[tulip] problems with DFE-570tx and alpha 21264a system

John Jasen jjasen1@umbc.edu
Wed, 20 Sep 2000 14:01:50 -0400


API UP2000 motherboard with two 21264a/667 cpus, SRM revision A5.5-82.

Redhat Linux 6.2, with the 2.2.16-3smp rpm installed.

noisy kernel: tulip.c:v0.91g-ppc 7/16/99 becker@cesdis.gsfc.nasa.gov

I can configure and ifup all four ports, and they will respond. They all
make it through ping flood tests from a few different machines, but the
machine completely freezes if I do large file copies to three of the ports
simultaneously, as long as one of the ports is the third one.

(file copy tests are a 1GB file from /dev/zero, scp'ed to each interface)

Also, after ping flood tests, I noticed that in /proc/interrupts, the
problem port has a _lot_ more interrupts than the other three on the card.

To wit: 
[root@noisy /root]# more /proc/interrupts 
  1:          2    keyboard
  8:    7612384    timer
 12:          0    PS/2 Mouse
 19:     350207    aic7xxx
 39:      53760    eth0
 40:        171    eth4
 41:      53921    eth3
 42:        161    eth2
 43:        159    eth1
 47:         45    aic7xxx

I have debug=6 set in conf.modules, and it reports errors such as this
while ping -f is going on.

Message from syslogd@noisy at Wed Jun  9 14:13:06 2049 ...
noisy kernel: 60000 new csr5=0xf0660000. 

Message from syslogd@noisy at Wed Jun  9 14:13:07 2049 ...
noisy kernel:  

Message from syslogd@noisy at Wed Jun  9 14:13:11 2049 ...
noisy kernel: 60000.

tulip-diags -f reports the following:

tulip-diag.c:v2.03 7/31/2000 Donald Becker (becker@scyld.com)
 http://www.scyld.com/diag/index.html
Index #1: Found a Digital DS21143 Tulip adapter at 0xb000.
 Port selection is 100mbps-SYM/PCS 100baseTx scrambler, full-duplex.
 Transmit started, Receive started, full-duplex.
  The Rx process state is 'Transferring Rx frame into memory'.
  The Tx process state is 'Closing Tx descriptor'.
  PCI bus error!: Unknown 7.
  The transmit unit is set to store-and-forward.
 Interrupt sources are pending!  CSR5 is ffffffff.
   Tx done indication.
   Tx complete indication.
   Tx out of buffers indication.
   Transmit Jabber indication.
   Link passed indication.
   Tx FIFO Underflow indication.
   Rx Done indication.
   Receiver out of buffers indication.
   Receiver stopped indication.
   Receiver jabber indication.
   Link changed indication.
   Timer expired indication.
   Link failed indication.
   PCI bus error indication.
   Early Rx indication.
  The NWay status register is ffffffff.
WARNING: The EEPROM is missing or erased!
  Internal autonegotiation state is 'Invalid state'.
Index #2: Found a Digital DS21143 Tulip adapter at 0xb800.
 Port selection is 100mbps-SYM/PCS 100baseTx scrambler, full-duplex.
 Transmit started, Receive started, full-duplex.
  The Rx process state is 'Transferring Rx frame into memory'.
  The Tx process state is 'Closing Tx descriptor'.
  PCI bus error!: Unknown 7.
  The transmit unit is set to store-and-forward.
 Interrupt sources are pending!  CSR5 is ffffffff.
   Tx done indication.
   Tx complete indication.
   Tx out of buffers indication.
   Transmit Jabber indication.
   Link passed indication.
   Tx FIFO Underflow indication.
   Rx Done indication.
   Receiver out of buffers indication.
   Receiver stopped indication.
   Receiver jabber indication.
   Link changed indication.
   Timer expired indication.
   Link failed indication.
   PCI bus error indication.
   Early Rx indication.
  The NWay status register is ffffffff.
WARNING: The EEPROM is missing or erased!
  Internal autonegotiation state is 'Invalid state'.
Index #3: Found a Digital DS21143 Tulip adapter at 0xc000.
 Port selection is 100mbps-SYM/PCS 100baseTx scrambler, full-duplex.
 Transmit started, Receive started, full-duplex.
  The Rx process state is 'Transferring Rx frame into memory'.
  The Tx process state is 'Closing Tx descriptor'.
  PCI bus error!: Unknown 7.
  The transmit unit is set to store-and-forward.
 Interrupt sources are pending!  CSR5 is ffffffff.
   Tx done indication.
   Tx complete indication.
   Tx out of buffers indication.
   Transmit Jabber indication.
   Link passed indication.
   Tx FIFO Underflow indication.
   Rx Done indication.
   Receiver out of buffers indication.
   Receiver stopped indication.
   Receiver jabber indication.
   Link changed indication.
   Timer expired indication.
   Link failed indication.
   PCI bus error indication.
   Early Rx indication.
  The NWay status register is ffffffff.
WARNING: The EEPROM is missing or erased!
  Internal autonegotiation state is 'Invalid state'.
Index #4: Found a Digital DS21143 Tulip adapter at 0xc800.
 Port selection is 100mbps-SYM/PCS 100baseTx scrambler, full-duplex.
 Transmit started, Receive started, full-duplex.
  The Rx process state is 'Transferring Rx frame into memory'.
  The Tx process state is 'Closing Tx descriptor'.
  PCI bus error!: Unknown 7.
  The transmit unit is set to store-and-forward.
 Interrupt sources are pending!  CSR5 is ffffffff.
   Tx done indication.
   Tx complete indication.
   Tx out of buffers indication.
   Transmit Jabber indication.
   Link passed indication.
   Tx FIFO Underflow indication.
   Rx Done indication.
   Receiver out of buffers indication.
   Receiver stopped indication.
   Receiver jabber indication.
   Link changed indication.
   Timer expired indication.
   Link failed indication.
   PCI bus error indication.
   Early Rx indication.
  The NWay status register is ffffffff.
WARNING: The EEPROM is missing or erased!
  Internal autonegotiation state is 'Invalid state'.
 Use '-a' or '-aa' to show device registers,
     '-e' to show EEPROM contents, -ee for parsed contents,
  or '-m' or '-mm' to show MII management registers.

Ethernet configuration on boot reports the following:
(apologies for date and line wrapping)

Jun  9 12:11:33 noisy kernel: epic100.c:v1.07h 8/18/99 Donald Becker
http://cesdis.gsfc.nasa.gov/linux/drivers/epic100.html 
Jun  9 12:11:33 noisy kernel: eth0: SMSC EPIC/100 83c170 at 0x10000a800,
IRQ 39, 00:e0:29:87:f9:69. 
Jun  9 12:11:33 noisy kernel: eth0: MII transceiver #3 control 3000 status
7849.
 
Jun  9 12:11:33 noisy kernel: eth0:  Autonegotiation advertising 01e1 link
partn
er 0001. 
Jun  9 12:11:33 noisy kernel: Found Digital DS21143 Tulip at PCI I/O
address 0x1
0000b000. 
Jun  9 12:11:33 noisy kernel: tulip.c:v0.91g-ppc 7/16/99
becker@cesdis.gsfc.nasa
.gov 
Jun  9 12:11:33 noisy kernel: eth1: Digital DS21143 Tulip rev 65 at
0x10000b000,
 00:80:C8:CA:AB:45, IRQ 43. 
Jun  9 12:11:33 noisy kernel: eth1:  EEPROM default media type Autosense. 
Jun  9 12:11:33 noisy kernel: eth1:  MII interface PHY 0, setup/reset
sequences 
0/0 long, capabilities e0 78. 
Jun  9 12:11:33 noisy kernel: eth1:  Index #0 - Media MII (#11) described
by a 2
1142 MII PHY (3) block. 
Jun  9 12:11:33 noisy kernel: eth1:  MII transceiver #1 config 3100 status
7869 
advertising 01e1. 
Jun  9 12:11:33 noisy kernel: Found Digital DS21143 Tulip at PCI I/O
address 0x1
0000b800. 
Jun  9 12:11:33 noisy kernel: eth2: Digital DS21143 Tulip rev 65 at
0x10000b800,
 00:80:C8:CA:AB:46, IRQ 42. 
Jun  9 12:11:33 noisy kernel: eth2:  EEPROM default media type Autosense. 
Jun  9 12:11:33 noisy kernel: eth2:  MII interface PHY 0, setup/reset
sequences 
0/0 long, capabilities e0 78. 
Jun  9 12:11:33 noisy kernel: eth2:  Index #0 - Media MII (#11) described
by a 2
1142 MII PHY (3) block. 
Jun  9 12:11:33 noisy kernel: eth2:  MII transceiver #1 config 3100 status
7869 
advertising 01e1. 
Jun  9 12:11:33 noisy kernel: Found Digital DS21143 Tulip at PCI I/O
address 0x1
0000c000. 
Jun  9 12:11:33 noisy kernel: eth3: Digital DS21143 Tulip rev 65 at
0x10000c000,
 00:80:C8:CA:AB:47, IRQ 41. 
Jun  9 12:11:33 noisy kernel: eth3:  EEPROM default media type Autosense. 
Jun  9 12:11:33 noisy kernel: eth3:  MII interface PHY 0, setup/reset
sequences 
0/0 long, capabilities e0 78. 
Jun  9 12:11:33 noisy kernel: eth3:  Index #0 - Media MII (#11) described
by a 2
1142 MII PHY (3) block. 
Jun  9 12:11:33 noisy kernel: eth3:  MII transceiver #1 config 3100 status
7869 
advertising 01e1. 
Jun  9 12:11:33 noisy kernel: Found Digital DS21143 Tulip at PCI I/O
address 0x1
0000c800. 
Jun  9 12:11:33 noisy kernel: eth4: Digital DS21143 Tulip rev 65 at
0x10000c800,
 00:80:C8:CA:AB:48, IRQ 40. 
Jun  9 12:11:33 noisy kernel: eth4:  EEPROM default media type Autosense. 
Jun  9 12:11:33 noisy kernel: eth4:  MII interface PHY 0, setup/reset
sequences 
0/0 long, capabilities e0 78. 
Jun  9 12:11:33 noisy kernel: eth4:  Index #0 - Media MII (#11) described
by a 2
1142 MII PHY (3) block. 
Jun  9 12:11:33 noisy kernel: eth4:  MII transceiver #1 config 3100 status
7869 
advertising 01e1.
Jun  9 12:11:34 noisy kernel: eth1: Using MII transceiver 1, status 786d. 
Jun  9 12:11:34 noisy kernel: eth2: Using MII transceiver 1, status 786d. 
Jun  9 12:11:34 noisy kernel: eth3: Using MII transceiver 1, status 786d. 
Jun  9 12:11:34 noisy kernel: eth4: Using MII transceiver 1, status 786d. 
Jun  9 12:11:34 noisy kernel: eth0: Setting full-duplex based on MII #3
link par
tner capability of 45e1. 
Jun  9 12:11:34 noisy kernel: eth1: 21143 negotiation status 000000c6,
MII. 
Jun  9 12:11:34 noisy kernel: eth1: MII status 786d, Link partner report
45e1. 
Jun  9 12:11:34 noisy kernel: eth1: Setting full-duplex based on MII#1
link part
ner capability of 45e1. 
Jun  9 12:11:34 noisy kernel: eth1: The transmitter stopped.  CSR5 is
f0678006, 
CSR6 b20e2202, new CSR6 820e0200. 
Jun  9 12:11:34 noisy kernel: eth2: 21143 negotiation status 000000c6,
MII. 
Jun  9 12:11:34 noisy kernel: eth2: MII status 786d, Link partner report
45e1. 
Jun  9 12:11:34 noisy kernel: eth2: Setting full-duplex based on MII#1
link part
ner capability of 45e1. 
Jun  9 12:11:34 noisy kernel: eth2: The transmitter stopped.  CSR5 is
f0678006, 
CSR6 b20e2202, new CSR6 820e0200. 
Jun  9 12:11:34 noisy kernel: eth3: 21143 negotiation status 000000c6,
MII. 
Jun  9 12:11:34 noisy kernel: eth3: MII status 786d, Link partner report
45e1. 
Jun  9 12:11:34 noisy kernel: eth3: Setting full-duplex based on MII#1
link part
ner capability of 45e1. 
Jun  9 12:11:34 noisy kernel: eth3: The transmitter stopped.  CSR5 is
f0678006, 
CSR6 b20e2202, new CSR6 820e0200. 
Jun  9 12:11:34 noisy kernel: eth4: 21143 negotiation status 000000c6,
MII. 
Jun  9 12:11:34 noisy kernel: eth4: MII status 786d, Link partner report
45e1. 
Jun  9 12:11:34 noisy kernel: eth4: Setting full-duplex based on MII#1
link part
ner capability of 45e1. 
Jun  9 12:11:34 noisy kernel: eth4: The transmitter stopped.  CSR5 is
f0678006, 
CSR6 b20e2202, new CSR6 820e0200.

Any suggestions on why it keeps on freezing under these conditions?

--
-- John E. Jasen (jjasen1@umbc.edu)
-- You can have it: right; cheap; now. Pick any two.