RHEL8:因为无法解释的 page_fault 导致内核 panic

Issue

• 内核 panic，带有以下日志信息:

[    2.534476] WARNING: CPU: 12 PID: 1 at arch/x86/kernel/alternative.c:820 __text_poke+0x23b/0x260
[    2.534477] Modules linked in:
[    2.534478] CPU: 12 PID: 1 Comm: systemd Tainted: G    B   W         -------- -  - 4.18.0-553.16.1.el8_10.x86_64 #1
[    2.534479] Hardware name: ASRockRack SO103A_G11/SPC621D8HM3/1U3, BIOS L0.10E 07/27/2023
[    2.534479] RIP: 0010:__text_poke+0x23b/0x260
[    2.534480] Code: e2 4c 89 ee 4c 89 f7 e8 e3 13 9e 00 31 d2 31 f6 bf 86 02 00 00 48 8b 05 8b 4f 3a 01 e8 de 42 9f 00 e9 4c ff ff ff 0f 0b 0f 0b <0f> 0b e9 39 fe ff ff 48 8b 05 47 5d 9e 01 e9 49 fe ff ff 48 8b 1d
[    2.534481] RSP: 0018:ff42d86780067ca8 EFLAGS: 00010246
[    2.534482] RAX: 0017ffffc0000000 RBX: ffb63418caeac500 RCX: 0000000000000001
[    2.534482] RDX: 0000000000000001 RSI: ffffffffb7493e2a RDI: ffffffffb5714157
[    2.534483] RBP: ffffffffb5714157 R08: 0000000000000000 R09: 0000000000000000
[    2.534483] R10: ff2f82044002afa0 R11: 0000000000000000 R12: 0000000000000001
[    2.534484] R13: ffffffffb7493e2a R14: ffffffffb5715157 R15: ffb6341800000000
[    2.534485] FS:  00007f41826df9c0(0000) GS:ff2f82ffbff00000(0000) knlGS:0000000000000000
[    2.534485] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    2.534486] CR2: 0000562a10d61658 CR3: 0000000401f34002 CR4: 0000000000771ee0
[    2.534486] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    2.534487] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    2.534487] PKRU: 55555554
[    2.534488] Call Trace:
[    2.534488]  ? __warn+0x94/0xe0
[    2.534489]  ? __text_poke+0x23b/0x260
[    2.534490]  ? __text_poke+0x23b/0x260
[    2.534491]  ? report_bug+0xb1/0xe0
[    2.534492]  ? do_error_trap+0x9e/0xd0
[    2.534494]  ? do_invalid_op+0x36/0x40
[    2.534495]  ? __text_poke+0x23b/0x260
[    2.534496]  ? invalid_op+0x14/0x20
[    2.534497]  ? retransmits_timed_out.part.11+0x117/0x1e0
[    2.534499]  ? tcp_send_fin+0x187/0x230
[    2.534501]  ? tcp_send_fin+0x187/0x230
[    2.534502]  ? __text_poke+0x23b/0x260
[    2.534503]  ? __text_poke+0x2f/0x260
[    2.534505]  text_poke_bp_batch+0x1be/0x260
[    2.534506]  text_poke_finish+0x1b/0x2a
[    2.534507]  arch_jump_label_transform_apply+0x16/0x30
[    2.534508]  static_key_disable_cpuslocked+0x58/0x90
[    2.534509]  static_key_disable+0x16/0x20
[    2.534510]  rebind_subsystems+0x401/0x4c0
[    2.534511]  cgroup_setup_root+0x17c/0x310
[    2.534512]  cgroup1_get_tree+0x239/0x3b9
[    2.534514]  vfs_get_tree+0x25/0xc0
[    2.534515]  do_mount+0x2e9/0x950
[    2.534517]  ksys_mount+0xbe/0xe0
[    2.534518]  __x64_sys_mount+0x21/0x30
[    2.534519]  do_syscall_64+0x5b/0x1a0
[    2.534521]  entry_SYSCALL_64_after_hwframe+0x66/0xcb
[    2.534522] RIP: 0033:0x7f4180950dbe
[    2.534523] Code: 48 8b 0d cd 60 39 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 9a 60 39 00 f7 d8 64 89 01 48
[    2.534524] RSP: 002b:00007ffc3d2aa458 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5
..............
[718740.625398] BUG: unable to handle kernel paging request at ff2f8235fb5c3000
[718740.625419] PGD 32bd601067 P4D 32bd602067 PUD 401e00063 PMD 80000032bb4001e1 
[718740.625433] Oops: 0003 [#1] SMP NOPTI
[718740.625441] CPU: 4 PID: 2034373 Comm: sbatchd Kdump: loaded Tainted: G    B   W  OE     -------- -  - 4.18.0-553.16.1.el8_10.x86_64 #1
[718740.625460] Hardware name: ASRockRack SO103A_G11/SPC621D8HM3/1U3, BIOS L0.10E 07/27/2023
[718740.625474] RIP: 0010:clear_page_erms+0x7/0x10
[718740.625485] Code: 48 89 47 18 48 89 47 20 48 89 47 28 48 89 47 30 48 89 47 38 48 8d 7f 40 75 d9 90 c3 cc cc cc cc 0f 1f 00 b9 00 10 00 00 31 c0 <f3> aa c3 cc cc cc cc 90 90 48 85 ff 0f 84 f4 00 00 00 48 8d 47 01
[718740.625513] RSP: 0000:ff42d8679bfefb90 EFLAGS: 00010246
[718740.625522] RAX: 0000000000000000 RBX: 0000000000000301 RCX: 0000000000001000
[718740.625533] RDX: ff2f820747464000 RSI: ffb63418caed70c0 RDI: ff2f8235fb5c3000
[718740.625545] RBP: ffb63418caed70c0 R08: ffb63418caed7100 R09: ffffffffffffffff
[718740.625556] R10: 0000000000000000 R11: 0000000000000100 R12: 0000000000000000
[718740.625568] R13: 00000000006280ca R14: 0000000000000001 R15: ff2f8303bffd4b80
[718740.625583] FS:  00007f78245d2780(0000) GS:ff2f82ffbfd00000(0000) knlGS:0000000000000000
[718740.625599] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[718740.625610] CR2: ff2f8235fb5c3000 CR3: 0000002c03544001 CR4: 0000000000771ee0
[718740.625624] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[718740.625638] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[718740.625652] PKRU: 55555554
[718740.625658] Call Trace:
[718740.625666]  ? __die_body+0x1a/0x60
[718740.625677]  ? no_context+0x1ba/0x3f0
[718740.625686]  ? __bad_area_nosemaphore+0x157/0x180
[718740.625697]  ? do_page_fault+0x37/0x12d
[718740.625706]  ? page_fault+0x1e/0x30
[718740.625717]  ? clear_page_erms+0x7/0x10
[718740.625726]  prep_new_page+0x92/0x100
[718740.625736]  get_page_from_freelist+0x11b1/0x13b0
[718740.625747]  __alloc_pages_nodemask+0x166/0x330
[718740.625757]  alloc_pages_vma+0x7e/0x200
[718740.625767]  handle_pte_fault+0x354/0x880
[718740.625777]  __handle_mm_fault+0x552/0x6d0
[718740.625787]  handle_mm_fault+0xca/0x2a0
[718740.625797]  __do_page_fault+0x1e4/0x440
[718740.625806]  do_page_fault+0x37/0x12d
[718740.625814]  ? page_fault+0x8/0x30
[718740.625823]  page_fault+0x1e/0x30
[718740.625831] RIP: 0033:0x70ba54
[718740.625839] Code: 00 31 d2 89 05 e9 d9 55 00 39 c2 7c 10 eb 2c 66 66 66 90 66 66 90 48 8b 0d c9 d9 55 00 48 63 f2 ff c2 48 8d 1c 76 48 c1 e3 04 <c7> 04 0b ff ff ff ff 8b 05 b7 d9 55 00 39 c2 7c db 48 63 f8 be 04
[718740.625874] RSP: 002b:00007fffe8748c50 EFLAGS: 00010206
[718740.625885] RAX: 000000000000ffff RBX: 000000000016e000 RCX: 00007f78226c5010
[718740.626058] RDX: 0000000000007a01 RSI: 0000000000007a00 RDI: 0000000000000000
[718740.626217] RBP: 0000000000a940a0 R08: 00007f78226c5010 R09: 0000000000000000
[718740.626352] R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000000005
[718740.626483] R13: 00007fffe874e948 R14: 0000000000000000 R15: 0000000000000000
[718740.626614] Modules linked in: dm_mod nfsv3 nfs_acl nfs lockd grace fscache bonding tls vfat fat ipmi_ssif rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_iser libiscsi scsi_transport_iscsi rdma_cm iw_cm ib_cm intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common i10nm_edac nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm iTCO_wdt iTCO_vendor_support irqbypass bnxt_re crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ib_uverbs rapl intel_cstate ib_core cdc_ether joydev usbnet intel_uncore mii pcspkr isst_if_mbox_pci isst_if_mmio mei_me ioatdma isst_if_common mei i2c_i801 wmi dca intel_vsec acpi_ipmi ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter acpi_pad binfmt_misc asrdev(OE) xfs libcrc32c ast i2c_algo_bit drm_shmem_helper drm_kms_helper syscopyarea sysfillrect sysimgblt drm nvme ahci nvme_core bnxt_en libahci libata crc32c_intel t10_pi fuse
[718740.627731] CR2: ff2f8235fb5c3000

• 另一个日志信息：

[    2.589205] WARNING: CPU: 0 PID: 1 at arch/x86/kernel/alternative.c:815 __text_poke+0x23b/0x260
[    2.589207] Modules linked in:
[    2.589207] CPU: 0 PID: 1 Comm: systemd Tainted: G    B   W        --------- -  - 4.18.0-372.75.1.el8_6.x86_64 #1
[    2.589208] Hardware name: ASRockRack SO103A_G11/SPC621D8HM3/1U3, BIOS L0.10E 07/27/2023
[    2.589209] RIP: 0010:__text_poke+0x23b/0x260
[    2.589210] Code: e2 4c 89 ee 4c 89 f7 e8 f3 c4 99 00 31 d2 31 f6 bf 86 02 00 00 48 8b 05 0b 84 18 01 e8 6e 54 bd 00 e9 4c ff ff ff 0f 0b 0f 0b <0f> 0b e9 39 fe ff ff 48 8b 05 47 c2 7e 01 e9 49 fe ff ff 48 8b 1d
[    2.589211] RSP: 0018:ff506cd680067c98 EFLAGS: 00010246
[    2.589212] RAX: 0017ffffc0000000 RBX: ffc93329010cce40 RCX: 0000000000000001
[    2.589212] RDX: 0000000000000001 RSI: ffffffffa280da09 RDI: ffffffffa0739849
[    2.589213] RBP: ffffffffa0739849 R08: 000000000000000f R09: 0000000000000000
[    2.589213] R10: ff30fd50c13b5ab0 R11: 0000000000000000 R12: 0000000000000001
[    2.589214] R13: ffffffffa280da09 R14: ffffffffa073a849 R15: ffc93326c0000000
[    2.589215] FS:  00007f2d1989a9c0(0000) GS:ff30fe453fc00000(0000) knlGS:0000000000000000
[    2.589215] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    2.589216] CR2: 00005562a153f658 CR3: 0000000121d14003 CR4: 0000000000771ef0
[    2.589216] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    2.589217] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    2.589217] PKRU: 55555554
[    2.589218] Call Trace:
[    2.589218]  text_poke_bp_batch+0x121/0x190
[    2.589220]  text_poke_finish+0x1b/0x2a
[    2.589222]  arch_jump_label_transform_apply+0x16/0x30
[    2.589223]  static_key_disable_cpuslocked+0x58/0x90
[    2.589224]  static_key_disable+0x16/0x20
[    2.589225]  rebind_subsystems+0x397/0x480
[    2.589226]  cgroup_setup_root+0x176/0x300
[    2.589227]  cgroup1_get_tree+0x239/0x3c6
[    2.589229]  vfs_get_tree+0x25/0xc0
[    2.589231]  do_mount+0x2e9/0x950
[    2.589232]  ksys_mount+0xbe/0xe0
[    2.589234]  __x64_sys_mount+0x21/0x30
[    2.589235]  do_syscall_64+0x5b/0x1b0
[    2.589237]  entry_SYSCALL_64_after_hwframe+0x61/0xc6
[    2.589238] RIP: 0033:0x7f2d17b242be
[    2.589239] Code: 48 8b 0d cd 4b 38 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 9a 4b 38 00 f7 d8 64 89 01 48
[    2.589240] RSP: 002b:00007ffede08d118 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5
[    2.589241] RAX: ffffffffffffffda RBX: 00007ffede08d180 RCX: 00007f2d17b242be
[    2.589241] RDX: 00005562a0ebd8a4 RSI: 00005562a153dd10 RDI: 00005562a0ebd8a4
[    2.589242] RBP: 0000000000000007 R08: 00005562a153dbc0 R09: 0000000000000005
[    2.589242] R10: 000000000000000e R11: 0000000000000246 R12: 00000000fffffffe
[    2.589243] R13: 0000000000000001 R14: 0000000000000000 R15: 00005562a153dd10
[    2.589244] ---[ end trace 55fe15356ee004ed ]---
..............
[    2.629719] BUG: Bad rss-counter state mm:00000000fdf32e35 idx:1 val:-1
[    2.632979] BUG: Bad rss-counter state mm:00000000fdf32e35 idx:3 val:1
..............
[1228225.411684] BUG: unable to handle kernel paging request at ff30fdd903000000
[1228225.411701] PGD 9046201067 P4D 1007ffff067 PUD 121e0a063 PMD 80000090430001e1
[1228225.411715] Oops: 0003 [#1] SMP NOPTI
[1228225.411723] CPU: 1 PID: 3764865 Comm: primesim_spice Kdump: loaded Tainted: G    B   W  OE    --------- -  - 4.18.0-372.75.1.el8_6.x86_64 #1
[1228225.411743] Hardware name: ASRockRack SO103A_G11/SPC621D8HM3/1U3, BIOS L0.10E 07/27/2023
[1228225.411755] RIP: 0010:clear_page_erms+0x7/0x10
[1228225.411767] Code: 48 89 47 18 48 89 47 20 48 89 47 28 48 89 47 30 48 89 47 38 48 8d 7f 40 75 d9 90 e9 b3 bd 23 00 0f 1f 00 b9 00 10 00 00 31 c0 <f3> aa e9 a2 bd 23 00 90 90 48 85 ff 0f 84 f4 00 00 00 48 8d 47 01
[1228225.411794] RSP: 0000:ff506cd6c00b3b90 EFLAGS: 00010246
[1228225.411803] RAX: 0000000000000000 RBX: 0000000000000301 RCX: 0000000000001000
[1228225.411815] RDX: ff30fd793e7bc000 RSI: ffc93329010c0000 RDI: ff30fdd903000000
[1228225.411826] RBP: ffc93329010c0000 R08: ffc93329010c0040 R09: 0000000007c6ed78
[1228225.411837] R10: 0000000000000000 R11: 0000000000000100 R12: 0000000000000000
[1228225.411848] R13: 00000000006280ca R14: 0000000000000001 R15: 0000000000000000
[1228225.411859] FS:  0000155549e76000(0000) GS:ff30fe453fc40000(0000) knlGS:0000000000000000
[1228225.411871] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[1228225.411881] CR2: ff30fdd903000000 CR3: 00000005258d0003 CR4: 0000000000771ee0
[1228225.411892] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[1228225.411903] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[1228225.411913] PKRU: 55555554
[1228225.411919] Call Trace:
[1228225.411924]  prep_new_page+0x92/0x100
[1228225.411935]  get_page_from_freelist+0x1114/0x1360
[1228225.411945]  ? nfs_mapping_need_revalidate_inode+0x13/0x30 [nfs]
[1228225.411968]  ? nfs_check_verifier+0x46/0xa0 [nfs]
[1228225.411983]  __alloc_pages_nodemask+0x166/0x320
[1228225.411992]  alloc_pages_vma+0x74/0x1d0
[1228225.412000]  handle_pte_fault+0x354/0x880
[1228225.412008]  __handle_mm_fault+0x453/0x6c0
[1228225.412017]  handle_mm_fault+0xca/0x2a0
[1228225.412024]  __do_page_fault+0x1f0/0x460
[1228225.412033]  do_page_fault+0x37/0x130
[1228225.412041]  ? page_fault+0x8/0x30
[1228225.412049]  page_fault+0x1e/0x30
[1228225.412056] RIP: 0033:0x3a617ee
[1228225.412063] Code: 72 da 41 d1 e9 41 39 d1 77 c2 41 83 c0 01 d1 ea 0f 85 06 ff ff ff 66 0f 1f 44 00 00 89 f9 89 d0 83 c2 01 d1 ef f2 0f 10 04 cb <f2> 41 0f 11 04 c4 75 ea f2 0f 10 03 48 8d 65 e0 5b 41 5c 41 5d 41