[PATCHv2] ath10k: Add wrapper function to ath10k debug

[PATCHv2] ath10k: Add wrapper function to ath10k debug

[Venkateswara Naralasetty]

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>
---
v2:
 * changed trace enabled check from IS_ENABLED(CONFIG_ATH10K_TRACING)
 * to trace_ath10k_log_dbg_enabled().

 drivers/net/wireless/ath/ath10k/core.c  |  2 ++
 drivers/net/wireless/ath/ath10k/debug.c |  8 ++++----
 drivers/net/wireless/ath/ath10k/debug.h | 22 ++++++++++++++++------
 drivers/net/wireless/ath/ath10k/trace.c |  1 +
 drivers/net/wireless/ath/ath10k/trace.h |  6 +++++-
 5 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index cfd7bb2..ab709bf 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -26,6 +26,8 @@
 #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 32d967a..1b63929 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -2620,8 +2620,8 @@ 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;
@@ -2638,7 +2638,7 @@ void ath10k_dbg(struct ath10k *ar, enum ath10k_debug_mask mask,
 
 	va_end(args);
 }
-EXPORT_SYMBOL(ath10k_dbg);
+EXPORT_SYMBOL(__ath10k_dbg);
 
 void ath10k_dbg_dump(struct ath10k *ar,
 		     enum ath10k_debug_mask mask,
@@ -2651,7 +2651,7 @@ 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 db78e85..a5b2039 100644
--- a/drivers/net/wireless/ath/ath10k/debug.h
+++ b/drivers/net/wireless/ath/ath10k/debug.h
@@ -240,18 +240,18 @@ 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;
 }
@@ -263,4 +263,14 @@ 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 ((ath10k_debug_mask & dbg_mask) ||			\
+	    trace_ath10k_log_dbg_enabled())			\
+		__ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \
+} while (0)
 #endif /* _DEBUG_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/trace.c b/drivers/net/wireless/ath/ath10k/trace.c
index 3ecdff1..c7d4c97 100644
--- a/drivers/net/wireless/ath/ath10k/trace.c
+++ b/drivers/net/wireless/ath/ath10k/trace.c
@@ -7,3 +7,4 @@
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
+EXPORT_SYMBOL(__tracepoint_ath10k_log_dbg);
diff --git a/drivers/net/wireless/ath/ath10k/trace.h b/drivers/net/wireless/ath/ath10k/trace.h
index ba977bb..ab91645 100644
--- a/drivers/net/wireless/ath/ath10k/trace.h
+++ b/drivers/net/wireless/ath/ath10k/trace.h
@@ -29,7 +29,11 @@ static inline u32 ath10k_frm_hdr_len(const void *buf, size_t len)
 #if !defined(CONFIG_ATH10K_TRACING)
 #undef TRACE_EVENT
 #define TRACE_EVENT(name, proto, ...) \
-static inline void trace_ ## name(proto) {}
+static inline void trace_ ## name(proto) {} \
+static inline bool trace_##name##_enabled(void) \
+{						\
+	return false;				\
+}
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(...)
 #undef DEFINE_EVENT
-- 
2.7.4

Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Ben Greear]

On 4/26/19 5:58 AM, Venkateswara Naralasetty wrote:
> 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>
> ---
> v2:
>   * changed trace enabled check from IS_ENABLED(CONFIG_ATH10K_TRACING)
>   * to trace_ath10k_log_dbg_enabled().
> 
>   drivers/net/wireless/ath/ath10k/core.c  |  2 ++
>   drivers/net/wireless/ath/ath10k/debug.c |  8 ++++----
>   drivers/net/wireless/ath/ath10k/debug.h | 22 ++++++++++++++++------
>   drivers/net/wireless/ath/ath10k/trace.c |  1 +
>   drivers/net/wireless/ath/ath10k/trace.h |  6 +++++-
>   5 files changed, 28 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
> index cfd7bb2..ab709bf 100644
> --- a/drivers/net/wireless/ath/ath10k/core.c
> +++ b/drivers/net/wireless/ath/ath10k/core.c
> @@ -26,6 +26,8 @@
>   #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 32d967a..1b63929 100644
> --- a/drivers/net/wireless/ath/ath10k/debug.c
> +++ b/drivers/net/wireless/ath/ath10k/debug.c
> @@ -2620,8 +2620,8 @@ 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;

Do you still need the check later in this method:

if (ath10k_debug_mask & mask)

since you already checked in the ath10k_dbg() macro?

Thanks,
Ben


-- 
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc  http://www.candelatech.com

RE: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Venkateswara Naralasetty]

> -----Original Message-----
> From: ath10k <ath10k-bounces@lists.infradead.org> On Behalf Of Ben
> Greear
> Sent: Friday, April 26, 2019 6:52 PM
> To: Venkateswara Naralasetty <vnaralas@codeaurora.org>;
> ath10k@lists.infradead.org
> Cc: Kan Yan <kyan@chromium.org>; linux-wireless@vger.kernel.org
> Subject: [EXT] Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug
> 
> On 4/26/19 5:58 AM, Venkateswara Naralasetty wrote:
> > 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>
> > ---
> > v2:
> >   * changed trace enabled check from
> IS_ENABLED(CONFIG_ATH10K_TRACING)
> >   * to trace_ath10k_log_dbg_enabled().
> >
> >   drivers/net/wireless/ath/ath10k/core.c  |  2 ++
> >   drivers/net/wireless/ath/ath10k/debug.c |  8 ++++----
> >   drivers/net/wireless/ath/ath10k/debug.h | 22 ++++++++++++++++------
> >   drivers/net/wireless/ath/ath10k/trace.c |  1 +
> >   drivers/net/wireless/ath/ath10k/trace.h |  6 +++++-
> >   5 files changed, 28 insertions(+), 11 deletions(-)
> >
> > diff --git a/drivers/net/wireless/ath/ath10k/core.c
> > b/drivers/net/wireless/ath/ath10k/core.c
> > index cfd7bb2..ab709bf 100644
> > --- a/drivers/net/wireless/ath/ath10k/core.c
> > +++ b/drivers/net/wireless/ath/ath10k/core.c
> > @@ -26,6 +26,8 @@
> >   #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 32d967a..1b63929 100644
> > --- a/drivers/net/wireless/ath/ath10k/debug.c
> > +++ b/drivers/net/wireless/ath/ath10k/debug.c
> > @@ -2620,8 +2620,8 @@ 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;
> 
> Do you still need the check later in this method:
> 
> if (ath10k_debug_mask & mask)
> 
> since you already checked in the ath10k_dbg() macro?
Yes, we need this check.
Otherwise all debug messages will be printed even without any debug mask set in case of tracing enabled. 
> 
> Thanks,
> Ben
> 
> 
> --
> Ben Greear <greearb@candelatech.com>
> Candela Technologies Inc  http://www.candelatech.com
> 
> 
> _______________________________________________
> ath10k mailing list
> ath10k@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/ath10k

Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Ben Greear]

On 4/26/19 6:38 AM, Venkateswara Naralasetty wrote:

>>>    #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;
>>
>> Do you still need the check later in this method:
>>
>> if (ath10k_debug_mask & mask)
>>
>> since you already checked in the ath10k_dbg() macro?
> Yes, we need this check.
> Otherwise all debug messages will be printed even without any debug mask set in case of tracing enabled.

Ahh, I see.

Thanks,
Ben

-- 
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc  http://www.candelatech.com

Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Michał Kazior]

On Fri, 26 Apr 2019 at 14:58, Venkateswara Naralasetty
<vnaralas@codeaurora.org> wrote:
>
> 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.
[...]

> +/* Avoid calling __ath10k_dbg() if debug_mask is not set and tracing
> + * disabled.
> + */
> +#define ath10k_dbg(ar, dbg_mask, fmt, ...)                     \
> +do {                                                           \
> +       if ((ath10k_debug_mask & dbg_mask) ||                   \
> +           trace_ath10k_log_dbg_enabled())                     \
> +               __ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \
> +} while (0)

Did you consider using jump labels (see include/linux/jump_label.h)?
It's what tracing uses under the hood. I wonder if you could squeeze
out a bit more performance with that? I guess you'd need to add
`struct static_key ath10k_dbg_mask_keys[ATH10K_DBG_MAX]` and re-do
ath10k_debug_mask enum a bit.


Michal

Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Ben Greear]

On 4/26/19 6:44 AM, Michał Kazior wrote:
> On Fri, 26 Apr 2019 at 14:58, Venkateswara Naralasetty
> <vnaralas@codeaurora.org> wrote:
>>
>> 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.
> [...]
> 
>> +/* Avoid calling __ath10k_dbg() if debug_mask is not set and tracing
>> + * disabled.
>> + */
>> +#define ath10k_dbg(ar, dbg_mask, fmt, ...)                     \
>> +do {                                                           \
>> +       if ((ath10k_debug_mask & dbg_mask) ||                   \
>> +           trace_ath10k_log_dbg_enabled())                     \
>> +               __ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \
>> +} while (0)
> 
> Did you consider using jump labels (see include/linux/jump_label.h)?
> It's what tracing uses under the hood. I wonder if you could squeeze
> out a bit more performance with that? I guess you'd need to add
> `struct static_key ath10k_dbg_mask_keys[ATH10K_DBG_MAX]` and re-do
> ath10k_debug_mask enum a bit.

Maybe first test with debugging just compiled out to see if there is still
any significant overhead with this new patch applied?

Thanks,
Ben

-- 
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc  http://www.candelatech.com

RE: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Venkateswara Naralasetty]

> -----Original Message-----
> From: ath10k <ath10k-bounces@lists.infradead.org> On Behalf Of Ben
> Greear
> Sent: Friday, April 26, 2019 7:27 PM
> To: Michał Kazior <kazikcz@gmail.com>; Venkateswara Naralasetty
> <vnaralas@codeaurora.org>
> Cc: Kan Yan <kyan@chromium.org>; linux-wireless <linux-
> wireless@vger.kernel.org>; ath10k@lists.infradead.org
> Subject: [EXT] Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug
> 
> On 4/26/19 6:44 AM, Michał Kazior wrote:
> > On Fri, 26 Apr 2019 at 14:58, Venkateswara Naralasetty
> > <vnaralas@codeaurora.org> wrote:
> >>
> >> 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.
> > [...]
> >
> >> +/* Avoid calling __ath10k_dbg() if debug_mask is not set and tracing
> >> + * disabled.
> >> + */
> >> +#define ath10k_dbg(ar, dbg_mask, fmt, ...)                     \
> >> +do {                                                           \
> >> +       if ((ath10k_debug_mask & dbg_mask) ||                   \
> >> +           trace_ath10k_log_dbg_enabled())                     \
> >> +               __ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \ }
> >> +while (0)
> >
> > Did you consider using jump labels (see include/linux/jump_label.h)?
> > It's what tracing uses under the hood. I wonder if you could squeeze
> > out a bit more performance with that? I guess you'd need to add
> > `struct static_key ath10k_dbg_mask_keys[ATH10K_DBG_MAX]` and re-do
> > ath10k_debug_mask enum a bit.
> 
> Maybe first test with debugging just compiled out to see if there is still any
> significant overhead with this new patch applied?
Since this macro ath10k_dbg defined outside of CONFIG_ATH10K_DEBUG will it make any difference even if debugging compiled out?

Thanks,
Venkatesh.
> 
> Thanks,
> Ben
> 
> --
> Ben Greear <greearb@candelatech.com>
> Candela Technologies Inc  http://www.candelatech.com
> 
> 
> _______________________________________________
> ath10k mailing list
> ath10k@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/ath10k

RE: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Venkateswara Naralasetty]

> -----Original Message-----
> From: ath10k <ath10k-bounces@lists.infradead.org> On Behalf Of Michal
> Kazior
> Sent: Friday, April 26, 2019 7:15 PM
> To: Venkateswara Naralasetty <vnaralas@codeaurora.org>
> Cc: Kan Yan <kyan@chromium.org>; linux-wireless <linux-
> wireless@vger.kernel.org>; ath10k@lists.infradead.org
> Subject: [EXT] Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug
> 
> On Fri, 26 Apr 2019 at 14:58, Venkateswara Naralasetty
> <vnaralas@codeaurora.org> wrote:
> >
> > 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.
> [...]
> 
> > +/* Avoid calling __ath10k_dbg() if debug_mask is not set and tracing
> > + * disabled.
> > + */
> > +#define ath10k_dbg(ar, dbg_mask, fmt, ...)                     \
> > +do {                                                           \
> > +       if ((ath10k_debug_mask & dbg_mask) ||                   \
> > +           trace_ath10k_log_dbg_enabled())                     \
> > +               __ath10k_dbg(ar, dbg_mask, fmt, ##__VA_ARGS__); \ }
> > +while (0)
> 
> Did you consider using jump labels (see include/linux/jump_label.h)?
> It's what tracing uses under the hood. I wonder if you could squeeze out a bit
> more performance with that? I guess you'd need to add `struct static_key
> ath10k_dbg_mask_keys[ATH10K_DBG_MAX]` and re-do
> ath10k_debug_mask enum a bit.
> 
I could not observe any significant Throughput/CPU improvement after using jump labels. For now shall we go with my patch?

Thanks,
Venkatesh.
> 
> Michal
> 
> _______________________________________________
> ath10k mailing list
> ath10k@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/ath10k

Re: [PATCHv2] ath10k: Add wrapper function to ath10k debug

[Kalle Valo]

Venkateswara Naralasetty <vnaralas@codeaurora.org> wrote:

> 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>
> Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

Patch applied to ath-next branch of ath.git, thanks.

9d740d6380e5 ath10k: Add wrapper function to ath10k debug

-- 
https://patchwork.kernel.org/patch/10919117/

https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches