| Message ID | 1537766878-11238-1-git-send-email-vnaralas@codeaurora.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | ath10k: Add wrapper function to ath10k debug | expand |
Venkateswara Naralasetty <vnaralas@codeaurora.org> writes: > ath10k_dbg() is called in ath10k_process_rx() with huge set of arguments > which is causing CPU overhead even when debug_mask is not set. > Good improvement was observed in the receive side performance when call > to ath10k_dbg() is avoided in the RX path. > > Since currently all debug messages are sent via tracing infrastructure, > we cannot entirely avoid calling ath10k_dbg. Therefore, call to > ath10k_dbg() is made conditional based on tracing config in the driver. > > Trasmit performance remains unchanged with this patch; below are some > experimental results with this patch and tracing disabled. > > mesh mode: > > w/o this patch with this patch > Traffic TP CPU Usage TP CPU usage > > TCP 840Mbps 76.53% 960Mbps 78.14% > UDP 1030Mbps 74.58% 1132Mbps 74.31% > > Infra mode: > > w/o this patch with this patch > Traffic TP CPU Usage TP CPU usage > > TCP Rx 1241Mbps 80.89% 1270Mbps 73.50% > UDP Rx 1433Mbps 81.77% 1472Mbps 72.80% > > Tested platform : IPQ8064 > hardware used : QCA9984 > firmware ver : ver 10.4-3.5.3-00057 > > Signed-off-by: Kan Yan <kyan@chromium.org> > Signed-off-by: Venkateswara Naralasetty <vnaralas@codeaurora.org> The first Signed-off-by should be the author's, in this case Venkateswara. If Kan helped to develop the patch you should also add Co-developed-by: https://www.kernel.org/doc/html/latest/process/submitting-patches.html#when-to-use-acked-by-cc-and-co-developed-by > +/* Avoid calling __ath10k_dbg() if debug_mask is not set and tracing > + * disabled. > + */ > +#define ath10k_dbg(ar, dbg_mask, fmt, ...) \ > +do { \ > + if (IS_ENABLED(CONFIG_ATH10K_TRACING) || \ > + (ath10k_debug_mask & dbg_mask)) \ > + __ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \ > +} while (0) > #endif /* _DEBUG_H_ */ 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). Documentation/trace/tracepoints.rst has more info about the trace_*_enabled() function. It does have a special requirement but I'm not sure if it matters here as we don't care if we loose a message or two in the beginning: "The trace_<tracepoint>() should always be within the block of the if (trace_<tracepoint>_enabled()) to prevent races between the tracepoint being enabled and the check being seen."
> 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)
> -----Original Message----- > From: ath10k <ath10k-bounces@lists.infradead.org> On Behalf Of Kalle Valo > Sent: Friday, October 12, 2018 8:58 PM > To: Venkateswara Naralasetty <vnaralas@codeaurora.org> > Cc: Kan Yan <kyan@chromium.org>; linux-wireless@vger.kernel.org; > ath10k@lists.infradead.org > Subject: [EXTERNAL] Re: [PATCH] ath10k: Add wrapper function to ath10k > debug > > Venkateswara Naralasetty <vnaralas@codeaurora.org> writes: > > > ath10k_dbg() is called in ath10k_process_rx() with huge set of > > arguments which is causing CPU overhead even when debug_mask is not > set. > > Good improvement was observed in the receive side performance when > > call to ath10k_dbg() is avoided in the RX path. > > > > Since currently all debug messages are sent via tracing > > infrastructure, we cannot entirely avoid calling ath10k_dbg. > > Therefore, call to > > ath10k_dbg() is made conditional based on tracing config in the driver. > > > > Trasmit performance remains unchanged with this patch; below are some > > experimental results with this patch and tracing disabled. > > > > mesh mode: > > > > w/o this patch with this patch > > Traffic TP CPU Usage TP CPU usage > > > > TCP 840Mbps 76.53% 960Mbps 78.14% > > UDP 1030Mbps 74.58% 1132Mbps 74.31% > > > > Infra mode: > > > > w/o this patch with this patch > > Traffic TP CPU Usage TP CPU usage > > > > TCP Rx 1241Mbps 80.89% 1270Mbps 73.50% > > UDP Rx 1433Mbps 81.77% 1472Mbps 72.80% > > > > Tested platform : IPQ8064 > > hardware used : QCA9984 > > firmware ver : ver 10.4-3.5.3-00057 > > > > Signed-off-by: Kan Yan <kyan@chromium.org> > > Signed-off-by: Venkateswara Naralasetty <vnaralas@codeaurora.org> > > The first Signed-off-by should be the author's, in this case Venkateswara. If > Kan helped to develop the patch you should also add > Co-developed-by: > > https://www.kernel.org/doc/html/latest/process/submitting- > patches.html#when-to-use-acked-by-cc-and-co-developed-by > > > +/* Avoid calling __ath10k_dbg() if debug_mask is not set and tracing > > + * disabled. > > + */ > > +#define ath10k_dbg(ar, dbg_mask, fmt, ...) \ > > +do { \ > > + if (IS_ENABLED(CONFIG_ATH10K_TRACING) || \ > > + (ath10k_debug_mask & dbg_mask)) \ > > + __ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); > \ > > +} while (0) > > #endif /* _DEBUG_H_ */ > > 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). > Sure I will check on this and send next version. > Documentation/trace/tracepoints.rst has more info about the > trace_*_enabled() function. It does have a special requirement but I'm not > sure if it matters here as we don't care if we loose a message or two in the > beginning: > > "The trace_<tracepoint>() should always be within the block of the > if (trace_<tracepoint>_enabled()) to prevent races between the > tracepoint being enabled and the check being seen." > > -- > Kalle Valo > > _______________________________________________ > ath10k mailing list > ath10k@lists.infradead.org > http://lists.infradead.org/mailman/listinfo/ath10k
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index cf3c47b..8460037 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -37,6 +37,8 @@ #include "coredump.h" unsigned int ath10k_debug_mask; +EXPORT_SYMBOL(ath10k_debug_mask); + static unsigned int ath10k_cryptmode_param; static bool uart_print; static bool skip_otp; diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index ada29a4..8f305c6 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -2545,8 +2545,8 @@ void ath10k_debug_unregister(struct ath10k *ar) #endif /* CONFIG_ATH10K_DEBUGFS */ #ifdef CONFIG_ATH10K_DEBUG -void ath10k_dbg(struct ath10k *ar, enum ath10k_debug_mask mask, - const char *fmt, ...) +void __ath10k_dbg(struct ath10k *ar, enum ath10k_debug_mask mask, + const char *fmt, ...) { struct va_format vaf; va_list args; @@ -2556,14 +2556,13 @@ void ath10k_dbg(struct ath10k *ar, enum ath10k_debug_mask mask, vaf.fmt = fmt; vaf.va = &args; - if (ath10k_debug_mask & mask) - dev_printk(KERN_DEBUG, ar->dev, "%pV", &vaf); + dev_printk(KERN_DEBUG, ar->dev, "%pV", &vaf); trace_ath10k_log_dbg(ar, mask, &vaf); va_end(args); } -EXPORT_SYMBOL(ath10k_dbg); +EXPORT_SYMBOL(__ath10k_dbg); void ath10k_dbg_dump(struct ath10k *ar, enum ath10k_debug_mask mask, @@ -2576,7 +2575,7 @@ void ath10k_dbg_dump(struct ath10k *ar, if (ath10k_debug_mask & mask) { if (msg) - ath10k_dbg(ar, mask, "%s\n", msg); + __ath10k_dbg(ar, mask, "%s\n", msg); for (ptr = buf; (ptr - buf) < len; ptr += 16) { linebuflen = 0; diff --git a/drivers/net/wireless/ath/ath10k/debug.h b/drivers/net/wireless/ath/ath10k/debug.h index 3a6191c..88fead6 100644 --- a/drivers/net/wireless/ath/ath10k/debug.h +++ b/drivers/net/wireless/ath/ath10k/debug.h @@ -250,18 +250,18 @@ void ath10k_sta_update_rx_tid_stats_ampdu(struct ath10k *ar, #endif /* CONFIG_MAC80211_DEBUGFS */ #ifdef CONFIG_ATH10K_DEBUG -__printf(3, 4) void ath10k_dbg(struct ath10k *ar, - enum ath10k_debug_mask mask, - const char *fmt, ...); +__printf(3, 4) void __ath10k_dbg(struct ath10k *ar, + enum ath10k_debug_mask mask, + const char *fmt, ...); void ath10k_dbg_dump(struct ath10k *ar, enum ath10k_debug_mask mask, const char *msg, const char *prefix, const void *buf, size_t len); #else /* CONFIG_ATH10K_DEBUG */ -static inline int ath10k_dbg(struct ath10k *ar, - enum ath10k_debug_mask dbg_mask, - const char *fmt, ...) +static inline int __ath10k_dbg(struct ath10k *ar, + enum ath10k_debug_mask dbg_mask, + const char *fmt, ...) { return 0; } @@ -273,4 +273,14 @@ static inline void ath10k_dbg_dump(struct ath10k *ar, { } #endif /* CONFIG_ATH10K_DEBUG */ + +/* Avoid calling __ath10k_dbg() if debug_mask is not set and tracing + * disabled. + */ +#define ath10k_dbg(ar, dbg_mask, fmt, ...) \ +do { \ + if (IS_ENABLED(CONFIG_ATH10K_TRACING) || \ + (ath10k_debug_mask & dbg_mask)) \ + __ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \ +} while (0) #endif /* _DEBUG_H_ */
ath10k_dbg() is called in ath10k_process_rx() with huge set of arguments which is causing CPU overhead even when debug_mask is not set. Good improvement was observed in the receive side performance when call to ath10k_dbg() is avoided in the RX path. Since currently all debug messages are sent via tracing infrastructure, we cannot entirely avoid calling ath10k_dbg. Therefore, call to ath10k_dbg() is made conditional based on tracing config in the driver. Trasmit performance remains unchanged with this patch; below are some experimental results with this patch and tracing disabled. mesh mode: w/o this patch with this patch Traffic TP CPU Usage TP CPU usage TCP 840Mbps 76.53% 960Mbps 78.14% UDP 1030Mbps 74.58% 1132Mbps 74.31% Infra mode: w/o this patch with this patch Traffic TP CPU Usage TP CPU usage TCP Rx 1241Mbps 80.89% 1270Mbps 73.50% UDP Rx 1433Mbps 81.77% 1472Mbps 72.80% Tested platform : IPQ8064 hardware used : QCA9984 firmware ver : ver 10.4-3.5.3-00057 Signed-off-by: Kan Yan <kyan@chromium.org> Signed-off-by: Venkateswara Naralasetty <vnaralas@codeaurora.org> --- drivers/net/wireless/ath/ath10k/core.c | 2 ++ drivers/net/wireless/ath/ath10k/debug.c | 11 +++++------ drivers/net/wireless/ath/ath10k/debug.h | 22 ++++++++++++++++------ 3 files changed, 23 insertions(+), 12 deletions(-)