How to get ECC error log of Xeon SPR

[ponsu]

I used SPR processor(Intel® Xeon® Gold 6430) and Servel model H3C G6 Ultra to test DDR5 RDIMM. OS:Centos8.5  Linux kernel version 6.6.48.

I test with fail DIMM, but no fail address info print, belowing is EDAC related fail log, please help me check why cant print fail address info.  many thanks

[ 5.227933] EDAC DEBUG: i10nm_init:
[ 5.227943] EDAC DEBUG: skx_get_hi_lo: tolm = 0x7c000000 tohm = 0x107c000000
[ 5.227962] EDAC DEBUG: skx_get_all_bus_mappings: busses: 0x7e, 0x7f, 0x0, 0x0
[ 5.227999] EDAC DEBUG: skx_get_all_bus_mappings: busses: 0xfe, 0xff, 0x0, 0x0
[ 5.228071] EDAC DEBUG: i10nm_get_imc_num: Get DDR CH number: 8
[ 5.228293] EDAC DEBUG: i10nm_get_ddr_munits: socket0 mmio base 0xcc000000 (reg 0x198)
[ 5.228311] EDAC DEBUG: i10nm_get_ddr_munits: mc0 mmio base 0xcc280000 size 0x80000 (reg 0x198)
[ 5.228344] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg 100f0d
[ 5.228361] EDAC DEBUG: i10nm_get_ddr_munits: mc1 mmio base 0xcc300000 size 0x80000 (reg 0x198)
[ 5.228368] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg 40010
[ 5.228385] EDAC DEBUG: i10nm_get_ddr_munits: mc2 mmio base 0xcc380000 size 0x80000 (reg 0x198)
[ 5.228392] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg 40010
[ 5.228409] EDAC DEBUG: i10nm_get_ddr_munits: mc3 mmio base 0xcc400000 size 0x80000 (reg 0x198)
[ 5.228415] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg 40010
[ 5.228489] EDAC DEBUG: i10nm_get_ddr_munits: socket1 mmio base 0xfb800000 (reg 0x1f7)
[ 5.228525] EDAC DEBUG: i10nm_get_ddr_munits: mc0 mmio base 0xfba80000 size 0x80000 (reg 0x1f7)
[ 5.228533] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg ffffffff
[ 5.228534] EDAC DEBUG: i10nm_imc_absent: ch1 mcmtr reg ffffffff
[ 5.228538] EDAC DEBUG: i10nm_get_ddr_munits: Skip absent mc0
[ 5.228574] EDAC DEBUG: i10nm_get_ddr_munits: mc1 mmio base 0xfbb00000 size 0x80000 (reg 0x1f7)
[ 5.228581] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg ffffffff
[ 5.228583] EDAC DEBUG: i10nm_imc_absent: ch1 mcmtr reg ffffffff
[ 5.228586] EDAC DEBUG: i10nm_get_ddr_munits: Skip absent mc1
[ 5.228622] EDAC DEBUG: i10nm_get_ddr_munits: mc2 mmio base 0xfbb80000 size 0x80000 (reg 0x1f7)
[ 5.228629] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg ffffffff
[ 5.228630] EDAC DEBUG: i10nm_imc_absent: ch1 mcmtr reg ffffffff
[ 5.228633] EDAC DEBUG: i10nm_get_ddr_munits: Skip absent mc2
[ 5.228670] EDAC DEBUG: i10nm_get_ddr_munits: mc3 mmio base 0xfbc00000 size 0x80000 (reg 0x1f7)
[ 5.228677] EDAC DEBUG: i10nm_imc_absent: ch0 mcmtr reg ffffffff
[ 5.228678] EDAC DEBUG: i10nm_imc_absent: ch1 mcmtr reg ffffffff
[ 5.228681] EDAC DEBUG: i10nm_get_ddr_munits: Skip absent mc3
[ 5.228682] EDAC i10nm: No hbm memory
[ 5.228684] EDAC DEBUG: i10nm_init: src_id = 0 node_id = 0
[ 5.228690] EDAC DEBUG: skx_register_mci: MC#0: mci = 0000000040eaf733
[ 5.228693] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x9091 mcddrtcfg 0x0 (mc0 ch0 dimm0)
[ 5.228695] EDAC DEBUG: skx_get_dimm_info: mc#0: channel 0, dimm 0, 65536 MiB (16777216 pages) bank: 32, rank: 2, row: 0x10, col: 0xb
[ 5.228698] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x30000 mcddrtcfg 0x0 (mc0 ch0 dimm1)
[ 5.228699] EDAC DEBUG: i10nm_check_ecc: ch0 mcmtr reg 100f0d
[ 5.228702] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc0 ch1 dimm0)
[ 5.228703] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc0 ch1 dimm1)
[ 5.228704] EDAC DEBUG: edac_mc_add_mc_with_groups:
[ 5.228718] EDAC DEBUG: edac_create_sysfs_mci_device: device mc0 created
[ 5.228735] EDAC DEBUG: edac_create_dimm_object: device dimm0 created at location channel 0 slot 0
[ 5.228746] EDAC DEBUG: edac_create_csrow_object: device csrow0 created
[ 5.228765] EDAC MC0: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#0: DEV 0000:7e:0c.0 (INTERRUPT)
[ 5.228771] EDAC DEBUG: skx_register_mci: MC#1: mci = 00000000e9f27481
[ 5.228774] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc1 ch0 dimm0)
[ 5.228776] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc1 ch0 dimm1)
[ 5.228779] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc1 ch1 dimm0)
[ 5.228780] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc1 ch1 dimm1)
[ 5.228781] EDAC DEBUG: edac_mc_add_mc_with_groups:
[ 5.228787] EDAC DEBUG: edac_create_sysfs_mci_device: device mc1 created
[ 5.228799] EDAC MC1: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#1: DEV 0000:7e:0d.0 (INTERRUPT)
[ 5.228803] EDAC DEBUG: skx_register_mci: MC#2: mci = 00000000834ebe66
[ 5.228807] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc2 ch0 dimm0)
[ 5.228808] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc2 ch0 dimm1)
[ 5.228811] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc2 ch1 dimm0)
[ 5.228813] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc2 ch1 dimm1)
[ 5.228814] EDAC DEBUG: edac_mc_add_mc_with_groups:
[ 5.228819] EDAC DEBUG: edac_create_sysfs_mci_device: device mc2 created
[ 5.228828] EDAC MC2: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#2: DEV 0000:7e:0e.0 (INTERRUPT)
[ 5.228833] EDAC DEBUG: skx_register_mci: MC#3: mci = 00000000bd0c7846
[ 5.228838] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc3 ch0 dimm0)
[ 5.228840] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc3 ch0 dimm1)
[ 5.228844] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc3 ch1 dimm0)
[ 5.228846] EDAC DEBUG: i10nm_get_dimm_config: dimmmtr 0x3000c mcddrtcfg 0x0 (mc3 ch1 dimm1)
[ 5.228847] EDAC DEBUG: edac_mc_add_mc_with_groups:
[ 5.228854] EDAC DEBUG: edac_create_sysfs_mci_device: device mc3 created
[ 5.228863] EDAC MC3: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#3: DEV 0000:7e:0f.0 (INTERRUPT)
[ 5.228866] EDAC DEBUG: i10nm_init: src_id = 1 node_id = 1
[ 5.228873] EDAC i10nm: v0.0.6

[Sazirah]

Hi ponsu,

Thank you for posting in Intel Ethernet Communities.

Upon checking from our end, you are using Server from H3C with Intel Xeon Processor 6430 that we believe is embedded in. Based on the information provided on this thread and support limitation from our end, we recommend you to contact H3C support team for further assistance. If H3C suspects a processor issue, they have a path to escalate to Intel engineering for further troubleshooting.

Since we unable to provide much assistance for now regarding this issue, we will proceed with archiving this case at our end. However, if you have any other questions, please let us know.

Regards,

Sazzy_Intel