Perf/dlmalloc guest allocator

[jotabulacios]

The guest allocator moves from embedded-alloc's TLSF heap to dlmalloc, with TLSF kept one
flag away (tlsf-alloc) for fallback. dlmalloc sits on a bump provider that hands it
page-aligned chunks of the guest heap, so it still reuses freed memory — no OOM — while
each alloc and free costs fewer guest instructions than TLSF.

Isolated A/B on the same tree, only the feature differs: guest cycles drop 11.2% on a
10-transfer ethrex block (1,702,365 → 1,511,225) and 13.1% on a 20-transfer one
(3,915,738 → 3,404,649). In the guest profile the allocator goes from 24.4% of cycles to
9.5%.

[diegokingston]

/bench

[github-actions]

Benchmark — ethrex 20 transfers (median of 3)

_{Table parallelism: auto (cores / 3)}

Metric	main	PR	Δ
Peak heap	51123 MB	49371 MB	-1752 MB (-3.4%) ⚪
Prove time	25.974s	25.617s	-0.357s (-1.4%) ⚪

✅ No significant change.

🔬 Looks like a small speedup (-1.4%) — below what 3 runs can confirm. Comment /bench-abba to run the drift-free ABBA tiebreaker (paired-t CI + exact Wilcoxon). Note: it occupies the bench server for ~30–40 min.
Optional pair count: /bench-abba 32 (20 resolves ~1%, 32 for ~0.6%).

✅ Low variance (time: 2.4%, heap: 2.1%)

_{Commit: 79e5437 · Baseline: cached · Runner: self-hosted bench}

[diegokingston]

/bench