Claude review: drm/msm/a6xx: Allow IFPC with perfcntr stream

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

Patch Review

Changes `sysprof_setup()` signature to add `bool force_on`, then uses it in `sample_worker` to inhibit IFPC while reading counter registers and re-enable it afterwards.

The `msm_gpu_sysprof_no_ifpc()` is decoupled from `msm_gpu_sysprof_no_perfcntr_zap()`:

```c
static inline bool msm_gpu_sysprof_no_ifpc(struct msm_gpu *gpu)
{
	return refcount_read(&gpu->sysprof_active) > 1;
}
```

This means IFPC is now only disabled for legacy userspace SYSPROF usage, not for the new kernel-managed perfcntr stream. The perfcntr stream instead briefly inhibits IFPC during sampling via `sysprof_setup(gpu, true/false)`. This is correct — the pwrup reglist (patch 15) handles restoring SEL registers on IFPC exit.

**Minor: bitwise OR vs logical OR.**

```c
bool sysprof = msm_gpu_sysprof_no_ifpc(gpu) | force_on;
```

This uses bitwise OR (`|`) on bools. While functionally correct, `||` would be more conventional for boolean operands. Very minor.

**Minor: diff artifact.** There appears to be a whitespace-damaged comment in the `msm_gpu_sysprof_no_ifpc()` diff (leading `+` on the comment line that was part of the removed block). This may just be a display artifact from the mbox formatting.

---
Generated by Claude Code Patch Reviewer