Hi David, maybe this crash is related to your recent netfs refactoring work; it is on a server with heavy NFS traffic (with fscache enabled). The kernel is 6.11.5 plus a dozen patches that are not relevant for NFS/netfs/fscache. BUG: unable to handle page fault for address: 0000025882015121 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP PTI CPU: 11 UID: 0 PID: 247837 Comm: kworker/u193:32 Not tainted 6.11.5-cm4all1-hp+ #219 Hardware name: HP ProLiant DL380 Gen9/ProLiant DL380 Gen9, BIOS P89 10/17/2018 Workqueue: nfsiod rpc_async_release RIP: 0010:netfs_rreq_unlock_folios_pgpriv2+0xd2/0x360 Code: 4c 8b 04 24 48 85 c0 49 89 c5 0f 84 38 01 00 00 49 81 fd 06 04 00 00 0f 84 f2 00 00 00 49 81 fd 02 04 00 00 0f 84 35 02 00 00 <49> 8b 45 20 ba 00 10 00 00 49 8b 4d 00 48 c1 e0 0c 83 e1 40 74 08 RSP: 0018:ffffb0056373fc90 EFLAGS: 00010216 RAX: 000000000000002d RBX: ffff89de0d2a6780 RCX: 0000000000000001 RDX: 00000000000000ad RSI: 0000000000000001 RDI: ffff89deb02e7b50 RBP: 0000000000000000 R08: ffff89de3c9e9400 R09: 000000000000002c R10: 0000000000000008 R11: 0000000000000001 R12: 00000000000000b7 R13: 0000025882015101 R14: 0000000000000000 R15: ffffb0056373fd28 FS: 0000000000000000(0000) GS:ffff89f51fac0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000025882015121 CR3: 000000005942e006 CR4: 00000000001706f0 Call Trace: <TASK> ? __die+0x1f/0x60 ? page_fault_oops+0x15c/0x450 ? search_extable+0x22/0x30 ? netfs_rreq_unlock_folios_pgpriv2+0xd2/0x360 ? search_module_extables+0xe/0x40 ? exc_page_fault+0x5e/0x100 ? asm_exc_page_fault+0x22/0x30 ? netfs_rreq_unlock_folios_pgpriv2+0xd2/0x360 ? select_task_rq_fair+0x1ed/0x1370 netfs_rreq_unlock_folios+0x40c/0x4b0 netfs_rreq_assess+0x348/0x580 netfs_subreq_terminated+0x193/0x2a0 nfs_netfs_read_completion+0x97/0xb0 nfs_read_completion+0x12e/0x200 rpc_free_task+0x39/0x60 rpc_async_release+0x2b/0x40 process_one_work+0x134/0x2e0 worker_thread+0x299/0x3a0 ? __pfx_worker_thread+0x10/0x10 kthread+0xba/0xe0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x30/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Modules linked in: CR2: 0000025882015121 ---[ end trace 0000000000000000 ]--- ERST: [Firmware Warn]: Firmware does not respond in time. pstore: backend (erst) writing error (-5) RIP: 0010:netfs_rreq_unlock_folios_pgpriv2+0xd2/0x360 Code: 4c 8b 04 24 48 85 c0 49 89 c5 0f 84 38 01 00 00 49 81 fd 06 04 00 00 0f 84 f2 00 00 00 49 81 fd 02 04 00 00 0f 84 35 02 00 00 <49> 8b 45 20 ba 00 10 00 00 49 8b 4d 00 48 c1 e0 0c 83 e1 40 74 08 RSP: 0018:ffffb0056373fc90 EFLAGS: 00010216 RAX: 000000000000002d RBX: ffff89de0d2a6780 RCX: 0000000000000001 RDX: 00000000000000ad RSI: 0000000000000001 RDI: ffff89deb02e7b50 RBP: 0000000000000000 R08: ffff89de3c9e9400 R09: 000000000000002c R10: 0000000000000008 R11: 0000000000000001 R12: 00000000000000b7 R13: 0000025882015101 R14: 0000000000000000 R15: ffffb0056373fd28 FS: 0000000000000000(0000) GS:ffff89f51fac0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000025882015121 CR3: 000000005942e006 CR4: 00000000001706f0 note: kworker/u193:32[247837] exited with irqs disabled (gdb) p netfs_rreq_unlock_folios_pgpriv2+0xd2 $1 = (void (*)(struct netfs_io_request *, size_t *)) 0xffffffff813d80c2 <netfs_rreq_unlock_folios_pgpriv2+210> (gdb) disassemble netfs_rreq_unlock_folios_pgpriv2+0xd2 Dump of assembler code for function netfs_rreq_unlock_folios_pgpriv2: [...] 0xffffffff813d8093 <+163>: call 0xffffffff81f0ec70 <xas_find> 0xffffffff813d8098 <+168>: mov (%rsp),%r8 0xffffffff813d809c <+172>: test %rax,%rax 0xffffffff813d809f <+175>: mov %rax,%r13 0xffffffff813d80a2 <+178>: je 0xffffffff813d81e0 <netfs_rreq_unlock_folios_pgpriv2+496> 0xffffffff813d80a8 <+184>: cmp $0x406,%r13 0xffffffff813d80af <+191>: je 0xffffffff813d81a7 <netfs_rreq_unlock_folios_pgpriv2+439> 0xffffffff813d80b5 <+197>: cmp $0x402,%r13 0xffffffff813d80bc <+204>: je 0xffffffff813d82f7 <netfs_rreq_unlock_folios_pgpriv2+775> 0xffffffff813d80c2 <+210>: mov 0x20(%r13),%rax 0xffffffff813d80c6 <+214>: mov $0x1000,%edx 0xffffffff813d80cb <+219>: mov 0x0(%r13),%rcx 0xffffffff813d80cf <+223>: shl $0xc,%rax 0xffffffff813d80d3 <+227>: and $0x40,%ecx 0xffffffff813d80d6 <+230>: je 0xffffffff813d80e0 <netfs_rreq_unlock_folios_pgpriv2+240> 0xffffffff813d80d8 <+232>: movzbl 0x40(%r13),%ecx 0xffffffff813d80dd <+237>: shl %cl,%rdx Right now, the machine is running and I have an unstripped kernel, just in case you need more information from /proc/kcore. Max [resent as text/plain only - damn you, gmail!]
