Merge branch 'evalmacro'

Resolved Conflicts:
	asm/preproc.c
	output/elf.h
	output/outelf.c
	output/outelf.h
	version

Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>

asm/pptok.dat

@@ -1,6 +1,6 @@
 ## --------------------------------------------------------------------------
 ##   
-##   Copyright 1996-2016 The NASM Authors - All Rights Reserved
+##   Copyright 1996-2019 The NASM Authors - All Rights Reserved
 ##   See the file AUTHORS included with the NASM distribution for
 ##   the specific copyright holders.
 ##
@@ -70,8 +70,12 @@
 %ideftok
 %if*
 %imacro
-%irmacro
 %include
+%ipathsearch
+%irmacro
+%istrcat
+%istrlen
+%isubstr
 %ixdefine
 %line
 %local

asm/quote.c

@@ -215,6 +215,14 @@ static char *emit_utf8(char *q, int32_t v)
     return q;
 }
 
+/*
+ * Quote a C string
+ */
+char *nasm_quote_cstr(const char *str)
+{
+    return nasm_quote(str, strlen(str));
+}
+
 /*
  * Do an *in-place* dequoting of the specified string, returning the
  * resulting length (which may be containing embedded nulls.)

asm/quote.h

@@ -37,6 +37,7 @@
 #include "compiler.h"
 
 char *nasm_quote(const char *str, size_t len);
+char *nasm_quote_cstr(const char *str);
 size_t nasm_unquote(char *str, char **endptr);
 char *nasm_skip_string(char *str);
 

configure.ac

@@ -42,6 +42,11 @@ AS_IF([$pa_no_optimize],
       [PA_ADD_CFLAGS([-O0])
        PA_ADD_CFLAGS([-fno-omit-frame-pointer])])
 
+dnl Profiling
+PA_ARG_ENABLED([profiling],
+ [compile with profiling (-pg option)],
+ [PA_ADD_CFLAGS([-pg])])
+
 dnl Abort on panic
 PA_ARG_ENABLED([panic-abort],
  [call abort() on panic to trap in the debugger],

doc/changes.src

@@ -18,6 +18,14 @@ since 2007.
 \b Suppress nuisance "\c{label changed during code generation}" messages
 after a real error.
 
+\b Add support for the \c{merge} and \c{strings} attributes on ELF
+sections. See \k{elfsect}.
+
+\b Add support for the \c{note}, \c{preinit_array}, \c{init_array},
+and \c{fini_array} sections type in ELF. See \k{elfsect}.
+
+\b Handle more than 32,633 sections in ELF.
+
 \S{cl-2.14.02} Version 2.14.02
 
 \b Fix crash due to multiple errors or warnings during the code

doc/nasmdoc.src

@@ -122,15 +122,14 @@
 \IR{- opunary} \c{-} operator, unary
 \IR{! opunary} \c{!} operator, unary
 \IR{alignment, in bin sections} alignment, in \c{bin} sections
-\IR{alignment, in elf sections} alignment, in \c{elf} sections
+\IR{alignment, in elf sections} alignment, in ELF sections
 \IR{alignment, in win32 sections} alignment, in \c{win32} sections
-\IR{alignment, of elf common variables} alignment, of \c{elf} common
+\IR{alignment, of elf common variables} alignment, of ELF common
 variables
 \IR{alignment, in obj sections} alignment, in \c{obj} sections
 \IR{a.out, bsd version} \c{a.out}, BSD version
 \IR{a.out, linux version} \c{a.out}, Linux version
-\IR{autoconf} Autoconf
-\IR{bin} bin
+\IR{bin} \c{bin} output format
 \IR{bitwise and} bitwise AND
 \IR{bitwise or} bitwise OR
 \IR{bitwise xor} bitwise XOR
@@ -150,8 +149,8 @@ variables
 \IR{codeview} CodeView debugging format
 \IR{common object file format} Common Object File Format
 \IR{common variables, alignment in elf} common variables, alignment
-in \c{elf}
-\IR{common, elf extensions to} \c{COMMON}, \c{elf} extensions to
+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
 \IR{default-wrt mechanism} default-\c{WRT} mechanism
@@ -165,7 +164,8 @@ in \c{elf}
 \IA{effective address}{effective addresses}
 \IA{effective-address}{effective addresses}
 \IR{elf} ELF
-\IR{elf, 16-bit code and} ELF, 16-bit code and
+\IR{elf, 16-bit code} ELF, 16-bit code
+\IR{elf, debug formats} ELF, debug formats
 \IR{elf shared libraries} ELF, shared libraries
 \IR{elf32} \c{elf32}
 \IR{elf64} \c{elf64}
@@ -181,7 +181,7 @@ in \c{elf}
 \IR{functions, pascal calling convention} functions, Pascal calling
 convention
 \IR{global, aoutb extensions to} \c{GLOBAL}, \c{aoutb} extensions to
-\IR{global, elf extensions to} \c{GLOBAL}, \c{elf} extensions to
+\IR{global, elf extensions to} \c{GLOBAL}, ELF extensions to
 \IR{global, rdf extensions to} \c{GLOBAL}, \c{rdf} extensions to
 \IR{got} GOT
 \IR{got relocations} \c{GOT} relocations
@@ -238,16 +238,16 @@ convention
 Object File Format
 \IR{relocations, pic-specific} relocations, PIC-specific
 \IA{repeating}{repeating code}
-\IR{section alignment, in elf} section alignment, in \c{elf}
+\IR{section alignment, in elf} section alignment, in ELF
 \IR{section alignment, in bin} section alignment, in \c{bin}
 \IR{section alignment, in obj} section alignment, in \c{obj}
 \IR{section alignment, in win32} section alignment, in \c{win32}
-\IR{section, elf extensions to} \c{SECTION}, \c{elf} extensions to
+\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{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}, \c{elf} extensions to
+\IR{segment, obj extensions to} \c{SEGMENT}, ELF extensions to
 \IR{segment names, borland pascal} segment names, Borland Pascal
 \IR{shift command} \c{shift} command
 \IA{sib}{sib byte}
@@ -259,6 +259,8 @@ Object File Format
 \IR{symbols, exporting from dlls} symbols, exporting from DLLs
 \IR{symbols, importing from dlls} symbols, importing from DLLs
 \IR{test subdirectory} \c{test} subdirectory
+\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{underscore, in c symbols} underscore, in C symbols
 \IR{unicode} Unicode
@@ -295,16 +297,16 @@ Object File Format
 
 The Netwide Assembler, NASM, is an 80x86 and x86-64 assembler designed
 for portability and modularity. It supports a range of object file
-formats, including Linux and \c{*BSD} \c{a.out}, \c{ELF}, \c{COFF},
-\c{Mach-O}, 16-bit and 32-bit \c{OBJ} (OMF) format, \c{Win32} and
-\c{Win64}. It will also output plain binary files, Intel hex and
+formats, including Linux and *BSD \c{a.out}, ELF, Mach-O, 16-bit and
+32-bit \c{.obj} (OMF) format, COFF (including its Win32 and Win64
+variants.) It can also output plain binary files, Intel hex and
 Motorola S-Record formats. Its syntax is designed to be simple and
 easy to understand, similar to the syntax in the Intel Software
 Developer Manual with minimal complexity. It supports all currently
 known x86 architectural extensions, and has strong support for macros.
 
-NASM also comes with a set of utilities for handling the \c{RDOFF}
-custom object-file format.
+NASM also comes with a set of utilities for handling its own RDOFF2
+object-file format.
 
 \S{legal} \i{License} Conditions
 
@@ -352,7 +354,7 @@ For example,
 
 \c nasm -f elf myfile.asm
 
-will assemble \c{myfile.asm} into an \c{ELF} object file \c{myfile.o}. And
+will assemble \c{myfile.asm} into an ELF object file \c{myfile.o}. And
 
 \c nasm -f bin myfile.asm -o myfile.com
 
@@ -374,7 +376,7 @@ The option \c{-hf} will also list the available output file formats,
 and what they are.
 
 If you use Linux but aren't sure whether your system is \c{a.out}
-or \c{ELF}, type
+or ELF, type
 
 \c file nasm
 
@@ -4298,7 +4300,7 @@ operating in 16-bit mode, 32-bit mode or 64-bit mode. The syntax is
 \c{BITS XX}, where XX is 16, 32 or 64.
 
 In most cases, you should not need to use \c{BITS} explicitly. The
-\c{aout}, \c{coff}, \c{elf}, \c{macho}, \c{win32} and \c{win64}
+\c{aout}, \c{coff}, \c{elf*}, \c{macho}, \c{win32} and \c{win64}
 object formats, which are designed for use in 32-bit or 64-bit
 operating systems, all cause NASM to select 32-bit or 64-bit mode,
 respectively, by default. The \c{obj} object format allows you
@@ -4575,9 +4577,8 @@ refer to symbols which \e{are} defined in the same module as the
 \c         ; some code
 
 \c{GLOBAL}, like \c{EXTERN}, allows object formats to define private
-extensions by means of a colon. The \c{elf} object format, for
-example, lets you specify whether global data items are functions or
-data:
+extensions by means of a colon. The ELF object format, for example,
+lets you specify whether global data items are functions or data:
 
 \c global  hashlookup:function, hashtable:data
 
@@ -4608,8 +4609,8 @@ at the same piece of memory.
 
 Like \c{GLOBAL} and \c{EXTERN}, \c{COMMON} supports object-format
 specific extensions. For example, the \c{obj} format allows common
-variables to be NEAR or FAR, and the \c{elf} format allows you to
-specify the alignment requirements of a common variable:
+variables to be NEAR or FAR, and the ELF format allows you to specify
+the alignment requirements of a common variable:
 
 \c common  commvar  4:near  ; works in OBJ
 \c common  intarray 100:4   ; works in ELF: 4 byte aligned
@@ -4681,7 +4682,7 @@ For example, when mangling local symbols via the generic namespace:
 This is useful when the directive is needed to be output format
 agnostic.
 
-The example is also euquivalent to this, when the output format is \c{elf}:
+The example is also euquivalent to this, when the output format is ELF:
 
 \c      %pragma elf gprefix _
 
@@ -5833,7 +5834,7 @@ Format} Object Files
 The \c{elf32}, \c{elf64} and \c{elfx32} output formats generate
 \c{ELF32 and ELF64} (Executable and Linkable Format) object files, as
 used by Linux as well as \i{Unix System V}, including \i{Solaris x86},
-\i{UnixWare} and \i{SCO Unix}. \c{elf} provides a default output
+\i{UnixWare} and \i{SCO Unix}. ELF provides a default output
 file-name extension of \c{.o}. \c{elf} is a synonym for \c{elf32}.
 
 The \c{elfx32} format is used for the \i{x32} ABI, which is a 32-bit
@@ -5847,8 +5848,8 @@ target operating system (OSABI).  This field can be set by using the
 system. If this directive is not used, the default value will be "UNIX
 System V ABI" (0) which will work on most systems which support ELF.
 
-\S{elfsect} \c{elf} extensions to the \c{SECTION} Directive
-\I{SECTION, elf extensions to}
+\S{elfsect} ELF extensions to the \c{SECTION} Directive
+\I{SECTION, ELF extensions to}
 
 Like the \c{obj} format, \c{elf} allows you to specify additional
 information on the \c{SECTION} directive line, to control the type
@@ -5873,13 +5874,52 @@ not.
 
 \b \i\c{progbits} defines the section to be one with explicit contents
 stored in the object file: an ordinary code or data section, for
-example, \i\c{nobits} defines the section to be one with no explicit
+example.
+
+\b \i\c{nobits} defines the section to be one with no explicit
 contents given, such as a BSS section.
 
-\b \c{align=}, used with a trailing number as in \c{obj}, gives the
+\b \i\c{note} indicates that this section contains ELF notes. The
+content of ELF notes are specified using normal assembly instructions;
+it is up to the programmer to ensure these are valid ELF notes.
+
+\b \i\c{preinit_array} indicates that this section contains function
+addresses to be called before any other initialization has happened.
+
+\b \i\c{init_array} indicates that this section contains function
+addresses to be called during initialization.
+
+\b \i\c{fini_array} indicates that this section contains function
+pointers to be called during termination.
+
+\b \I{align, ELF attribute}\c{align=}, used with a trailing number as in \c{obj}, gives the
 \I{section alignment, in elf}\I{alignment, in elf sections}alignment
 requirements of the section.
 
+\b \c{byte}, \c{word}, \c{dword}, \c{qword}, \c{tword}, \c{oword},
+\c{yword}, or \c{zword} with an optional \c{*}\i{multiplier} specify
+the fundamental data item size for a section which contains either
+fixed-sized data structures or strings; it also sets a default
+alignment. This is generally used with the \c{strings} and \c{merge}
+attributes (see below.) For example \c{byte*4} defines a unit size of
+4 bytes, with a default alignment of 1; \c{dword} also defines a unit
+size of 4 bytes, but with a default alignment of 4. The \c{align=}
+attribute, if specified, overrides this default alignment.
+
+\b \I{pointer, ELF attribute}\c{pointer} is equivalent to \c{dword}
+for \c{elf32} or \c{elfx32}, and \c{qword} for \c{elf64}.
+
+\b \I{strings, ELF attribute}\c{strings} indicate that this section
+contains exclusively null-terminated strings. By default these are
+assumed to be byte strings, but a size specifier can be used to
+override that.
+
+\b \i\c{merge} indicates that duplicate data elements in this section
+should be merged with data elements from other object files. Data
+elements can be either fixed-sized objects or null-terminatedstrings
+(with the \c{strings} attribute.) A size specifier is required unless
+\c{strings} is specified, in which case the size defaults to \c{byte}.
+
 \b \i\c{tls} defines the section to be one which contains
 thread local variables.
 
@@ -5899,6 +5939,10 @@ qualifiers are:
 \c section .tdata         progbits      alloc   noexec  write    align=4   tls
 \c section .tbss          nobits        alloc   noexec  write    align=4   tls
 \c section .comment       progbits      noalloc noexec  nowrite  align=1
+\c section .preinit_array preinit_array alloc   noexec  nowrite  pointer
+\c section .init_array    init_array    alloc   noexec  nowrite  pointer
+\c section .fini_array    fini_array    alloc   noexec  nowrite  pointer
+\c section .note          note          noalloc noexec  nowrite  align=4
 \c section other          progbits      alloc   noexec  nowrite  align=1
 
 (Any section name other than those in the above table
@@ -5906,7 +5950,7 @@ qualifiers are:
  Please note that section names are case sensitive.)
 
 
-\S{elfwrt} \i{Position-Independent Code}\I{PIC}: \c{macho} Special
+\S{elfwrt} \i{Position-Independent Code}\I{PIC}: ELF Special
 Symbols and \i\c{WRT}
 
 Since \c{ELF} does not support segment-base references, the \c{WRT}
@@ -6044,7 +6088,7 @@ requires that it be aligned on a 4-byte boundary.
 
 
 \S{elf16} 16-bit code and ELF
-\I{ELF, 16-bit code and}
+\I{ELF, 16-bit code}
 
 The \c{ELF32} specification doesn't provide relocations for 8- and
 16-bit values, but the GNU \c{ld} linker adds these as an extension.
@@ -6054,7 +6098,7 @@ be linked as ELF using GNU \c{ld}. If NASM is used with the
 these relocations is generated.
 
 \S{elfdbg} Debug formats and ELF
-\I{ELF, Debug formats and}
+\I{ELF, debug formats}
 
 ELF provides debug information in \c{STABS} and \c{DWARF} formats.
 Line number information is generated for all executable sections, but please
@@ -8142,7 +8186,7 @@ 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\c{synchronisation}' point, or indeed
+To avoid this, you can specify a `\i{synchronisation}' point, or indeed
 as many synchronisation 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

macros/standard.mac

@@ -49,12 +49,6 @@ STD: nasm
 ; here, not all of them are: the user-level form of a format-specific
 ; directive should be defined in the module for that directive.
 
-; These three need to be defined, though the actual definitions will
-; be constantly updated during preprocessing.
-%define __FILE__
-%define __LINE__
-%define __BITS__
-
 %define __SECT__            ; it ought to be defined, even if as nothing
 
 %imacro section 1+.nolist

nasmlib/saa.c

@@ -262,9 +262,12 @@ void saa_fread(struct SAA *s, size_t posn, void *data, size_t len)
 void saa_fwrite(struct SAA *s, size_t posn, const void *data, size_t len)
 {
     size_t ix;
+    size_t padding = 0;
 
-    /* Seek beyond the end of the existing array not supported */
-    nasm_assert(posn <= s->datalen);
+    if (posn > s->datalen) {
+        padding = posn - s->datalen;
+        posn = s->datalen;
+    }
 
     if (likely(s->blk_len == SAA_BLKLEN)) {
         ix = posn >> SAA_BLKSHIFT;
@@ -281,6 +284,9 @@ void saa_fwrite(struct SAA *s, size_t posn, const void *data, size_t len)
         s->wblk--;
     }
 
+    if (padding)
+        saa_wbytes(s, NULL, padding);
+
     saa_wbytes(s, data, len);
 }
 

output/elf.h

@@ -160,7 +160,11 @@
 #define SHT_REL         9
 #define SHT_SHLIB       10
 #define SHT_DYNSYM      11
-#define SHT_NUM		12
+#define SHT_INIT_ARRAY	14
+#define SHT_FINI_ARRAY	15
+#define SHT_PREINIT_ARRAY 16
+#define SHT_GROUP	17
+#define SHT_SYMTAB_SHNDX 18
 #define SHT_LOPROC      0x70000000
 #define SHT_HIPROC      0x7fffffff
 #define SHT_LOUSER      0x80000000
@@ -179,14 +183,25 @@
 #define SHF_TLS			(1 << 10)	/* Section hold thread-local data */
 
 /* Special section numbers */
-#define SHN_UNDEF	0
+#define SHN_UNDEF       0x0000
 #define SHN_LORESERVE   0xff00
 #define SHN_LOPROC      0xff00
 #define SHN_HIPROC      0xff1f
 #define SHN_ABS         0xfff1
 #define SHN_COMMON      0xfff2
+#define SHN_XINDEX	0xffff
 #define SHN_HIRESERVE   0xffff
 
+/* Same, but signed/sign-extended */
+#define XSHN_UNDEF      ((int16_t)SHN_UNDEF)
+#define XSHN_LORESERVE  ((int16_t)SHN_LORESERVE)
+#define XSHN_LOPROC     ((int16_t)SHN_LOPROC)
+#define XSHN_HIPROC     ((int16_t)SHN_HIPROC)
+#define XSHN_ABS        ((int16_t)SHN_ABS)
+#define XSHN_COMMON     ((int16_t)SHN_COMMON)
+#define XSHN_XINDEX     ((int16_t)SHN_XINDEX)
+#define XSHN_HIRESERVE  ((int16_t)SHN_HIRESERVE)
+
 /* Section align flag */
 #define SHA_ANY		1	/* No alignment constraint */
 

output/outelf.h

@@ -1,6 +1,6 @@
 /* ----------------------------------------------------------------------- *
  *
- *   Copyright 1996-2009 The NASM Authors - All Rights Reserved
+ *   Copyright 1996-2019 The NASM Authors - All Rights Reserved
  *   See the file AUTHORS included with the NASM distribution for
  *   the specific copyright holders.
  *
@@ -53,31 +53,14 @@
 /* this stuff is needed for the dwarf/stabs debugging format */
 #define TY_DEBUGSYMLIN 0x40     /* internal call to debug_out */
 
-/* Known sections with nonstandard defaults */
-struct elf_known_section {
-    const char *name;   /* Name of section */
-    int type;           /* Section type (SHT_) */
-    uint32_t flags;     /* Section flags (SHF_) */
-    uint32_t align;     /* Section alignment */
-};
-extern const struct elf_known_section elf_known_sections[];
-
 /*
- * Special ELF sections (after the real sections but before debugging ones)
- */
-#define sec_shstrtab            (nsects + 1)
-#define sec_symtab              (nsects + 2)
-#define sec_strtab              (nsects + 3)
-#define sec_numspecial          3
-
-/*
- * Debugging ELF sections (last in the file)
+ * Debugging ELF sections (section indicies starting with sec_debug)
  */
 
 /* stabs */
-#define sec_stab                (nsections-3)
-#define sec_stabstr             (nsections-2)
-#define sec_rel_stab            (nsections-1)
+#define sec_stab                (sec_debug + 0)
+#define sec_stabstr             (sec_debug + 1)
+#define sec_rel_stab            (sec_debug + 2)
 
 /* stabs symbol table format */
 struct stabentry {
@@ -89,16 +72,16 @@ struct stabentry {
 };
 
 /* dwarf */
-#define sec_debug_aranges       (nsections-10)
-#define sec_rela_debug_aranges  (nsections-9)
-#define sec_debug_pubnames      (nsections-8)
-#define sec_debug_info          (nsections-7)
-#define sec_rela_debug_info     (nsections-6)
-#define sec_debug_abbrev        (nsections-5)
-#define sec_debug_line          (nsections-4)
-#define sec_rela_debug_line     (nsections-3)
-#define sec_debug_frame         (nsections-2)
-#define sec_debug_loc           (nsections-1)
+#define sec_debug_aranges       (sec_debug + 0)
+#define sec_rela_debug_aranges  (sec_debug + 1)
+#define sec_debug_pubnames      (sec_debug + 2)
+#define sec_debug_info          (sec_debug + 3)
+#define sec_rela_debug_info     (sec_debug + 4)
+#define sec_debug_abbrev        (sec_debug + 5)
+#define sec_debug_line          (sec_debug + 6)
+#define sec_rela_debug_line     (sec_debug + 7)
+#define sec_debug_frame         (sec_debug + 8)
+#define sec_debug_loc           (sec_debug + 9)
 
 extern uint8_t elf_osabi;
 extern uint8_t elf_abiver;
@@ -137,14 +120,15 @@ struct elf_section {
     uint64_t            len;
     uint64_t            size;
     uint64_t            nrelocs;
-    int32_t             index;
-    int                 type;           /* SHT_PROGBITS or SHT_NOBITS */
+    int32_t             index;		/* NASM index or NO_SEG if internal */
+    int			shndx;          /* ELF index */
+    int                 type;           /* SHT_* */
     uint64_t            align;          /* alignment: power of two */
     uint64_t            flags;          /* section flags */
     int64_t		pass_last_seen;
+    uint64_t		entsize;        /* entry size */
     char                *name;
     struct SAA          *rel;
-    uint64_t             rellen;
     struct elf_reloc    *head;
     struct elf_reloc    **tail;
     struct rbtree       *gsyms;         /* global symbols in section */

test/evalmacro.asm

@@ -0,0 +1,4 @@
+%define tonum(=x) x
+
+	dd tonum(1+3)
+	dd tonum(5*7)

test/fewsecs.asm

@@ -0,0 +1,2 @@
+%assign NSECS 64
+%include "manysecs.asm"

test/manysecs.asm

@@ -0,0 +1,15 @@
+%ifndef NSECS
+  %assign NSECS 16384
+%endif
+
+%assign NSECS ((NSECS+3) & ~3)
+
+%assign n 0
+%rep NSECS
+  %assign gcom (n & ~3)	+ 2
+	section .text %+ n progbits exec
+start_ %+ n:
+	nop
+	jmp start_ %+ gcom
+  %assign n n+1
+%endrep

test/moresecs.asm

@@ -0,0 +1,3 @@
+; Less than 65,279 data sections, but more total sections
+%assign NSECS 37600
+%include "manysecs.asm"

test/mostsecs.asm

@@ -0,0 +1,3 @@
+; More than 65,279 data sections
+%assign NSECS 131072
+%include "manysecs.asm"