Claude review: drm/amd/display: Fix mem_type change detection for async flips

[Claude Code Review Bot <claude-review@example.com>]

Patch Review

**Bug analysis: Correct.** The existing code at `amdgpu_dm.c:12785-12786`:

```c
new_plane_state = drm_atomic_get_plane_state(state, plane);
old_plane_state = drm_atomic_get_plane_state(state, plane);
```

`drm_atomic_get_plane_state()` is declared `__must_check` and returns an `ERR_PTR` on failure or the (new) plane state pointer on success. Since both calls pass the same `(state, plane)`, the second call finds the plane already added to the atomic state and returns the same `new_state` pointer. So `old_plane_state == new_plane_state` always, and the mem_type comparison is a no-op.

**Fix analysis: Correct.** The replacement:

```c
new_plane_state = drm_atomic_get_new_plane_state(state, plane);
old_plane_state = drm_atomic_get_old_plane_state(state, plane);
```

These are simple inline lookups (confirmed in `drm_atomic.h:808-828`) that return `state->planes[idx].old_state` and `.new_state` respectively, or NULL if the plane is not part of the commit. This correctly retrieves distinct old/new states for comparison.

**NULL handling: Correct.** The change from `IS_ERR()` to a NULL check with `continue`:

```c
if (!old_plane_state || !new_plane_state)
    continue;
```

This is correct because `drm_atomic_get_old/new_plane_state()` returns NULL (not ERR_PTR) when the plane isn't in the commit. Using `continue` rather than `return false` is the right semantic — a plane not participating in this commit can't have a mem_type change, so we skip it and check the remaining planes. The old code's `return false` was also defensively acceptable (since that means "no change detected"), but `continue` is more precise and avoids short-circuiting the loop.

**Iteration scope note (minor).** The loop uses `crtc_state->plane_mask`, which includes all planes currently associated with the CRTC — including planes not being modified in this commit. For those planes, `drm_atomic_get_new_plane_state()` will return NULL, and the `continue` correctly skips them. This is a strict improvement over the old code, which would have *added* every plane in the mask to the atomic state as a side effect of calling `drm_atomic_get_plane_state()` — unnecessarily pulling in unrelated planes during atomic check.

**Commit message quality: Good.** The `[Why]`/`[How]` structure clearly explains both the root cause and the fix. The `Fixes:` tag references the correct introducing commit. The description of the real-world symptom (corruption under gamescope with DCN 3.0.1 when buffers migrate between VRAM and GTT) is helpful.

**No issues found.** The patch is clean, correct, and minimal.

---
Generated by Claude Code Patch Reviewer