diff mbox series

[v8,RESEND,6/6] r8169: Disable ASPM while doing NAPI poll

Message ID 20230221023849.1906728-7-kai.heng.feng@canonical.com (mailing list archive)
State Superseded
Headers show
Series r8169: Enable ASPM for recent 1.0/2.5Gbps Realtek NICs | expand

Commit Message

Kai-Heng Feng Feb. 21, 2023, 2:38 a.m. UTC
NAPI poll of Realtek NICs don't seem to perform well ASPM is enabled.
The vendor driver uses a mechanism called "dynamic ASPM" to toggle ASPM
based on the packet number in given time period.

Instead of implementing "dynamic ASPM", use a more straightforward way
by disabling ASPM during NAPI poll, as a similar approach was
implemented to solve slow performance on Realtek wireless NIC, see
commit 24f5e38a13b5 ("rtw88: Disable PCIe ASPM while doing NAPI poll on
8821CE").

Since NAPI poll should be handled as fast as possible, also remove the
delay in rtl_hw_aspm_clkreq_enable() which was added by commit
94235460f9ea ("r8169: Align ASPM/CLKREQ setting function with vendor
driver").

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
---
v8:
 - New patch.

 drivers/net/ethernet/realtek/r8169_main.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

Comments

Heiner Kallweit Feb. 21, 2023, 11:08 a.m. UTC | #1
On 21.02.2023 03:38, Kai-Heng Feng wrote:
> NAPI poll of Realtek NICs don't seem to perform well ASPM is enabled.
> The vendor driver uses a mechanism called "dynamic ASPM" to toggle ASPM
> based on the packet number in given time period.
> 
> Instead of implementing "dynamic ASPM", use a more straightforward way
> by disabling ASPM during NAPI poll, as a similar approach was
> implemented to solve slow performance on Realtek wireless NIC, see
> commit 24f5e38a13b5 ("rtw88: Disable PCIe ASPM while doing NAPI poll on
> 8821CE").
> 
> Since NAPI poll should be handled as fast as possible, also remove the
> delay in rtl_hw_aspm_clkreq_enable() which was added by commit
> 94235460f9ea ("r8169: Align ASPM/CLKREQ setting function with vendor
> driver").
> 
> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> ---
> v8:
>  - New patch.
> 
>  drivers/net/ethernet/realtek/r8169_main.c | 14 ++++++++++++--
>  1 file changed, 12 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
> index 897f90b48bba6..4d4a802346ae3 100644
> --- a/drivers/net/ethernet/realtek/r8169_main.c
> +++ b/drivers/net/ethernet/realtek/r8169_main.c
> @@ -2711,8 +2711,6 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
>  		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
>  		RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
>  	}
> -
> -	udelay(10);
>  }
>  
>  static void rtl_set_fifo_size(struct rtl8169_private *tp, u16 rx_stat,
> @@ -4577,6 +4575,12 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
>  	struct net_device *dev = tp->dev;
>  	int work_done;
>  
> +	if (tp->aspm_manageable) {
> +		rtl_unlock_config_regs(tp);

NAPI poll runs in softirq context (except for threaded NAPI).
Therefore you should use a spinlock instead of a mutex.

> +		rtl_hw_aspm_clkreq_enable(tp, false);
> +		rtl_lock_config_regs(tp);
> +	}
> +
>  	rtl_tx(dev, tp, budget);
>  
>  	work_done = rtl_rx(dev, tp, budget);
> @@ -4584,6 +4588,12 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
>  	if (work_done < budget && napi_complete_done(napi, work_done))
>  		rtl_irq_enable(tp);
>  
> +	if (tp->aspm_manageable) {
> +		rtl_unlock_config_regs(tp);
> +		rtl_hw_aspm_clkreq_enable(tp, true);
> +		rtl_lock_config_regs(tp);

Why not moving lock/unlock into rtl_hw_aspm_clkreq_enable()?

> +	}
> +
>  	return work_done;
>  }
>
Kai-Heng Feng Feb. 22, 2023, 1:03 p.m. UTC | #2
On Tue, Feb 21, 2023 at 7:09 PM Heiner Kallweit <hkallweit1@gmail.com> wrote:
>
> On 21.02.2023 03:38, Kai-Heng Feng wrote:
> > NAPI poll of Realtek NICs don't seem to perform well ASPM is enabled.
> > The vendor driver uses a mechanism called "dynamic ASPM" to toggle ASPM
> > based on the packet number in given time period.
> >
> > Instead of implementing "dynamic ASPM", use a more straightforward way
> > by disabling ASPM during NAPI poll, as a similar approach was
> > implemented to solve slow performance on Realtek wireless NIC, see
> > commit 24f5e38a13b5 ("rtw88: Disable PCIe ASPM while doing NAPI poll on
> > 8821CE").
> >
> > Since NAPI poll should be handled as fast as possible, also remove the
> > delay in rtl_hw_aspm_clkreq_enable() which was added by commit
> > 94235460f9ea ("r8169: Align ASPM/CLKREQ setting function with vendor
> > driver").
> >
> > Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> > ---
> > v8:
> >  - New patch.
> >
> >  drivers/net/ethernet/realtek/r8169_main.c | 14 ++++++++++++--
> >  1 file changed, 12 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
> > index 897f90b48bba6..4d4a802346ae3 100644
> > --- a/drivers/net/ethernet/realtek/r8169_main.c
> > +++ b/drivers/net/ethernet/realtek/r8169_main.c
> > @@ -2711,8 +2711,6 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
> >               RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> >               RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> >       }
> > -
> > -     udelay(10);
> >  }
> >
> >  static void rtl_set_fifo_size(struct rtl8169_private *tp, u16 rx_stat,
> > @@ -4577,6 +4575,12 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
> >       struct net_device *dev = tp->dev;
> >       int work_done;
> >
> > +     if (tp->aspm_manageable) {
> > +             rtl_unlock_config_regs(tp);
>
> NAPI poll runs in softirq context (except for threaded NAPI).
> Therefore you should use a spinlock instead of a mutex.

You are right. Will change it in next revision.

>
> > +             rtl_hw_aspm_clkreq_enable(tp, false);
> > +             rtl_lock_config_regs(tp);
> > +     }
> > +
> >       rtl_tx(dev, tp, budget);
> >
> >       work_done = rtl_rx(dev, tp, budget);
> > @@ -4584,6 +4588,12 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
> >       if (work_done < budget && napi_complete_done(napi, work_done))
> >               rtl_irq_enable(tp);
> >
> > +     if (tp->aspm_manageable) {
> > +             rtl_unlock_config_regs(tp);
> > +             rtl_hw_aspm_clkreq_enable(tp, true);
> > +             rtl_lock_config_regs(tp);
>
> Why not moving lock/unlock into rtl_hw_aspm_clkreq_enable()?

Because where it gets called at other places don't need the lock.
But yes this will make it easier to read, will do in next revision.

Kai-Heng

>
> > +     }
> > +
> >       return work_done;
> >  }
> >
>
Kai-Heng Feng Feb. 24, 2023, 3:38 a.m. UTC | #3
On Wed, Feb 22, 2023 at 9:03 PM Kai-Heng Feng
<kai.heng.feng@canonical.com> wrote:
>
> On Tue, Feb 21, 2023 at 7:09 PM Heiner Kallweit <hkallweit1@gmail.com> wrote:
> >
> > On 21.02.2023 03:38, Kai-Heng Feng wrote:
> > > NAPI poll of Realtek NICs don't seem to perform well ASPM is enabled.
> > > The vendor driver uses a mechanism called "dynamic ASPM" to toggle ASPM
> > > based on the packet number in given time period.
> > >
> > > Instead of implementing "dynamic ASPM", use a more straightforward way
> > > by disabling ASPM during NAPI poll, as a similar approach was
> > > implemented to solve slow performance on Realtek wireless NIC, see
> > > commit 24f5e38a13b5 ("rtw88: Disable PCIe ASPM while doing NAPI poll on
> > > 8821CE").
> > >
> > > Since NAPI poll should be handled as fast as possible, also remove the
> > > delay in rtl_hw_aspm_clkreq_enable() which was added by commit
> > > 94235460f9ea ("r8169: Align ASPM/CLKREQ setting function with vendor
> > > driver").
> > >
> > > Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> > > ---
> > > v8:
> > >  - New patch.
> > >
> > >  drivers/net/ethernet/realtek/r8169_main.c | 14 ++++++++++++--
> > >  1 file changed, 12 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
> > > index 897f90b48bba6..4d4a802346ae3 100644
> > > --- a/drivers/net/ethernet/realtek/r8169_main.c
> > > +++ b/drivers/net/ethernet/realtek/r8169_main.c
> > > @@ -2711,8 +2711,6 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
> > >               RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
> > >               RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
> > >       }
> > > -
> > > -     udelay(10);
> > >  }
> > >
> > >  static void rtl_set_fifo_size(struct rtl8169_private *tp, u16 rx_stat,
> > > @@ -4577,6 +4575,12 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
> > >       struct net_device *dev = tp->dev;
> > >       int work_done;
> > >
> > > +     if (tp->aspm_manageable) {
> > > +             rtl_unlock_config_regs(tp);
> >
> > NAPI poll runs in softirq context (except for threaded NAPI).
> > Therefore you should use a spinlock instead of a mutex.
>
> You are right. Will change it in next revision.
>
> >
> > > +             rtl_hw_aspm_clkreq_enable(tp, false);
> > > +             rtl_lock_config_regs(tp);
> > > +     }
> > > +
> > >       rtl_tx(dev, tp, budget);
> > >
> > >       work_done = rtl_rx(dev, tp, budget);
> > > @@ -4584,6 +4588,12 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
> > >       if (work_done < budget && napi_complete_done(napi, work_done))
> > >               rtl_irq_enable(tp);
> > >
> > > +     if (tp->aspm_manageable) {
> > > +             rtl_unlock_config_regs(tp);
> > > +             rtl_hw_aspm_clkreq_enable(tp, true);
> > > +             rtl_lock_config_regs(tp);
> >
> > Why not moving lock/unlock into rtl_hw_aspm_clkreq_enable()?
>
> Because where it gets called at other places don't need the lock.
> But yes this will make it easier to read, will do in next revision.

We can't do that because it creates deadlock:
rtl_hw_start()
  rtl_unlock_config_regs()
  rtl_hw_start_8168()
  rtl_hw_config()
    rtl_hw_start_8168h_1()
      rtl_hw_aspm_clkreq_enable()

Kai-Heng

>
> Kai-Heng
>
> >
> > > +     }
> > > +
> > >       return work_done;
> > >  }
> > >
> >
diff mbox series

Patch

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 897f90b48bba6..4d4a802346ae3 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2711,8 +2711,6 @@  static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
 		RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
 	}
-
-	udelay(10);
 }
 
 static void rtl_set_fifo_size(struct rtl8169_private *tp, u16 rx_stat,
@@ -4577,6 +4575,12 @@  static int rtl8169_poll(struct napi_struct *napi, int budget)
 	struct net_device *dev = tp->dev;
 	int work_done;
 
+	if (tp->aspm_manageable) {
+		rtl_unlock_config_regs(tp);
+		rtl_hw_aspm_clkreq_enable(tp, false);
+		rtl_lock_config_regs(tp);
+	}
+
 	rtl_tx(dev, tp, budget);
 
 	work_done = rtl_rx(dev, tp, budget);
@@ -4584,6 +4588,12 @@  static int rtl8169_poll(struct napi_struct *napi, int budget)
 	if (work_done < budget && napi_complete_done(napi, work_done))
 		rtl_irq_enable(tp);
 
+	if (tp->aspm_manageable) {
+		rtl_unlock_config_regs(tp);
+		rtl_hw_aspm_clkreq_enable(tp, true);
+		rtl_lock_config_regs(tp);
+	}
+
 	return work_done;
 }