i < $n; $i++) {
    my $h = ${$g}[$i*2+1];
-    print OUT "        ", defined($h) ? $h : 'UNUSED', ",\n";
+    print OUT "        ", defined($h) ? $h : 'UNUSED_HASH_ENTRY', ",\n";
 }
 print OUT "    };\n";

--- a/nasmlib/perfhash.pl
+++ b/nasmlib/perfhash.pl
@@ -334,18 +334,18 @@ if ($output eq 'h') {
    }
    print F "\n};\n\n";

-    print F "#define UNUSED (65536/3)\n\n";
+    print F "#define UNUSED_HASH_ENTRY (65536/3)\n\n";

    printf F "static const int16_t %s_hashvals[%d] = ", $name, $n*2;
    $c = '{';
    for (my $i = 0; $i < $n; $i++) {
 	my $h = ${$g}[$i*2+0];
-	print F "$c\n    ", defined($h) ? $h : 'UNUSED';
+	print F "$c\n    ", defined($h) ? $h : 'UNUSED_HASH_ENTRY';
 	$c = ',';
    }
    for (my $i = 0; $i < $n; $i++) {
 	my $h = ${$g}[$i*2+1];
-	print F "$c\n    ", defined($h) ? $h : 'UNUSED';
+	print F "$c\n    ", defined($h) ? $h : 'UNUSED_HASH_ENTRY';
 	$c = ',';
    }
    print F "\n};\n\n";
--- a/nasmlib/strlist.c
+++ b/nasmlib/strlist.c
@@ -1,6 +1,6 @@
 /* ----------------------------------------------------------------------- *
 *
- *   Copyright 1996-2018 The NASM Authors - All Rights Reserved
+ *   Copyright 1996-2020 The NASM Authors - All Rights Reserved
 *   See the file AUTHORS included with the NASM distribution for
 *   the specific copyright holders.
 *
@@ -102,7 +102,8 @@ strlist_add(struct strlist *list, const char *str)
 const struct strlist_entry *
 strlist_vprintf(struct strlist *list, const char *fmt, va_list ap)
 {
-	struct strlist_entry *e;
+	/* clang miscompiles offsetin() unless e is initialized here */
+	struct strlist_entry *e = NULL;
 	struct hash_insert hi;

 	if (!list)
--- a/test/dup.asm
+++ b/test/dup.asm
@@ -19,3 +19,18 @@

 	dd 16 dup (0xaaaa, ?, 0xbbbbbb)
 	dd 64 dup (?)
+
+	resb 1
+	resb 2
+	resb 4
+	resb 8
+
+	resw 1
+	resw 2
+	resw 4
+	resw 8
+
+	resq 1
+	resq 2
+	resq 4
+	resq 8
--- a/test/emptyarg.asm
+++ b/test/emptyarg.asm
@@ -1 +0,0 @@
-../../nasm-2.14.xx/test/emptyarg.asm
--- a/test/emptyarg.asm
+++ b/test/emptyarg.asm
@@ -0,0 +1,147 @@
+%define EMPTY
+
+%macro bar 1
+	db "bar", __LINE__, %0, %1
+%endmacro
+
+%macro baz 2
+	db "baz", __LINE__, %0, %1, %2
+%endmacro
+
+%macro nothing 0
+	db "nothing", __LINE__, %0
+%endmacro
+
+%macro xyzzy 1-2
+	db "xyzzy", __LINE__, %0, %1, %2, %3
+%endmacro
+
+%macro vararg 0-*
+	db "vararg", __LINE__, %0
+	%assign %%i 1
+	%rep %0
+	  db "vararg arg ", %%i, %1
+	  %rotate 1
+	  %assign %%i %%i + 1
+	%endrep
+%endmacro
+
+%macro defargs 1-5 def2, def3, def4, def5
+	db "defargs", __LINE__, %0, %1, %2, %3, %4, %5
+%endmacro
+
+%macro ivar 1
+	vararg %1
+%endmacro
+
+%macro foo 1-2
+	db "foo", __LINE__, %0, %1, %2
+	bar %2
+	bar {%2}
+	bar %2,
+	bar {%2},
+	baz %1,%2
+	baz {%1},{%2}
+	nothing %1
+	nothing %2
+	xyzzy "meep",%1,%2,
+	xyzzy "meep","meep",%1,%2
+	xyzzy "alpha","bravo",
+	xyzzy "with","empty",EMPTY
+%endmacro
+
+%macro orange 1
+	db %{1:1}
+%endmacro
+
+%macro prange1 2-3
+	db %{1:2}, 0%3
+%endmacro
+
+%macro prange2 1-3 'two', 'three'
+	db %{1:3}
+%endmacro
+
+	db 4,
+	nothing
+	nothing 1
+	nothing			; foo
+	nothing EMPTY
+
+flup:	foo 1,2
+	foo 3
+	bar
+	bar EMPTY
+	foo 6,
+	foo 6,			; With space/comment
+	foo 6,EMPTY
+	baz 8,EMPTY
+	foo 6,{}
+	foo ,5
+
+	xyzzy 13,14,15,
+	xyzzy 13,14,15,EMPTY
+	xyzzy 20,21
+	xyzzy 22,23,
+	xyzzy 24,25,EMPTY
+	xyzzy 26,27,,
+	xyzzy 28,29,EMPTY,EMPTY
+
+	vararg
+	vararg EMPTY
+	vararg ,
+	vararg 10
+	vararg 11,
+	vararg 12,EMPTY
+	vararg 13,14,15,
+	vararg 13,14,15,EMPTY
+	vararg 20,21
+	vararg 22,23,
+	vararg 24,25,EMPTY
+	vararg 26,27,,
+	vararg 28,29,EMPTY,EMPTY
+
+	ivar {}
+	ivar {EMPTY}
+	ivar EMPTY
+	ivar ,
+	ivar {,}
+	ivar {60}
+	ivar {61,}
+	ivar {62,EMPTY}
+	ivar {63,64,65,}
+	ivar {63,64,65,EMPTY}
+	ivar {70,71}
+	ivar {72,73,}
+	ivar {74,75,EMPTY}
+	ivar {76,77,,}
+	ivar {78,79,EMPTY,EMPTY}
+
+	defargs EMPTY
+	defargs 91
+	defargs 91,92
+	defargs 91,92,93
+	defargs 91,92,93,94
+	defargs 91,92,93,94,95
+	defargs ,
+	defargs 91,
+	defargs 91,92,
+	defargs 91,92,93,
+	defargs 91,92,93,94,
+	defargs 91,92,93,94,95,
+
+	prange1 101
+	prange1 101, 102
+	prange1 101, 102, 103
+	prange2 121
+	prange2 121, 122
+	prange2 121, 122, 123
+	prange2 {121}
+	prange2 {121,121}
+	prange2 {121},{122}
+	prange2 {121},122,{123}
+	prange2 121,{122,122},123
+
+	orange 130
+	orange 130, 131
+	orange {130, 131}