[lts8.6] selftests/bpf: Fix pyperf180 compilation failure with clang18

tools/testing/selftests/bpf/progs/pyperf.h

@@ -231,8 +231,12 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx)
 #ifdef NO_UNROLL
 #pragma clang loop unroll(disable)
 #else
+#ifdef UNROLL_COUNT
+#pragma clang loop unroll_count(UNROLL_COUNT)
+#else
 #pragma clang loop unroll(full)
 #endif
+#endif /* NO_UNROLL */
 		/* Unwind python stack */
 		for (int i = 0; i < STACK_MAX_LEN; ++i) {
 			if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) {

tools/testing/selftests/bpf/progs/pyperf180.c

@@ -1,4 +1,26 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #define STACK_MAX_LEN 180
+
+/* llvm upstream commit at clang18
+ *   https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e
+ * changed inlining behavior and caused compilation failure as some branch
+ * target distance exceeded 16bit representation which is the maximum for
+ * cpu v1/v2/v3. Macro __BPF_CPU_VERSION__ is later implemented in clang18
+ * to specify which cpu version is used for compilation. So a smaller
+ * unroll_count can be set if __BPF_CPU_VERSION__ is less than 4, which
+ * reduced some branch target distances and resolved the compilation failure.
+ *
+ * To capture the case where a developer/ci uses clang18 but the corresponding
+ * repo checkpoint does not have __BPF_CPU_VERSION__, a smaller unroll_count
+ * will be set as well to prevent potential compilation failures.
+ */
+#ifdef __BPF_CPU_VERSION__
+#if __BPF_CPU_VERSION__ < 4
+#define UNROLL_COUNT 90
+#endif
+#elif __clang_major__ == 18
+#define UNROLL_COUNT 90
+#endif
+
 #include "pyperf.h"

tools/testing/selftests/bpf/progs/pyperf600.c

@@ -1,9 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #define STACK_MAX_LEN 600
-/* clang will not unroll the loop 600 times.
- * Instead it will unroll it to the amount it deemed
- * appropriate, but the loop will still execute 600 times.
- * Total program size is around 90k insns
+/* Full unroll of 600 iterations will have total
+ * program size close to 298k insns and this may
+ * cause BPF_JMP insn out of 16-bit integer range.
+ * So limit the unroll size to 150 so the
+ * total program size is around 80k insns but
+ * the loop will still execute 600 times.
  */
+#define UNROLL_COUNT 150
 #include "pyperf.h"