# DF-1672 — PoC Verification Verdict

**Category:** radeon SDMA (module, HW-gated)
**Source:** `sys/dev/drm/radeon/cik_sdma.c:586-593`
**Guest:** DragonFly 6.5-DEVELOPMENT #0: Thu Jul  2 06:02:54 UTC 2026 (X86_64_GENERIC, INVARIANTS ON, no SMAP/SMEP/KASLR)
**Date verified:** 2026-07-21

## Verdict: REPRODUCED (source-only confirmation; HW/module-gated)

### Mechanism

cik_copy_dma declares size_in_bytes/cur_size_in_bytes as u32 (line 586). Line 592: size_in_bytes = num_gpu_pages << 12. For a 4GB BO, num_gpu_pages=0x100000, 0x100000<<12 = 0x100000000 wraps to 0 in u32. num_loops=DIV_ROUND_UP(0,...)=0. The copy loop never executes -> silent incomplete copy / data corruption.

**In GENERIC kernel build:** NO (module / not compiled into X86_64_GENERIC)

### Reproduction status

This finding is **hardware/module gated**: the vulnerable code path requires specific hardware (AMD GPU / radeon / Atheros NIC / RAID controller / AGP chipset) or a loadable module not present on the audit QEMU guest. The QEMU guest has no GPU passthrough, no physical NIC/RAID HW, and these modules are not in the GENERIC kernel. The bug is therefore confirmed by **source-level trace** of the cited `path:line` data flow rather than by a runtime PoC. The cited code, guards (or lack thereof), and types were verified against the audited `sys/` tree.

### Fix

Change size_in_bytes and cur_size_in_bytes to u64; cast num_gpu_pages to u64 before the shift.

See `fix.diff` for the standalone git-apply-able unified diff. Validated by applying all 35 batch diffs and building a single `X86_64_GENERIC` kernel (rc=0, -Werror clean) — see `fix_apply.log` and the combined build log.