sky2: receive dma mapping error handling
in [Kernel]
|
From: Stephen Hemminger on 3 Feb 2010 12:00 On Wed, 03 Feb 2010 11:47:19 -0500 Michael Breuer <mbreuer(a)majjas.com> wrote: > Tracked this down. The status being returned is 0x3c0080 - good flow > control packets. Nothing is actually being dropped (confirmed by packet > trace on switch compared with packet trace on server). > > I whipped up a trivial patch to not count these as dropped packets and > will post to netdev. > > I'm not really sure what the driver should be doing in this case, but > resubmit seems to work. Looks like a flow control negotiation issue. You probably turned off flow control on the Linux side, but the switch is still doing flow control. -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Michael Breuer on 3 Feb 2010 12:10 On 02/03/2010 11:56 AM, Stephen Hemminger wrote: > On Wed, 03 Feb 2010 11:47:19 -0500 > Michael Breuer<mbreuer(a)majjas.com> wrote: > > >> Tracked this down. The status being returned is 0x3c0080 - good flow >> control packets. Nothing is actually being dropped (confirmed by packet >> trace on switch compared with packet trace on server). >> >> I whipped up a trivial patch to not count these as dropped packets and >> will post to netdev. >> >> I'm not really sure what the driver should be doing in this case, but >> resubmit seems to work. >> > Looks like a flow control negotiation issue. You probably turned off > flow control on the Linux side, but the switch is still doing flow > control. > > According to the driver: Feb 3 12:03:02 mail kernel: sky2 eth0: Link is up at 1000 Mbps, full duplex, flow control both So if the rx flow control packet status is due to flow control being disabled, then there's a different issue. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Justin P. Mattock on 3 Feb 2010 12:20 On 02/03/10 08:56, Stephen Hemminger wrote: > On Wed, 03 Feb 2010 11:47:19 -0500 > Michael Breuer<mbreuer(a)majjas.com> wrote: > >> Tracked this down. The status being returned is 0x3c0080 - good flow >> control packets. Nothing is actually being dropped (confirmed by packet >> trace on switch compared with packet trace on server). >> >> I whipped up a trivial patch to not count these as dropped packets and >> will post to netdev. >> >> I'm not really sure what the driver should be doing in this case, but >> resubmit seems to work. > > Looks like a flow control negotiation issue. You probably turned off > flow control on the Linux side, but the switch is still doing flow > control. > I noticed this in a hotel last week, I can try at the home to see if this fires of, if so I can test any patches you have. Justin P. Mattock -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Stephen Hemminger on 3 Feb 2010 13:30 On Wed, 03 Feb 2010 10:23:01 -0800 "Justin P. Mattock" <justinmattock(a)gmail.com> wrote: > On 02/03/10 09:07, Michael Breuer wrote: > > On 02/03/2010 11:56 AM, Stephen Hemminger wrote: > >> On Wed, 03 Feb 2010 11:47:19 -0500 > >> Michael Breuer<mbreuer(a)majjas.com> wrote: > >> > >>> Tracked this down. The status being returned is 0x3c0080 - good flow > >>> control packets. Nothing is actually being dropped (confirmed by packet > >>> trace on switch compared with packet trace on server). > >>> > >>> I whipped up a trivial patch to not count these as dropped packets and > >>> will post to netdev. > >>> > >>> I'm not really sure what the driver should be doing in this case, but > >>> resubmit seems to work. > >> Looks like a flow control negotiation issue. You probably turned off > >> flow control on the Linux side, but the switch is still doing flow > >> control. > >> > > According to the driver: > > Feb 3 12:03:02 mail kernel: sky2 eth0: Link is up at 1000 Mbps, full > > duplex, flow control both > > > > So if the rx flow control packet status is due to flow control being > > disabled, then there's a different issue. > > > > > > -- > > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > > the body of a message to majordomo(a)vger.kernel.org > > More majordomo info at http://vger.kernel.org/majordomo-info.html > > Please read the FAQ at http://www.tux.org/lkml/ > > > > > hmm.. after an hour or so I'm not seeing anything. > from what I remember I turned the machine on in the > hotel, then left the system there as I went out for a few hours > (so maybe I need to wait). > > Anyways I did keep dmesg of when this occurred, basically > the log was spammed with these: > > [ 863.294057] sky2 eth0: rx error, status 0x580002 length 88 > [ 865.646645] sky2 eth0: rx error, status 0x600002 length 96 > [ 1286.420471] sky2 eth0: rx error, status 0x600002 length 96 > [ 1286.499459] sky2 eth0: rx error, status 0x600002 length 96 > [ 1746.903826] sky2 eth0: rx error, status 0x600002 length 96 > [ 1754.263692] sky2 eth0: rx error, status 0x600002 length 96 > [ 1755.309360] sky2 eth0: rx error, status 0x680002 length 104 > [ 2213.256294] sky2 eth0: rx error, status 0x600002 length 96 > [ 2219.653342] sky2 eth0: rx error, status 0x580002 length 88 > [ 2221.673601] sky2 eth0: rx error, status 0x600002 length 96 > [ 2679.654655] sky2 eth0: rx error, status 0x680002 length 104 > [ 2692.315058] sky2 eth0: rx error, status 0x500002 length 80 > [ 2694.349612] sky2 eth0: rx error, status 0x580002 length 88 > [ 2703.676717] sky2 eth0: rx error, status 0x700002 length 112 > [ 2703.826375] sky2 eth0: rx error, status 0x600002 length 96 > [ 3187.504843] sky2 eth0: rx error, status 0x600002 length 96 > [ 3189.560744] sky2 eth0: rx error, status 0x600002 length 96 > [ 3672.475719] sky2 eth0: rx error, status 0x680002 length 104 > [ 3676.696959] sky2 eth0: rx error, status 0x680002 length 104 > > but while using the system with this, I didn't notice anything > out of the ordinary. > (if this fires off I can try a bisect for you guys, but right now > since I'm not seeing anything, might be a different story); > You were on a crappy hotel switch. Those are all CRC errors. -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Justin P. Mattock on 3 Feb 2010 13:30
On 02/03/10 09:07, Michael Breuer wrote: > On 02/03/2010 11:56 AM, Stephen Hemminger wrote: >> On Wed, 03 Feb 2010 11:47:19 -0500 >> Michael Breuer<mbreuer(a)majjas.com> wrote: >> >>> Tracked this down. The status being returned is 0x3c0080 - good flow >>> control packets. Nothing is actually being dropped (confirmed by packet >>> trace on switch compared with packet trace on server). >>> >>> I whipped up a trivial patch to not count these as dropped packets and >>> will post to netdev. >>> >>> I'm not really sure what the driver should be doing in this case, but >>> resubmit seems to work. >> Looks like a flow control negotiation issue. You probably turned off >> flow control on the Linux side, but the switch is still doing flow >> control. >> > According to the driver: > Feb 3 12:03:02 mail kernel: sky2 eth0: Link is up at 1000 Mbps, full > duplex, flow control both > > So if the rx flow control packet status is due to flow control being > disabled, then there's a different issue. > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo(a)vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ > hmm.. after an hour or so I'm not seeing anything. from what I remember I turned the machine on in the hotel, then left the system there as I went out for a few hours (so maybe I need to wait). Anyways I did keep dmesg of when this occurred, basically the log was spammed with these: [ 863.294057] sky2 eth0: rx error, status 0x580002 length 88 [ 865.646645] sky2 eth0: rx error, status 0x600002 length 96 [ 1286.420471] sky2 eth0: rx error, status 0x600002 length 96 [ 1286.499459] sky2 eth0: rx error, status 0x600002 length 96 [ 1746.903826] sky2 eth0: rx error, status 0x600002 length 96 [ 1754.263692] sky2 eth0: rx error, status 0x600002 length 96 [ 1755.309360] sky2 eth0: rx error, status 0x680002 length 104 [ 2213.256294] sky2 eth0: rx error, status 0x600002 length 96 [ 2219.653342] sky2 eth0: rx error, status 0x580002 length 88 [ 2221.673601] sky2 eth0: rx error, status 0x600002 length 96 [ 2679.654655] sky2 eth0: rx error, status 0x680002 length 104 [ 2692.315058] sky2 eth0: rx error, status 0x500002 length 80 [ 2694.349612] sky2 eth0: rx error, status 0x580002 length 88 [ 2703.676717] sky2 eth0: rx error, status 0x700002 length 112 [ 2703.826375] sky2 eth0: rx error, status 0x600002 length 96 [ 3187.504843] sky2 eth0: rx error, status 0x600002 length 96 [ 3189.560744] sky2 eth0: rx error, status 0x600002 length 96 [ 3672.475719] sky2 eth0: rx error, status 0x680002 length 104 [ 3676.696959] sky2 eth0: rx error, status 0x680002 length 104 but while using the system with this, I didn't notice anything out of the ordinary. (if this fires off I can try a bisect for you guys, but right now since I'm not seeing anything, might be a different story); Justin P. Mattock -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |