> Johannes had an interesting idea to use trace_ath10k_log_dbg_enabled(). > Could you investigate if that would work? That way we might get the > performance improvement even when is enabled CONFIG_ATH10K_TRACING (but > actual trace point is disabled, of course).
That's a good idea. This patch was originally made for Google Wifi's 3.18 kernel and It does use trace_ath10k_log_dbg_enabled(): https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/391891 +#define ath10k_dbg(ar, mask, format, ...) \ + do { \ + if (unlikely((ath10k_debug_mask & mask) || \ + trace_ath10k_log_dbg_enabled())) { \ + __ath10k_dbg(ar, mask, format, ##__VA_ARGS__); \ + } \ + } while (0)
