| Message ID | 20190307102447.1205-1-horms+renesas@verge.net.au (mailing list archive) |
|---|---|
| State | Accepted |
| Delegated to: | Geert Uytterhoeven |
| Headers | show |
| Series | [net] ravb: Decrease TxFIFO depth of Q3 and Q2 to one | expand |
From: Simon Horman <horms+renesas@verge.net.au> Date: Thu, 7 Mar 2019 11:24:47 +0100 > From: Masaru Nagai <masaru.nagai.vx@renesas.com> > > Hardware has the CBS (Credit Based Shaper) which affects only Q3 > and Q2. When updating the CBS settings, even if the driver does so > after waiting for Tx DMA finished, there is a possibility that frame > data still remains in TxFIFO. > > To avoid this, decrease TxFIFO depth of Q3 and Q2 to one. > > This patch has been exercised this using netperf TCP_MAERTS, TCP_STREAM > and UDP_STREAM tests run on an Ebisu board. No performance change was > detected, outside of noise in the tests, both in terms of throughput and > CPU utilisation. > > Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") > Signed-off-by: Masaru Nagai <masaru.nagai.vx@renesas.com> > Signed-off-by: Kazuya Mizuguchi <kazuya.mizuguchi.ks@renesas.com> > [simon: updated changelog] > Signed-off-by: Simon Horman <horms+renesas@verge.net.au> Applied and queued up for -stable, thanks.
Hello! On 03/07/2019 01:24 PM, Simon Horman wrote: > From: Masaru Nagai <masaru.nagai.vx@renesas.com> > > Hardware has the CBS (Credit Based Shaper) which affects only Q3 > and Q2. When updating the CBS settings, We seem to only write the defaults into TCG, not update them below... Do we really use TX queues 2/3? I though the driver only uses TX queues 0/1... > even if the driver does so > after waiting for Tx DMA finished, there is a possibility that frame > data still remains in TxFIFO. > > To avoid this, decrease TxFIFO depth of Q3 and Q2 to one. > > This patch has been exercised this using netperf TCP_MAERTS, TCP_STREAM > and UDP_STREAM tests run on an Ebisu board. No performance change was > detected, outside of noise in the tests, both in terms of throughput and > CPU utilisation. > Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper") > Signed-off-by: Masaru Nagai <masaru.nagai.vx@renesas.com> > Signed-off-by: Kazuya Mizuguchi <kazuya.mizuguchi.ks@renesas.com> > [simon: updated changelog] > Signed-off-by: Simon Horman <horms+renesas@verge.net.au> > --- > drivers/net/ethernet/renesas/ravb_main.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c > index d28c8f9ca55b..8154b38c08f7 100644 > --- a/drivers/net/ethernet/renesas/ravb_main.c > +++ b/drivers/net/ethernet/renesas/ravb_main.c > @@ -458,7 +458,7 @@ static int ravb_dmac_init(struct net_device *ndev) > RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR); > > /* Set FIFO size */ > - ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC); > + ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC); Looks harmless... and DaveM has already merged it anyway. :-) MBR, Sergei
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index d28c8f9ca55b..8154b38c08f7 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -458,7 +458,7 @@ static int ravb_dmac_init(struct net_device *ndev) RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR); /* Set FIFO size */ - ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC); + ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC); /* Timestamp enable */ ravb_write(ndev, TCCR_TFEN, TCCR);