added a helper build.sh script

1 files changed, 242 insertions, 0 deletions

diff --git a/ecomp-c/build.sh b/ecomp-c/build.sh
new file mode 100755
index 0000000..b146182
--- /dev/null
+++ b/ecomp-c/build.sh
@@ -0,0 +1,242 @@
+#!/bin/bash
+
+BINARY=${1:-ec}
+COMPILER=${2:-gcc}
+MODE=${3:-freestanding}
+LEVEL=${4:-0}
+
+DEBUG=0
+
+declare -a MODULES
+MODULES+=("libc-${MODE}.c")
+MODULES+=("$BINARY.c")
+
+case "${COMPILER}" in
+	gcc)
+		CFLAGS="-m32 -march=i386 -Werror -Wno-noreturn -Wall -pedantic -std=c89 -x c"
+		;;
+	clang)
+		CFLAGS="-m32 -march=i386 -Werror -Wall -pedantic -std=c89 -x c"
+		;;
+	pcc)
+		CFLAGS="-march=i386 -Werror -Wall -std=c89 -x c"
+		;;
+	tcc)
+		CFLAGS="-m32 -march=i386 -Werror -Wall -std=c89"
+esac
+
+case "${LEVEL}" in
+	0|1|2|3)
+		CFLAGS+=" -O${LEVEL}"
+		;;
+	d)
+		CFLAGS+=" -g -O0"
+		DEBUG=1
+		;;
+esac
+
+case "${COMPILER}:${MODE}" in
+	gcc:freestanding)
+		CFLAGS+=" -ffreestanding -fno-stack-protector -nostdlib -emain -fno-pic -fno-omit-frame-pointer"
+		;;
+	clang:freestanding)
+		CFLAGS+=" -ffreestanding -fno-stack-protector -nostdlib -Wl,-emain -fno-omit-frame-pointer"
+		;;
+	pcc:freestanding)
+		CFLAGS+=" -ffreestanding -nostdlib -Wl,-emain"
+		;;
+	tcc:freestanding)
+		CFLAGS+=" -fno-bultin -nostdlib"
+		MODULES+=("_start-stub.c")
+		;;
+	*:hosted)
+		CFLAGS+=" -lbsd"
+		;;
+esac
+
+if [ "${DEBUG}" = 1 ]; then
+	cat ${MODULES[@]} > "${BINARY}_tmp.c"
+	${COMPILER} ${CFLAGS} -o ${BINARY} "${BINARY}_tmp.c"
+else
+	cat ${MODULES[@]} | ${COMPILER} ${CFLAGS} -o ${BINARY} -
+fi
+
+exit 0
+#TODO: amalgamation xxx.c or stding -x c -
+
+# debbuging freestanding compiler
+cat libc-freestanding.c ec.c > test.c
+gcc -g -O0 -m32 -march=i386 -ffreestanding -fno-stack-protector -nostdlib -emain -Werror -Wno-noreturn -Wall -pedantic -fno-pic -std=c89 -o ec test.c
+
+assembler
+---------
+
+cat libc-freestanding.c asm-i386.c | gcc -g -O0 -m32 -march=i386 -ffreestanding -fno-stack-protector -nostdlib -emain -Werror -Wno-noreturn -Wall -pedantic -fno-pic -std=c89 -o asm-i386 -x c -
+# optimized with own libc, syscalls need -fno-omit-frame-pointer otherwise they clobber the stack
+cat libc-freestanding.c asm-i386.c | gcc -g -O1 -m32 -march=i386 -fno-omit-frame-pointer -ffreestanding -fno-stack-protector -nostdlib -emain -Werror -Wno-noreturn -Wall -pedantic -fno-pic -std=c89 -o asm-i386 -x c -
+cat libc-freestanding.c asm-i386.c | gcc -g -O2 -m32 -march=i386 -fno-omit-frame-pointer -ffreestanding -fno-stack-protector -nostdlib -emain -Werror -Wno-noreturn -Wall -pedantic -fno-pic -std=c89 -o asm-i386 -x c -
+cat libc-freestanding.c asm-i386.c | gcc -g -O3 -m32 -march=i386 -fno-omit-frame-pointer -ffreestanding -fno-stack-protector -nostdlib -emain -Werror -Wno-noreturn -Wall -pedantic -fno-pic -std=c89 -o asm-i386 -x c -
+
+# to use libc and syscall of the host
+cat libc-hosted.c asm-i386.c | gcc -g -O0 -m32 -march=i386 -fno-stack-protector -Werror -Wno-noreturn -Wall -pedantic -fno-pic -std=c89 -o asm-i386 -x c - -lbsd
+cat libc-hosted.c asm-i386.c | gcc -g -O3 -m32 -march=i386 -Werror -Wall -pedantic -std=c89 -o asm-i386.c -lbsd -x c -
+
+cat libc-freestanding.c asm-i386.c | clang -g -O0 -m32 -march=i386 -ffreestanding -fno-stack-protector -nostdlib -Wl,-emain -Werror -Wall -pedantic -std=c89 -o asm-i386 -x c -
+# ENOSYS in syscall wrappers, is the optimizer clobbering something here?
+cat libc-freestanding.c asm-i386.c | clang -g -O1 -m32 -march=i386 -fno-omit-frame-pointer  -ffreestanding -fno-stack-protector -nostdlib -Wl,-emain -Werror -Wall -pedantic -std=c89 -o asm-i386 -x c -
+cat libc-freestanding.c asm-i386.c | clang -g -O2 -m32 -march=i386 -fno-omit-frame-pointer  -ffreestanding -fno-stack-protector -nostdlib -Wl,-emain -Werror -Wall -pedantic -std=c89 -o asm-i386 -x c -
+cat libc-freestanding.c asm-i386.c | clang -g -O3 -m32 -march=i386 -fno-omit-frame-pointer  -ffreestanding -fno-stack-protector -nostdlib -Wl,-emain -Werror -Wall -pedantic -std=c89 -o asm-i386 -x c -
+# to use libc and syscall of the host
+cat libc-hosted.c asm-i386.c | clang -g -O3 -m32 -march=i386 -Werror -Wall -pedantic -std=c89 -o asm-i386 -lbsd -x c -
+
+cat libc-freestanding.c asm-i386.c | pcc -g -O1 -march=i386 -ffreestanding -nostdlib -Wl,-emain -Werror -Wall -std=c89 -o asm-i386 -x c -
+# to use libc and syscall of the host
+# valgrind fails in SIGILL at unhandled instruction bytes: 0xC8 0x4 0x0 0x0
+cat libc-hosted.c asm-i386.c | pcc -g -O1 -march=i386 -Werror -Wall -std=c89 -o asm-i386 -lbsd -x c -
+
+cat libc-freestanding.c asm-i386.c _start-stub.c | tcc -g -m32 -march=i386 -nostdlib -std=c89 -Werror -Wall -o asm-i386 -
+cat libc-freestanding.c asm-i386.c _start-stub.c | tcc -g -m32 -march=i386 -nostdlib -std=c89 -Werror -Wall -o asm-i386 -
+
+# -nostdlib segfaults with tcc 0.9.27
+# hangs with git version above 0.9.27
+cat libc-freestanding.c asm-i386.c | tcc -g -m32 -march=i386 -fno-builtin -std=c89 -Werror -Wall -o asm-i386 -
+# needs git version above 0.9.27
+cat libc-freestanding.c asm-i386.c _start-stub.c | tcc -g -m32 -march=i386 -nostdlib -std=c89 -Werror -Wall -o asm-i386 -
+# to use libc and syscall of the host
+cat libc-hosted.c asm-i386.c | tcc -g -m32 -march=i386 -std=c89 -Werror -Wall -o asm-i386 -lbsd -
+
+# for debugging freestandig mode
+cat libc-freestanding.c asm-i386.c > test.c
+gcc -g -O0 -m32 -march=i386 -ffreestanding -fno-stack-protector -nostdlib -emain -Werror -Wno-noreturn -Wall -pedantic -fno-pic -std=c89 -o asm-i386 test.c
+
+# for debugging hosted mode
+cat libc-hosted.c asm-i386.c > test.c
+gcc -g -O0 -m32 -march=i386 -Werror -Wall -pedantic -std=c89 -o asm-i386 -lbsd test.c
+
+usage
+-----
+
+# compile
+./ec < test1.e > test1.asm
+# use the host assembler to produce a binary
+fasm test1.asm test1.bin
+# use our own minimalistic assembler
+./asm-i386 < test1.asm > test1.bin
+gcc -g -Wall -std=c99 -o emul emul.c -lunicorn -lcapstone -pthread
+./emul test1.bin 
+
+# run test framework
+tests/run_tests.sh
+
+links
+-----
+
+1:10:00 video Hjalfi writes a compiler
+
+things I got from cowgol:
+inner-nested functions/procedures
+don't do automatic type promotion, maybe something like uint8, int8, etc.
+no recursion, well, we might need that
+
+4:09:00 video Hjalfi writes an assembler
+
+no frees as things are freed in the end, well, we don't obey that rule,
+compiler/assember should be embedable and they have local scopes which
+can be freed while running, thus reducing the memory usage and hence
+allowing bigger modules to be comiled/assembled.
+
+hashtables as simple table on the first character + list, avoids complex
+hashtable classes in C.
+
+pass operator precedence as recursive descent variable (as in retargetable
+C compiler). We prefer the hierarchical approach
+
+syscalls
+--------
+
+https://www.win.tue.nl/~aeb/linux/lk/lk-4.html
+
+memory management
+-----------------
+
+nice lecture on the topic:
+http://dmitrysoshnikov.com/compilers/writing-a-memory-allocator/
+
+https://www.informatik.htw-dresden.de/~beck/ASM/syscall_list.html
+sbrk and brk inspiration drawn form rt0 (git@github.com:lpsantil/rt0.git)
+
+malloc inspired by:
+https://arjunsreedharan.org/post/148675821737/memory-allocators-101-write-a-simple-memory
+https://github.com/arjun024/memalloc.git
+
+full bootstrappable compiler
+----------------------------
+
+we also embedd the needed syscalls (currently Linux 32-bit only):
+- exit
+- read from stdin
+- write to stdout
+- brk
+the parts of libc we needs are embedded. this mininimalistic libc
+uses the syscalls.
+
+requirements
+------------
+ 
+our parser requires a language recursive functions
+
+const expressions
+-----------------
+
+const
+	N : integer = 20;
+	M : integer = 2 * N + 3;
+
+this needs a small interpreter to create the right constants. If we
+have a different target architecture we must emulate that target
+architecture's semantic!
+
+const folding also is desireable for functions: 
+
+function f( x : integer ) : integer
+begin
+	return 2 * x;
+end
+
+const
+	M : integer = 2 * f( N );
+	
+This makes the compiler much more complicated, as we have to basically
+interpret arbitrary code.
+
+const folding eliminates the need for a preprocessor, as we can
+easily define global constants like platforms, etc.
+
+const
+	PLATFORM_BITS : integer = 32;
+
+type
+	integer32 : ARRAY[PLATFORM_BITS] OF BIT;
+	
+there are henn-and-egg dragons here!
+
+but we need it for internal constants like 'true' and 'false' for
+initializing a constant of 'boolean'.
+
+detection of uninitialized variables
+------------------------------------
+
+this might be very hard and heuristical (and the depend on the compiler
+optimization level). Simple flows can be statically analyzed, what
+to do when conditions, loops and complex data structures come into place?
+
+assembler
+---------
+
+http://ref.x86asm.net/coder32.html
+"Art Of Intel x86 Assembly"
+Intel® 64 and IA-32 Architectures Software Developer’s Manual
+https://www.felixcloutier.com/x86/index.html
+http://www.c-jump.com/CIS77/CPU/x86/lecture.html#X77_0140_encoding_add_ecx_eax
+https://c9x.me/x86/html/file_module_x86_id_147.html
+