Re: [PATCH] mt76: usb: fix static tracepoints

[Felix Fietkau]

On 2018-10-18 00:35, Lorenzo Bianconi wrote:
> Add submit_urb and rx_urb static tracepoints in mt76-usb module.
> Move trace_mac_txstat_fetch in mt76x02_mac_load_tx_status routine
> in order to be available to usb drivers. Moreover remove
> no longer used mt76x0/trace.{c,h}
> 
> Signed-off-by: Lorenzo Bianconi 
Applied, thanks.

- Felix

Re: [PATCH] mt76: usb: fix static tracepoints

[Stanislaw Gruszka]

On Thu, Oct 18, 2018 at 10:13:51AM +0200, Lorenzo Bianconi wrote:
> On Oct 18, Stanislaw Gruszka wrote:
> > On Thu, Oct 18, 2018 at 12:35:32AM +0200, Lorenzo Bianconi wrote:
> > > Add submit_urb and rx_urb static tracepoints in mt76-usb module.
> > > Move trace_mac_txstat_fetch in mt76x02_mac_load_tx_status routine
> > > in order to be available to usb drivers. Moreover remove
> > > no longer used mt76x0/trace.{c,h}
> > > 
> > > Signed-off-by: Lorenzo Bianconi 
> > > ---
> > > @@ -54,7 +53,7 @@ mt76x0_rf_csr_wr(struct mt76x02_dev *dev, u32 offset, 
> > > u8 value)
> > >   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
> > >   MT_RF_CSR_CFG_WR |
> > >   MT_RF_CSR_CFG_KICK);
> > > - trace_mt76x0_rf_write(>mt76, bank, offset, value);
> > 
> > I think tracing RF registers writes/read can still be useful.
> 
> Hi Stanislaw,
> 
> I removed tracing for RF registers since these operations are already tracked 
> in
> mt76_wr/mt76_rr so I thought they were redundant. Do you think deducing rf
> read/write operations from mt76_{rr,wr} tracing is too convoluted? If so I
> can reintroduce them in v2.

No, if we can trace RF access thats ok. ACK for patch.

Thanks
Stanislaw

Re: [PATCH] mt76: usb: fix static tracepoints

[Lorenzo Bianconi]

On Oct 18, Stanislaw Gruszka wrote:
> On Thu, Oct 18, 2018 at 12:35:32AM +0200, Lorenzo Bianconi wrote:
> > Add submit_urb and rx_urb static tracepoints in mt76-usb module.
> > Move trace_mac_txstat_fetch in mt76x02_mac_load_tx_status routine
> > in order to be available to usb drivers. Moreover remove
> > no longer used mt76x0/trace.{c,h}
> > 
> > Signed-off-by: Lorenzo Bianconi 
> > ---
> > @@ -54,7 +53,7 @@ mt76x0_rf_csr_wr(struct mt76x02_dev *dev, u32 offset, u8 
> > value)
> > FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
> > MT_RF_CSR_CFG_WR |
> > MT_RF_CSR_CFG_KICK);
> > -   trace_mt76x0_rf_write(>mt76, bank, offset, value);
> 
> I think tracing RF registers writes/read can still be useful.

Hi Stanislaw,

I removed tracing for RF registers since these operations are already tracked in
mt76_wr/mt76_rr so I thought they were redundant. Do you think deducing rf
read/write operations from mt76_{rr,wr} tracing is too convoluted? If so I
can reintroduce them in v2.

Regards,
Lorenzo

> 
> Thanks
> Stanislaw

Re: [PATCH] mt76: usb: fix static tracepoints

[Stanislaw Gruszka]

On Thu, Oct 18, 2018 at 12:35:32AM +0200, Lorenzo Bianconi wrote:
> Add submit_urb and rx_urb static tracepoints in mt76-usb module.
> Move trace_mac_txstat_fetch in mt76x02_mac_load_tx_status routine
> in order to be available to usb drivers. Moreover remove
> no longer used mt76x0/trace.{c,h}
> 
> Signed-off-by: Lorenzo Bianconi 
> ---
> @@ -54,7 +53,7 @@ mt76x0_rf_csr_wr(struct mt76x02_dev *dev, u32 offset, u8 
> value)
>   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
>   MT_RF_CSR_CFG_WR |
>   MT_RF_CSR_CFG_KICK);
> - trace_mt76x0_rf_write(>mt76, bank, offset, value);

I think tracing RF registers writes/read can still be useful.

Thanks
Stanislaw