|WARNING| app/dma_perf: skip case if worker maps to main lcore

[dpdklab at iol.unh.edu]

Test-Label: ai-code-review
Test-Status: WARNING
https://dpdk.org/patch/166087

_AI Code Review_

=== Patch Review: series.patch (via Claude) ===
Review date: 2026-06-24

# DPDK Patch Review

## Summary
This patch adds early validation to reject test cases where a worker lcore is the same as the EAL main lcore, preventing a deadlock where the main thread would wait on itself.

---

## Errors

None found.

---

## Warnings

### 1. Missing return code propagation

**File:** `app/test-dma-perf/main.c`

The existing `run_test()` function has void return type and uses `return` without a value to skip test cases. The new check follows this pattern, but there's no way for the caller to distinguish between:
- Normal test completion
- Test skipped due to insufficient lcores
- Test skipped due to worker-on-main-lcore conflict

**Suggested fix:**

The existing code already has this issue and is not introduced by this patch, but it would be clearer if `run_test()` returned an `int` status code:

```c
static int
run_test(uint32_t case_id, struct test_configure *case_cfg)
{
	/* ... */
	if (nb_lcores < case_cfg->num_worker + 1) {
		printf("Case %u: Not enough lcores.\n", case_id);
		return -EINVAL;
	}

	for (uint32_t i = 0; i < case_cfg->num_worker; i++) {
		worker_lcore = case_cfg->dma_config[i].lcore_dma_map.lcore;
		if (worker_lcore == main_lcore) {
			printf("Case %u: worker %u (lcore %u) cannot run on the EAL main lcore (%u).\n",
			       case_id, i, worker_lcore, main_lcore);
			return -EINVAL;
		}
	}
	/* ... */
	return 0;
}
```

However, since this patch is a targeted fix for a deadlock and the void return pattern is already established throughout the file, changing the return type would be a separate refactoring. This is acceptable for a stable backport.

---

## Info

### 1. Variable declaration style

**File:** `app/test-dma-perf/main.c`

The patch declares variables at the start of the function block, consistent with existing code in this file. This is acceptable per DPDK guidelines (both C89-style declarations at block start and C99-style declarations at point of first use are allowed).

### 2. Loop bounds check

The loop iterates over `case_cfg->num_worker` which is validated earlier in the function against available lcores. The check is safe.

### 3. Message clarity

The error message clearly identifies the conflict and provides all relevant lcore IDs for debugging.

---

## Conclusion

The patch correctly addresses the deadlock issue described. The fix is minimal, clear, and appropriate for backporting to stable branches. No correctness bugs or coding standard violations were found.