Description of problem: Kernel panic within minutes of of starting load run. Version-Release number of selected component (if applicable): 2.4.21-17.ELsmp on an x86_64 How reproducible: Very, just about every run. Steps to Reproduce: 1.Run heavy load of sequential read (512 bytes) requests to 30 Fiber channel disks (30 processes) 2.HBA is Qlogic ISP 2312 using default qla2300.o driver 3.Opteron based system with 8 Gig memory Actual results: Red Hat Enterprise Linux AS release 3 (Taroon Update 3) Kernel 2.4.21-17.ELsmp on an x86_64 Unable to handle kernel paging request at virtual address ffffffffffffffff printing rip: ffffffffa000952c PML4 103027 PGD 18344f067 PMD 0 Oops: 0002 CPU 2 Pid: 2296, comm: rawread Not tainted RIP: 0010:[<ffffffffa000952c>]{:scsi_mod:scsi_request_fn+188} RSP: 0018:000001017f597ce8 EFLAGS: 00010097 RAX: ffffffffffffffff RBX: 00000101ffa1d430 RCX: 00000101fe7ead98 RDX: 0000000000000018 RSI: 000001017f597d98 RDI: ffffffffa0010a2b RBP: 000001017f597d68 R08: 0000000000000000 R09: 0000000000000003 R10: 0000000000000001 R11: 0000000000000001 R12: 00000101ffa1d400 R13: 00000101ffd78000 R14: 00000101ffa1d430 R15: 0000000000000001 FS: 000000004a9ff970(005b) GS:ffffffff805dd040(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffffffffffffffff CR3: 00000000079c3000 CR4: 00000000000006e0 Call Trace: [<ffffffff801f7a05>]{submit_bh_linked+357} [<ffffffff801f6669>]{generic_unplug_device+89} [<ffffffff8012aec3>]{__run _task_queue+115} [<ffffffff8017a786>]{kiobuf_wait_for_io+102} [<ffffffff80162936>]{brw_kio vec+1174} [<ffffffff8013bc9a>]{__get_user_pages+314} [<ffffffff801e0635>] {rw_raw_de v+453} [<ffffffff8015de52>]{sys_read+178} [<ffffffff80110177>] {system_call+119} Process rawread (pid: 2296, stackpage=1017f597000) Stack: 000001017f597ce8 0000000000000018 0000000000000000 000001017f597cf8 ffffffff801f7a05 0000000000000020 00000101ffa1d430 000001017f597d68 000001017f597d98 00000101fe7ead90 0000000000000200 0000000000000001 ffffffff801f6669 00000101ffd78100 0000000000000212 000001017f597d68 ffffffff8012aec3 0000000000000000 0000000000000212 00000101ffa1d4d8 00000101ffa1d4d8 0000000000000001 000001017f596000 00000101fe7ead40 ffffffff8017a786 0000000000000000 000001017f596000 00000101fe7ead98 00000101fe7ead98 0000000000000000 0000000000000000 00000101fe8e9aa8 00000101fe8e9aa8 00000101fe7ead40 0000000000000001 0000000000000009 ffffffff80162936 000001017f596000 0000000000000000 0000000000000200 Call Trace: [<ffffffff801f7a05>]{submit_bh_linked+357} [<ffffffff801f6669>]{generic_unplug_device+89} [<ffffffff8012aec3>]{__run _task_queue+115} [<ffffffff8017a786>]{kiobuf_wait_for_io+102} [<ffffffff80162936>]{brw_kio vec+1174} [<ffffffff8013bc9a>]{__get_user_pages+314} [<ffffffff801e0635>] {rw_raw_de v+453} [<ffffffff8015de52>]{sys_read+178} [<ffffffff80110177>] {system_call+119} Code: f0 fe 08 0f 88 74 04 00 00 41 8b 95 b4 00 00 00 85 d2 7e 0c Kernel panic: Fatal exception Expected results: no panic Additional info: We have NDA with RedHat that can be used for additional system configuration information.
This looks like general highmem mapping issues on x86_64 that were solved some time ago. If this problem still persists, please let us know.
This bug has been in NEEDINFO for an extended period of time. I'm assuming that indicates the issue was resolved. Closing this bug out.