#!/usr/bin/env python3
"""Minimal PowerPC disassembler for /image/sylpheed.pe.

    tools/ppc-dis <start_va> <end_va>          disassemble a range
    tools/ppc-dis --find-imm <value> [lo hi]   every instruction with that immediate

The image is a FLAT VA DUMP: file offset = VA - 0x82000000. There is no `duckdb`
and no PowerPC `objdump` in this container, so this is the working route to the
bytes -- and the bytes are primary, the database is somebody's analysis of them.

⚠️ It lives here rather than in /tmp because the scratchpad is wiped by container
restarts, which cost this tool three times in one session.

Covers the integer/branch/load-store forms this corpus actually reads. Floating
point is printed as `FP<op> ... xo=<n>` rather than decoded: no finding so far has
needed an FP mnemonic, and a wrong one would be worse than an honest placeholder.
"""
import struct, sys
BASE = 0x82000000
IMG = "/image/sylpheed.pe"

def _mask(mb, me):
    m, i = 0, mb
    while True:
        m |= 1 << (31 - i)
        if i == me:
            break
        i = (i + 1) & 31
    return m

XO = {0:'cmpw',32:'cmplw',28:'and',444:'or',316:'xor',60:'andc',266:'add',40:'subf',
      104:'neg',24:'slw',536:'srw',824:'srawi',23:'lwzx',87:'lbzx',279:'lhzx',
      151:'stwx',339:'mfspr',467:'mtspr',235:'mullw',491:'divw',459:'divwu',
      922:'extsh',954:'extsb',407:'sthx',215:'stbx',343:'lhax',55:'lwzux',
      20:'lwarx',150:'stwcx.',412:'orc',476:'nand',124:'nor',8:'subfc',10:'addc',
      138:'adde',26:'cntlzw',792:'sraw'}
DF = {32:'lwz',33:'lwzu',34:'lbz',35:'lbzu',36:'stw',37:'stwu',38:'stb',39:'stbu',
      40:'lhz',41:'lhzu',42:'lha',44:'sth',45:'sthu',14:'addi',15:'addis',
      12:'addic',13:'addic.',7:'mulli',8:'subfic',24:'ori',25:'oris',26:'xori',
      27:'xoris',28:'andi.',29:'andis.',10:'cmpli',11:'cmpi',48:'lfs',50:'lfd',
      52:'stfs',54:'stfd'}
FPOPS = {48, 49, 50, 51, 52, 53, 54, 55}

def dis(va, x):
    op = x >> 26; rD = (x >> 21) & 31; rA = (x >> 16) & 31; rB = (x >> 11) & 31
    imm = x & 0xFFFF; s = imm - 0x10000 if imm & 0x8000 else imm
    if op in DF:
        m = DF[op]; r = 'f' if op in FPOPS else 'r'
        if m in ('addi', 'addis') and rA == 0:
            return "li r%d,%d" % (rD, s)
        if m in ('ori', 'oris', 'xori', 'xoris', 'andi.', 'andis.'):
            return "%s r%d,r%d,0x%X" % (m, rA, rD, imm)
        if m in ('cmpli', 'cmpi'):
            return "%s cr%d,r%d,%s" % (m, (x >> 23) & 7, rA,
                                       hex(imm) if m == 'cmpli' else s)
        if m in ('addi', 'addis', 'addic', 'addic.', 'mulli', 'subfic'):
            return "%s r%d,r%d,%d" % (m, rD, rA, s)
        return "%s %s%d,%d(r%d)" % (m, r, rD, s, rA)
    if op in (20, 21):
        S, A, SH, MB, ME = rD, rA, (x >> 11) & 31, (x >> 6) & 31, (x >> 1) & 31
        return "%s r%d,r%d,%d,%d,%d  ; mask=0x%08X" % (
            'rlwimi' if op == 20 else 'rlwinm', A, S, SH, MB, ME, _mask(MB, ME))
    if op == 31:
        e = (x >> 1) & 0x3FF; m = XO.get(e)
        if m is None:
            return ".long 0x%08X  ; op31 xo=%d" % (x, e)
        if m in ('cmpw', 'cmplw'):
            return "%s cr%d,r%d,r%d" % (m, (x >> 23) & 7, rA, rB)
        if m == 'srawi':
            return "srawi r%d,r%d,%d" % (rA, rD, rB)
        if m in ('or', 'and', 'xor', 'andc', 'orc', 'nand', 'nor', 'slw', 'srw', 'sraw'):
            return "%s r%d,r%d,r%d" % (m, rA, rD, rB)
        if m in ('extsh', 'extsb', 'neg', 'cntlzw'):
            return "%s r%d,r%d" % (m, rA, rD)
        return "%s r%d,r%d,r%d" % (m, rD, rA, rB)
    if op == 18:
        li = x & 0x03FFFFFC
        if li & 0x02000000:
            li -= 0x04000000
        return "b%s 0x%08X" % ('l' if x & 1 else '', (va + li) & 0xFFFFFFFF)
    if op == 16:
        bo, bi = rD, rA
        bd = x & 0xFFFC
        if bd & 0x8000:
            bd -= 0x10000
        cond = {(12,0):'blt',(12,1):'bgt',(12,2):'beq',(4,0):'bge',(4,1):'ble',(4,2):'bne'}
        nm = cond.get((bo, bi & 3)) or cond.get((bo & 0x1E, bi & 3)) or "bc(%d,%d)" % (bo, bi)
        return "%s cr%d,0x%08X" % (nm, bi >> 2, (va + bd) & 0xFFFFFFFF)
    if op == 19:
        return {16: 'blr', 528: 'bctr'}.get((x >> 1) & 0x3FF, ".long 0x%08X" % x)
    if op in (59, 63):
        return "FP%d rD=%d rA=%d rB=%d rC=%d xo=%d" % (op, rD, rA, rB, (x >> 6) & 31,
                                                       (x >> 1) & 0x1F)
    return ".long 0x%08X  ; op=%d" % (x, op)

def main(argv):
    d = open(IMG, 'rb').read()
    if argv[0] == '--find-imm':
        want = int(argv[1], 0)
        lo = int(argv[2], 16) if len(argv) > 2 else BASE
        hi = int(argv[3], 16) if len(argv) > 3 else BASE + len(d)
        for a in range(lo, hi, 4):
            x = struct.unpack_from('>I', d, a - BASE)[0]
            if (x & 0xFFFF) == (want & 0xFFFF) and (x >> 26) in DF:
                print("%08X  %08X  %s" % (a, x, dis(a, x)))
        return 0
    a, e = int(argv[0], 16), int(argv[1], 16)
    while a < e:
        x = struct.unpack_from('>I', d, a - BASE)[0]
        print("%08X  %08X  %s" % (a, x, dis(a, x)))
        a += 4
    return 0

if __name__ == '__main__':
    sys.exit(main(sys.argv[1:]))
