[dpdk-dev] [Bug 263] ixgbe does not support 10GBASE-T copper SFP+

[bugzilla@dpdk.org]

https://bugs.dpdk.org/show_bug.cgi?id=263

            Bug ID: 263
           Summary: ixgbe does not support 10GBASE-T copper SFP+
           Product: DPDK
           Version: 17.11
          Hardware: x86
                OS: Linux
            Status: CONFIRMED
          Severity: normal
          Priority: Normal
         Component: ethdev
          Assignee: dev@dpdk.org
          Reporter: ido@cgstowernetworks.com
  Target Milestone: ---

Tried couple of vendor's 10GBASE-T copper SFPs and they fail at init
Transceiver example http://www.eoptolink.com/products/copper-10g-sfp

        root@AFS:/home/cgs# ./testpmd -c7 -n3 -w 0000:0a:00.0 -- -i
        EAL: Detected 28 lcore(s)
        EAL: Detected 2 NUMA nodes
        EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
        EAL: No available hugepages reported in hugepages-1048576kB
        EAL: Probing VFIO support...
        EAL: PCI device 0000:0a:00.0 on NUMA socket 0
        EAL:   probe driver: 8086:10fb net_ixgbe
        eth_ixgbe_dev_init(): Unsupported SFP+ Module
        eth_ixgbe_dev_init(): Hardware Initialization Failure: -19
        EAL: ethdev initialisation failedEAL: Requested device 0000:0a:00.0
cannot be used
        testpmd: No probed ethernet devices

Tested in 2 different Intel controllers 82599ES and X552 
        cgs@AFS:~# lspci -s  0a:00.0
        0a:00.0 Ethernet controller: Intel Corporation 82599ES 10-Gigabit
SFI/SFP+ Network Connection (rev 01)
        cgs@AFS:~$ lspci -s 04:00.0
        04:00.0 Ethernet controller: Intel Corporation Ethernet Connection X552
10 GbE SFP+


If the SFPs is inserted only *after* the dpdk app starts (after rte_eal_init
and pci devices are probed) it will work! 
as it is only identified and blocked as not supported in
ixgbe_identify_sfp_module_generic
Though the ixgbe_identify_sfp_module_generic function tries to be premissive in
case the allow_unsupported_sfp is set
        if (hw->allow_unsupported_sfp == true) {
                                EWARN(hw,
                                        "WARNING: Intel (R) Network Connections
are quality tested using Intel (R) Ethernet Optics. "
                                        "Using untested modules is not
supported and may cause unstable operation or damage to the module or the
adapter. "
                                        "Intel Corporation is not responsible
for any harm caused by using untested modules.\n");
                                status = IXGBE_SUCCESS;
                        }
but this is too late as this SFP falls into earlier case in the function
        /* Verify supported 1G SFP modules */
        if (comp_codes_10g == 0 &&
                    !(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 ||
                      hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 ||
                      hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 ||
                      hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 ||
                      hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 ||
                      hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) {
                        hw->phy.type = ixgbe_phy_sfp_unsupported;
                        status = IXGBE_ERR_SFP_NOT_SUPPORTED;
                        goto out;
                }

The driver reads 0 from eeprom IXGBE_SFF_10GBE_COMP_CODES offset and
comp_codes_10g=0 
I guess because there's no 10GBASE-T code defined in SFF-8472 TABLE 5-3
TRANSCEIVER COMPLIANCE CODES [https://members.snia.org/document/dl/25916] 

This same 10GBASE-T SFP does work in i40e controllers

see more info and suggested patch in
http://mails.dpdk.org/archives/dev/2019-April/131091.html

-- 
You are receiving this mail because:
You are the assignee for the bug.