From: rich Date: Sat, 8 Sep 2007 13:58:02 +0000 (+0000) Subject: More docs X-Git-Url: http://git.annexia.org/?a=commitdiff_plain;h=9dc526d7477809c27b8e153cd2e0dea6bbcf69d5;p=jonesforth.git More docs --- diff --git a/jonesforth.S b/jonesforth.S index 81fd9a0..53e2706 100644 --- a/jonesforth.S +++ b/jonesforth.S @@ -66,6 +66,9 @@ This code draws heavily on the design of LINA FORTH (http://home.hccnet.nl/a.w.m.van.der.horst/lina.html) by Albert van der Horst. Any similarities in the code are probably not accidental. + Also I used this document (http://ftp.funet.fi/pub/doc/IOCCC/1992/buzzard.2.design) which really + defies easy explanation. + SETTING UP ---------------------------------------------------------------------- Let's get a few housekeeping things out of the way. Firstly because I need to draw lots of @@ -605,6 +608,10 @@ DOUBLE: .int DOCOL // codeword Don't worry too much about the exact implementation details of this macro - it's complicated! */ +/* Flags - these are discussed later. */ +#define F_IMMED 0x80 +#define F_HIDDEN 0x20 + // Store the chain of links. .set link,0 @@ -642,7 +649,7 @@ name_\label : | LINK in next word - Again, for brevity in writing the header I'm going to use an assembler macro called defcode. + Again, for brevity in writing the header I'm going to write an assembler macro called defcode. */ .macro defcode name, namelen, flags=0, label @@ -727,13 +734,13 @@ code_\label : // assembler code follows NEXT defcode "+",1,,ADD - pop %eax - addl %eax,(%esp) + pop %eax // get top of stack + addl %eax,(%esp) // and add it to next word on stack NEXT defcode "-",1,,SUB - pop %eax - subl %eax,(%esp) + pop %eax // get top of stack + subl %eax,(%esp) // and subtract if from next word on stack NEXT defcode "*",1,,MUL @@ -798,24 +805,83 @@ code_\label : // assembler code follows orl %eax,(%esp) NEXT - defcode "INVERT",6,,INVERT + defcode "INVERT",6,,INVERT // this is the FORTH "NOT" function notl (%esp) NEXT -/* Flags. */ -#define F_IMMED 0x80 -#define F_HIDDEN 0x20 +/* + RETURNING FROM FORTH WORDS ---------------------------------------------------------------------- - // COLD must not return (ie. must not call EXIT). - defword "COLD",4,,COLD - // XXX reinitialisation of the interpreter - .int INTERPRETER // call the interpreter loop (never returns) - .int LIT,1,SYSEXIT // hmmm, but in case it does, exit(1). + Time to talk about what happens when we EXIT a function. In this diagram QUADRUPLE has called + DOUBLE, and DOUBLE is about to exit (look at where %esi is pointing): + + QUADRUPLE + +------------------+ + | codeword | + +------------------+ DOUBLE + | addr of DOUBLE ---------------> +------------------+ + +------------------+ | codeword | + | addr of DOUBLE | +------------------+ + +------------------+ | addr of DUP | + | addr of EXIT | +------------------+ + +------------------+ | addr of + | + +------------------+ + %esi -> | addr of EXIT | + +------------------+ + + What happens when the + function does NEXT? Well, the following code is executed. +*/ defcode "EXIT",4,,EXIT POPRSP %esi // pop return stack into %esi NEXT +/* + EXIT gets the old %esi which we saved from before on the return stack, and puts it in %esi. + So after this (but just before NEXT) we get: + + QUADRUPLE + +------------------+ + | codeword | + +------------------+ DOUBLE + | addr of DOUBLE ---------------> +------------------+ + +------------------+ | codeword | + %esi -> | addr of DOUBLE | +------------------+ + +------------------+ | addr of DUP | + | addr of EXIT | +------------------+ + +------------------+ | addr of + | + +------------------+ + | addr of EXIT | + +------------------+ + + And NEXT just completes the job by, well in this case just by calling DOUBLE again :-) + + LITERALS ---------------------------------------------------------------------- + + The final point I "glossed over" before was how to deal with functions that do anything + apart from calling other functions. For example, suppose that DOUBLE was defined like this: + + : DOUBLE 2 * ; + + It does the same thing, but how do we compile it since it contains the literal 2? One way + would be to have a function called "2" (which you'd have to write in assembler), but you'd need + a function for every single literal that you wanted to use. + + FORTH solves this by compiling the function using a special word called LIT: + + +---------------------------+-------+-------+-------+-------+-------+ + | (usual header of DOUBLE) | DOCOL | LIT | 2 | * | EXIT | + +---------------------------+-------+-------+-------+-------+-------+ + + LIT is executed in the normal way, but what it does next is definitely not normal. It + looks at %esi (which now points to the literal 2), grabs it, pushes it on the stack, then + manipulates %esi in order to skip the literal as if it had never been there. + + What's neat is that the whole grab/manipulate can be done using a single byte single + i386 instruction, our old friend LODSL. Rather than me drawing more ASCII-art diagrams, + see if you can find out how LIT works: +*/ + defcode "LIT",3,,LIT // %esi points to the next command, but in this case it points to the next // literal 32 bit integer. Get that literal into %eax and increment %esi. @@ -824,25 +890,13 @@ code_\label : // assembler code follows push %eax // push the literal number on to stack NEXT - defcode "LITSTRING",9,,LITSTRING - lodsl // get the length of the string - push %eax // push it on the stack - push %esi // push the address of the start of the string - addl %eax,%esi // skip past the string - addl $3,%esi // but round up to next 4 byte boundary - andl $~3,%esi - NEXT - - defcode "BRANCH",6,,BRANCH - add (%esi),%esi // add the offset to the instruction pointer - NEXT +/* + MEMORY ---------------------------------------------------------------------- - defcode "0BRANCH",7,,ZBRANCH - pop %eax - test %eax,%eax // top of stack is zero? - jz code_BRANCH // if so, jump back to the branch function above - lodsl // otherwise we need to skip the offset - NEXT + As important point about FORTH is that it gives you direct access to the lowest levels + of the machine. Manipulating memory directly is done frequently in FORTH, and these are + the primitive words for doing it. +*/ defcode "!",1,,STORE pop %ebx // address to store at @@ -886,6 +940,21 @@ code_\label : // assembler code follows push %eax // push value onto stack NEXT +/* + BUILT-IN VARIABLES ---------------------------------------------------------------------- + + These are some built-in variables and related standard FORTH words. Of these, the only one that we + have discussed so far was LATEST, which points to the last (most recently defined) word in the + FORTH dictionary. LATEST is also a FORTH word which pushes the address of LATEST (the variable) + on to the stack, so you can read or write it using @ and ! operators. For example, to print + the current value of LATEST (and this can apply to any FORTH variable) you would do: + + LATEST @ . CR + + To make defining variables shorter, I'm using a macro called defvar, similar to defword and + defcode above. (In fact the defvar macro uses defcode to do the dictionary header). +*/ + .macro defvar name, namelen, flags=0, label, initial=0 defcode \name,\namelen,\flags,\label push $var_\name @@ -896,26 +965,35 @@ var_\name : .int \initial .endm - // The STATE variable is 0 for execute mode, != 0 for compile mode - defvar "STATE",5,,STATE +/* + The built-in variables are: - // This points to where compiled words go. - defvar "HERE",4,,HERE,user_defs_start + STATE Is the interpreter executing code (0) or compiling a word (non-zero)? + LATEST Points to the latest (most recently defined) word in the dictionary. + HERE When compiling, compiled words go here. + _X These are three scratch variables, used by some standard dictionary words. + _Y + _Z + S0 Stores the address of the top of the parameter stack. + R0 Stores the address of the top of the return stack. - // This is the last definition in the dictionary. +*/ + defvar "STATE",5,,STATE + defvar "HERE",4,,HERE,user_defs_start defvar "LATEST",6,,LATEST,name_SYSEXIT // SYSEXIT must be last in built-in dictionary - - // _X, _Y and _Z are scratch variables used by standard words. defvar "_X",2,,TX defvar "_Y",2,,TY defvar "_Z",2,,TZ - - // This stores the top of the data stack. defvar "S0",2,,SZ - - // This stores the top of the return stack. defvar "R0",2,,RZ,return_stack +/* + RETURN STACK ---------------------------------------------------------------------- + + These words allow you to access the return stack. Recall that the register %ebp always points to + the top of the return stack. +*/ + defcode "DSP@",4,,DSPFETCH mov %esp,%eax push %eax @@ -947,6 +1025,14 @@ var_\name : lea 4(%ebp),%ebp // pop return stack and throw away NEXT +/* + INPUT AND OUTPUT ---------------------------------------------------------------------- + + + + +*/ + #include defcode "KEY",3,,KEY @@ -1211,14 +1297,13 @@ _COMMA: movl %edi,var_HERE // Update HERE (incremented) ret - defcode "HIDDEN",6,,HIDDEN - call _HIDDEN + defcode ";",1,F_IMMED,SEMICOLON + movl $EXIT,%eax // EXIT is the final codeword in compiled words. + call _COMMA // Store it. + call _HIDDEN // Toggle the HIDDEN flag (unhides the new word). + xor %eax,%eax // Set STATE to 0 (back to execute mode). + movl %eax,var_STATE NEXT -_HIDDEN: - movl var_LATEST,%edi // LATEST word. - addl $4,%edi // Point to name/flags byte. - xorb $F_HIDDEN,(%edi) // Toggle the HIDDEN bit. - ret defcode "IMMEDIATE",9,F_IMMED,IMMEDIATE call _IMMEDIATE @@ -1229,13 +1314,14 @@ _IMMEDIATE: xorb $F_IMMED,(%edi) // Toggle the IMMED bit. ret - defcode ";",1,F_IMMED,SEMICOLON - movl $EXIT,%eax // EXIT is the final codeword in compiled words. - call _COMMA // Store it. - call _HIDDEN // Toggle the HIDDEN flag (unhides the new word). - xor %eax,%eax // Set STATE to 0 (back to execute mode). - movl %eax,var_STATE + defcode "HIDDEN",6,,HIDDEN + call _HIDDEN NEXT +_HIDDEN: + movl var_LATEST,%edi // LATEST word. + addl $4,%edi // Point to name/flags byte. + xorb $F_HIDDEN,(%edi) // Toggle the HIDDEN bit. + ret /* This definiton of ' (TICK) is strictly cheating - it also only works in compiled code. */ defcode "'",1,,TICK @@ -1243,6 +1329,31 @@ _IMMEDIATE: pushl %eax // Push it on the stack. NEXT + defcode "BRANCH",6,,BRANCH + add (%esi),%esi // add the offset to the instruction pointer + NEXT + + defcode "0BRANCH",7,,ZBRANCH + pop %eax + test %eax,%eax // top of stack is zero? + jz code_BRANCH // if so, jump back to the branch function above + lodsl // otherwise we need to skip the offset + NEXT + + defcode "LITSTRING",9,,LITSTRING + lodsl // get the length of the string + push %eax // push it on the stack + push %esi // push the address of the start of the string + addl %eax,%esi // skip past the string + addl $3,%esi // but round up to next 4 byte boundary + andl $~3,%esi + NEXT + + // COLD must not return (ie. must not call EXIT). + defword "COLD",4,,COLD + .int INTERPRETER // call the interpreter loop (never returns) + .int LIT,1,SYSEXIT // hmmm, but in case it does, exit(1). + /* This interpreter is pretty simple, but remember that in FORTH you can always override * it later with a more powerful one! */