1822网卡环境，打流+反复网卡上下电/热插拔，一段时间后系统crash，出现hinic_physical_port_id空指针访问

【标题描述】1822网卡环境，打流+反复网卡上下电/热插拔，一段时间后系统crash
【环境信息】
硬件信息：
1） Huawei TaiShan 200 (Model 2280)
2） 1822网卡
软件信息：
[root@openEuler ~]# cat /etc/openEuler-latest
openeulerversion=openEuler-22.03-LTS
compiletime=2022-03-05-12-01-45
gccversion=10.3.1-9.oe1
kernelversion=5.10.0-60.2.0.35.oe1
openjdkversion=1.8.0.312.b07-11.oe1 
【附件信息】
[16468.331304] hinic 0000:0c:00.0: [COMM]Pcie device probed
[16468.353121] hinic 0000:0e:00.0: [COMM]Pcie device probe begin
[16468.369056] hinic 0000:0e:00.0: [COMM]Doorbell size: 0x80000, chip mode: 0
[16468.377480] hinic 0000:0e:00.0: [COMM]global_func_idx: 2, func_type: 0, host_id: 0, ppf: 0, mpf: 0
[16468.389044] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000028
[16468.399570] Mem abort info:
[16468.403725]   ESR = 0x96000004
[16468.405507] hinic 0000:0e:00.0: [COMM]Cfg mgmt: ceqs=0x4, remain=0x4
[16468.408008]   EC = 0x25: DABT (current EL), IL = 32 bits
[16468.415612] hinic 0000:0e:00.0: [COMM]Interrupt type: 0, irq num: 32
[16468.422202]   SET = 0, FnV = 0
[16468.422203]   EA = 0, S1PTW = 0
[16468.422207] Data abort info:
[16468.430437] hinic 0000:0e:00.0: [COMM]Request 32 msix vector success
[16468.434143]   ISV = 0, ISS = 0x00000004
[16468.434144]   CM = 0, WnR = 0
[16468.434149] user pgtable: 4k pages, 48-bit VAs, pgdp=0000202069b21000
[16468.438543] hinic 0000:0e:00.0: [COMM]Adjust aeq num to 3
[16468.442674] [0000000000000028] pgd=0000000000000000, p4d=0000000000000000
[16468.482773] Internal error: Oops: 96000004 [#1] SMP
[16468.489008] Modules linked in: hinic(+) vxlan ip6_udp_tunnel udp_tunnel aer_inject bonding vrf 8021q garp mrp xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_nat_tftp nft_objref nf_conntrack_tftp tun bridge stp llc nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_tables ebtable_nat ebtable_broute ip6table_nat ip6table_mangle ip6table_raw ip6table_security iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c iptable_mangle iptable_raw iptable_security rfkill ip_set nfnetlink ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter rpcrdma ipmi_ssif rdma_ucm ib_srpt ib_isert iscsi_target_mod sunrpc target_core_mod ib_iser rdma_cm iw_cm ib_cm libiscsi scsi_transport_iscsi hns_roce_hw_v2 sg hibmc_drm ib_uverbs drm_vram_helper acpi_ipmi drm_ttm_helper ib_core ttm ipmi_si ipmi_devintf ipmi_msghandler hisi_uncore_hha_pmu hisi_uncore_l3c_pmu hisi_uncore_ddrc_pmu
[16468.489085]  hisi_uncore_pmu nls_cp437 vfat fat sch_fq_codel fuse ip_tables ext4 mbcache jbd2 sd_mod t10_pi realtek hclge ghash_ce sha2_ce hisi_sas_v3_hw sha256_arm64 hisi_sas_main sha1_ce sbsa_gwdt libsas ahci libahci scsi_transport_sas hns3 hnae3 libata host_edma_drv i2c_designware_platform i2c_designware_core dm_mirror dm_region_hash dm_log dm_mod aes_neon_bs aes_neon_blk aes_ce_blk crypto_simd cryptd aes_ce_cipher [last unloaded: hinic]
[16468.623463] CPU: 78 PID: 486990 Comm: hinicadm Kdump: loaded Not tainted 5.10.0 #2
[16468.632777] Hardware name: Huawei TaiShan 200 (Model 2280)/BC82AMDD, BIOS 1.38 07/04/2020
[16468.642710] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO BTYPE=--)
[16468.650022] pc : hinic_physical_port_id+0x10/0x40 [hinic]
[16468.656705] lr : hinic_get_pf_id+0x68/0xb0 [hinic]
[16468.662760] sp : ffff800025eebcc0
[16468.667339] x29: ffff800025eebcc0 x28: ffff20206ef71340 
[16468.673899] x27: 0000000000000000 x26: 0000000000000000 
[16468.680453] x25: 0000000000000000 x24: ffff0021127a4800 
[16468.687000] x23: ffff00210e808380 x22: ffff00210e808384 
[16468.693536] x21: 0000000000000001 x20: ffff002111b8c010 
[16468.700061] x19: ffff20205bddfc00 x18: 0000000000000000 
[16468.706585] x17: 0000000000000000 x16: 0000000000000000 
[16468.713096] x15: 0000ffffc6f3165c x14: 0000000000000000 
[16468.719594] x13: 0000000000000000 x12: 0000000000000030 
[16468.726075] x11: 0101010101010101 x10: 0000000000000000 
[16468.732543] x9 : ffff8000095aed6c x8 : 0000000000000004 
[16468.739001] x7 : ffff8000095daba8 x6 : ffff8000095da9b8 
[16468.745448] x5 : ffff8000095b64b4 x4 : ffff20206ef71340 
[16468.751882] x3 : ffff8000095de9a8 x2 : 0000000000000000 
[16468.758305] x1 : ffff20206ef71340 x0 : 0000000000000000 
[16468.764718] Call trace:
[16468.768281]  hinic_physical_port_id+0x10/0x40 [hinic]
[16468.774433]  get_pf_id+0x3c/0x50 [hinic]
[16468.779449]  nictool_exec_cmd+0x240/0x290 [hinic]
[16468.785236]  nictool_k_unlocked_ioctl+0x324/0x640 [hinic]
[16468.791698]  __arm64_sys_ioctl+0xb0/0xf4
[16468.796684]  el0_svc_common.constprop.0+0x7c/0x1bc
[16468.802530]  do_el0_svc+0x2c/0x94
[16468.806903]  el0_svc+0x20/0x30
[16468.810998]  el0_sync_handler+0xb0/0xb4
[16468.815859]  el0_sync+0x160/0x180
[16468.820188] Code: aa1e03e9 d503201f b4000080 f9402000 (3940a000) 
[16468.827347] SMP: stopping secondary CPUs
[16468.834804] Starting crashdump kernel...
[16468.839752] Bye!

src-openEuler/kernel
关闭

内容风险标识

评论 (3)

src-openEuler/kernel关闭 .gitee-modal { width: 500px !important; }

内容风险标识