Syplheed-Reborn/tools/re-capture/isl_report.py

#!/usr/bin/env python3
"""Regenerate the committed ISL artefacts under `docs/re/data/`.

    isl_report.py <StageNN.ssb> calls   -> the call-site census + a listing

The artefact was produced by an uncommitted one-off, so it drifted out of date
twice: once when operand staging was fixed (calls printed with too few
arguments) and once when three built-in names were corrected. Keeping the
generator in the tree is the point of this file.

    isl_report.py <StageNN.ssb> phase-ends -> every END_PHASE with its context
    isl_report.py <StageNN.ssb> conditions   -> every condition site, comparand resolved
    isl_report.py <StageNN.ssb> phase-guards -> the NECESSARY conditions for each exit
    isl_report.py <dir>          phase-guards -> the same for every Stage*.ssb it holds

The "needs the coroutine entry points" blocker recorded here is REFUTED: the
instruction stream is FLAT and `isl.linear_offsets` reaches 25705/25705 call
sites across all 28 stages. What broke the naive linear decode was `isl.dis`
stopping at op 20 (`ret`), which in a coroutine VM is a yield, not an end of
code -- see `docs/re/isl-stream-is-flat.md`.
"""
import collections
import os
import sys

import isl
import isl_cfg

def census(b):
    cs = isl.call_sites(b)
    return cs, collections.Counter(bid for _, bid, _ in cs)


def emit_calls(b, path):
    cs, h = census(b)
    s1, s2 = isl.symbols(b, 1), isl.symbols(b, 2)
    print('# %s — ISL disassembly artefacts' % path)
    print()
    print('Generated by `tools/re-capture/isl_report.py calls`.')
    print()
    print('%d call sites, %d distinct built-ins' % (len(cs), len(h)))
    for bid, n in h.most_common():
        print('  builtin %-4d %5d site(s)' % (bid, n))
    print()
    print('## phase-control sites')
    for bid, nm in ((6, 'END_PHASE'), (62, 'FORCE_END_PHASE'),
                    (39, 'MARK_LAST_PHASE'), (40, 'mark_not_last')):
        offs = [off for off, b2, _ in cs if b2 == bid]
        print('%-3d %-18s %2d: %s'
              % (bid, nm, len(offs), ' '.join('0x%x' % o for o in offs)))
    print()
    print('## named built-ins used, by traffic')
    for bid, n in h.most_common():
        nm = isl.BUILTIN.get(bid)
        if nm:
            print('  %-3d %-24s %4d' % (bid, nm, n))
    print()
    print('## phase code bases')
    print('Each phase has its OWN base; the file header offset is not it.')
    print('  ' + ' '.join('0x%x' % x for x in isl.phase_bases(b)))
    print()
    print('## disassembly into the first END_PHASE')
    target = [off for off, bid, _ in cs if bid == 6][0]
    start = isl.resync(b, target)
    print('resync from 0x%X' % start)
    for line in isl.dis(b, start, 64, code_base=0x24, sym2=s2, sym1=s1):
        print(line)


def emit_phase_ends(b, path):
    """Every phase-ending call with the instructions that lead into it."""
    offs = isl.linear_offsets(b)
    idx = {o: k for k, o in enumerate(offs)}
    bases = isl.phase_bases(b)
    s1, s2 = isl.symbols(b, 1), isl.symbols(b, 2)
    ends = [(o, bid) for o, bid, _ in isl.call_sites(b) if bid in (6, 62)]
    print('# %s — where each phase ends' % path)
    print()
    print('Generated by `tools/re-capture/isl_report.py phase-ends`.')
    print('Decoded with `stop_at_ret=False`; a `ret` is a coroutine YIELD, so')
    print('the listing continues past it.')
    print()
    print('phase code bases: ' + ' '.join('0x%x' % x for x in bases))
    print('%d phase-ending call(s): %d END_PHASE, %d FORCE_END_PHASE'
          % (len(ends), sum(1 for _, b2 in ends if b2 == 6),
             sum(1 for _, b2 in ends if b2 == 62)))
    for o, bid in ends:
        ph = sum(1 for x in bases if x <= o)
        k = idx.get(o)
        if k is None:
            print('\n## 0x%X builtin %d — NOT on the linear stream' % (o, bid))
            continue
        print('\n## phase %d — builtin %d (%s) at 0x%X'
              % (ph, bid, isl.BUILTIN.get(bid, '?'), o))
        for line in isl.dis(b, offs[max(0, k - 16)], 22,
                            code_base=bases[ph - 1], sym2=s2, sym1=s1,
                            stop_at_ret=False):
            print('    ' + line)


def emit_conditions(b, path):
    """Every condition site with its comparand — what `data/isl-stage02-conditions.txt`
    never had a generator for."""
    import collections
    cs = isl_cfg.conditions(b, isl.symbols(b, 1), isl.symbols(b, 2))
    bases = isl.phase_bases(b)
    print('# %s — condition sites, comparands resolved' % path)
    print()
    print('Generated by `tools/re-capture/isl_report.py conditions`.')
    print()
    print('The deque ops are an expression stack: `push.i` saves the comparand,')
    print('the right-hand side is evaluated (its result lands in `special[0]`),')
    print('`pop.i` restores the comparand into `special[1]`, then `cmp.i` compares.')
    print()
    print('Operands come from a CFG dataflow fixpoint (`isl_cfg.py`), joining each')
    print('block over its ACTUAL predecessors — not from a linear walk.')
    print()
    print('%d condition sites; phase bases %s'
          % (len(cs), ' '.join('0x%x' % x for x in bases)))
    h = collections.Counter(c['lhs'].split('(')[0] for c in cs if c['lhs'] and '(' in c['lhs'])
    print()
    print('## most-tested predicates')
    for k, n in h.most_common(20):
        print('  %-28s %4d' % (k, n))
    for ph in range(1, len(bases) + 1):
        rows = [c for c in cs if c['phase'] == ph]
        print()
        print('## phase %d — %d sites' % (ph, len(rows)))
        for c in rows:
            lhs = c['lhs'] if c['lhs'] is not None else '<unknown: no static entry>'
            rhs = c['rhs'] if c['rhs'] is not None else '<unknown>'
            print('  0x%06X  if %s %s %s  -> 0x%X'
                  % (c['off'], lhs, c['rel'], rhs, c['target']))


def emit_phase_guards(b, path):
    """The conditions that DOMINATE each phase exit — the per-phase clear condition."""
    rows, reached, total = isl_cfg.dominating_conditions(b)
    print('# %s — what each phase exit requires' % path)
    print()
    print('Generated by `tools/re-capture/isl_report.py phase-guards`.')
    print()
    print('A condition is listed when it DOMINATES the exit: every path from an')
    print('entry to that `END_PHASE` passes through it, so it is NECESSARY for the')
    print('phase to end that way.  Reachability alone is the wrong query here —')
    print('in a poll loop both successors reach the exit.')
    print()
    print('CFG reached %d of %d instructions (%.1f%%).' % (reached, total, 100.0 * reached / total))
    for r in rows:
        nm = isl.BUILTIN.get(r['builtin'], 'builtin%d' % r['builtin'])
        if r['conds'] is None:
            print()
            print('## phase %d — %s at 0x%06X: UNREACHABLE from any static entry'
                  % (r['phase'], nm, r['end']))
            print('   (started from the trigger queue at `phase+272`, by data not code)')
            continue
        print()
        print('## phase %d — %s at 0x%06X: %d necessary condition(s)'
              % (r['phase'], nm, r['end'], len(r['conds'])))
        for c in r['conds']:
            lhs = c['lhs'] if c['lhs'] is not None else '<unknown>'
            rhs = c['rhs'] if c['rhs'] is not None else '<unknown>'
            print('    0x%06X  %s %s %s' % (c['off'], lhs, c['rel'], rhs))


def main():
    # The dominator pass over a large stage is memory-hungry and once OOM-KILLED
    # a run on this 15 GB box.  Cap the address space so a bad input fails this
    # process instead of the machine.
    try:
        import resource
        resource.setrlimit(resource.RLIMIT_AS, (10 * 1024 ** 3,) * 2)
    except Exception:
        pass
    path = sys.argv[1]
    if os.path.isdir(path):
        import glob
        files = sorted(glob.glob(os.path.join(path, 'Stage*.ssb')))
        for i, f in enumerate(files):
            if i: print(); print('-' * 72); print()
            {'calls': emit_calls, 'phase-ends': emit_phase_ends,
             'conditions': emit_conditions,
             'phase-guards': emit_phase_guards}[sys.argv[2]](
                isl.load(f), os.path.basename(f))
        return
    b = isl.load(path)
    name = path.replace('\\', '/').split('/')[-1]
    {'calls': emit_calls, 'phase-ends': emit_phase_ends,
     'conditions': emit_conditions,
     'phase-guards': emit_phase_guards}[sys.argv[2]](b, name)


if __name__ == '__main__':
    main()