[LU-2986] Kernel Oops on ioctl LL_IOC_GET_MDTIDX

Fri, 5 Dec 2014 18:50:55 +0000

A PowerPC64 sequoia LAC node panicked when I ran the following test program:

#include <stdio.h>
#include <errno.h>
#include <sys/ioctl.h>
#include <string.h>

#include <sys/stat.h>
#include <fcntl.h>
#include <lustre/lustre_user.h>

int main(int argc, char **argv)
{
        int rc = -1;
        int mdtidx = 0;
        int fd;
        char *path = argv[1];

        if (argc != 2) {
                fprintf(stderr, "Usage: %s <path>\n", argv[0]);
                goto out;
        }

        fd = open(path, O_RDONLY);
        if (fd < 0) {
                fprintf(stderr, "open() error on %s: %s\n", path,
                        strerror(errno));
                goto out;
        }

        rc = ioctl(fd, LL_IOC_GET_MDTIDX, &mdtidx);
        if (rc < 0) {
                fprintf(stderr, "ioctl() error: %s\n", strerror(errno));
                goto out;
        }
        printf("mdtidx %d\n", mdtidx);

out:
        return rc;
}

Here is the backtrace from crash:

PID: 4522   TASK: c000000f565f6900  CPU: 29  COMMAND: "a.out"
 #0 [c000000f4c2632c0] .crash_kexec at c0000000000e5bf4
 #1 [c000000f4c2634c0] .die at c0000000000309d8
 #2 [c000000f4c263570] .bad_page_fault at c000000000043378
 #3 [c000000f4c2635f0] handle_page_fault at c000000000005228
 Data Access error  [300] exception frame:
 R0:  0000000000000000    R1:  c000000f4c2638e0    R2:  d0000000127283e0   
 R3:  c000000e0d6f6f00    R4:  c000000de5ea1700    R5:  0000000000000000   
 R6:  c000000de5ea1838    R7:  0000000000000001    R8:  0000000000000720   
 R9:  0000000000000000    R10: 2b94515100000000    R11: 0000000000003000   
 R12: d0000000136b27f0    R13: c000000001006d80    R14: 000000001012b3dc   
 R15: 0000000000000000    R16: 0000000000000000    R17: 0000000010129c58   
 R18: 0000000010129bf8    R19: 000000001012b948    R20: 0000000000000000   
 R21: 000000001012daf0    R22: c000000f4b772480    R23: 00000000400466af   
 R24: c000000e046d33f8    R25: 0000000000000000    R26: c000000e0d6f6f00   
 R27: d00000000cc74b48    R28: c000000de5ea1700    R29: d00000000cc74b48   
 R30: d000000012726ee0    R31: c000000f4c2638e0   
 NIP: d000000012701940    MSR: 8000000000009032    OR3: d0000000136e7588
 CTR: d0000000127018c0    LR:  d0000000136166ec    XER: 0000000020000010
 CCR: 0000000024000428    MQ:  0000000000000001    DAR: 0000000000000000
 DSISR: 0000000042000000     Syscall Result: 0000000000000000

 #4 [c000000f4c2638e0] .mdc_getattr at d000000012701940 [mdc]
 [Link Register ]  [c000000f4c2638e0] .ll_get_mdt_idx at d0000000136166ec
 #5 [c000000f4c263990] .ll_get_mdt_idx at d0000000136166ec [lustre]  (unreliable)
 #6 [c000000f4c263a60] .ll_dir_ioctl at d0000000136234c4 [lustre]
 #7 [c000000f4c263c00] .vfs_ioctl at c0000000001d7f24
 #8 [c000000f4c263c90] .do_vfs_ioctl at c0000000001d8170
 #9 [c000000f4c263d80] .sys_ioctl at c0000000001d8954
#10 [c000000f4c263e30] syscall_exit at c000000000008564
 syscall  [c01] exception frame:
 R0:  0000000000000036    R1:  00000fffffffedb0    R2:  0000008053993268   
 R3:  0000000000000003    R4:  00000000400466af    R5:  00000fffffffeea0   
 R6:  0000000000004000    R7:  00000080538c91f0    R8:  800000000200f032   
 R9:  0000000000000000    R10: 0000000000000000    R11: 0000000000000000   
 R12: 0000000000000000    R13: 00000080537ac250   
 NIP: 00000080538cfc70    MSR: 800000000200f032    OR3: 0000000000000003
 CTR: 00000080538cfbd0    LR:  000000001000082c    XER: 0000000000000010
 CCR: 0000000042000428    MQ:  0000000000000001    DAR: 00000080538c91dc
 DSISR: 0000000040000000     Syscall Result: 0000000000000003

Console panic message:

Unable to handle kernel paging request for data at address 0x00000000
Faulting instruction address: 0xd000000012701940
Oops: Kernel access of bad area, sig: 11 [#1]
SMP NR_CPUS=1024 NUMA pSeries
Modules linked in: xt_owner nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack mgc(U) lustre(U) mdc(U) fid(U) fld(U) lov(U) osc(U) ptlrpc(U) obdclass(U) lvfs(U) nfs fscache lockd auth_rpcgss nfs_acl ko2iblnd(U) lnet(U) sha512_generic sha256_generic libcfs(U) sunrpc ipt_LOG xt_multiport iptable_filter ip_tables ib_ipoib rdma_ucm ib_ucm ib_uverbs ib_umad rdma_cm ib_cm iw_cm ib_addr ipv6 uinput raid1 sg ses enclosure mlx4_ib ib_sa ib_mad ib_core mlx4_en mlx4_core e1000e ehea ext4 jbd2 mbcache raid456 async_pq async_xor xor async_raid6_recov raid6_pq async_memcpy async_tx sd_mod crc_t10dif ipr dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan]
NIP: d000000012701940 LR: d0000000136166ec CTR: d0000000127018c0
REGS: c000000f4c263660 TRAP: 0300   Not tainted  (2.6.32-348.1chaos.bgq62.ppc64)
MSR: 8000000000009032 <EE,ME,IR,DR>  CR: 24000428  XER: 20000010
DAR: 0000000000000000, DSISR: 0000000042000000
TASK = c000000f565f6900[4522] 'a.out' THREAD: c000000f4c260000 CPU: 29
GPR00: 0000000000000000 c000000f4c2638e0 d0000000127283e0 c000000e0d6f6f00 
GPR04: c000000de5ea1700 0000000000000000 c000000de5ea1838 0000000000000001 
GPR08: 0000000000000720 0000000000000000 2b94515100000000 0000000000003000 
GPR12: d0000000136b27f0 c000000001006d80 000000001012b3dc 0000000000000000 
GPR16: 0000000000000000 0000000010129c58 0000000010129bf8 000000001012b948 
GPR20: 0000000000000000 000000001012daf0 c000000f4b772480 00000000400466af 
GPR24: c000000e046d33f8 0000000000000000 c000000e0d6f6f00 d00000000cc74b48 
GPR28: c000000de5ea1700 d00000000cc74b48 d000000012726ee0 c000000f4c2638e0 
NIP [d000000012701940] .mdc_getattr+0x80/0x3d0 [mdc]
LR [d0000000136166ec] .ll_get_mdt_idx+0x1ac/0x8d0 [lustre]
Call Trace:
[c000000f4c2638e0] [c000000f4c263990] 0xc000000f4c263990 (unreliable)
[c000000f4c263990] [d0000000136166ec] .ll_get_mdt_idx+0x1ac/0x8d0 [lustre]
[c000000f4c263a60] [d0000000136234c4] .ll_dir_ioctl+0x1d14/0x8080 [lustre]
[c000000f4c263c00] [c0000000001d7f24] .vfs_ioctl+0x54/0x140
[c000000f4c263c90] [c0000000001d8170] .do_vfs_ioctl+0x90/0x7c0
[c000000f4c263d80] [c0000000001d8954] .SyS_ioctl+0xb4/0xd0
[c000000f4c263e30] [c000000000008564] syscall_exit+0x0/0x40
Instruction dump:
7fa85840 41dd02e0 eb7e8028 801b0000 780907e1 41820014 e93e8030 80090000 
7809ffe3 408201fc 38000000 7f43d378 <f8190000> 48012c3d e8410028 e89e8048

Source code information:

(gdb) l *(mdc_getattr+0x80)
0x11940 is in mdc_getattr (/builddir/build/BUILD/lustre-2.3.58/lustre/mdc/mdc_request.c:211).
206     /builddir/build/BUILD/lustre-2.3.58/lustre/mdc/mdc_request.c: No such file or directory.
        in /builddir/build/BUILD/lustre-2.3.58/lustre/mdc/mdc_request.c
(gdb)

 204 int mdc_getattr(struct obd_export *exp, struct md_op_data *op_data,
 205                 struct ptlrpc_request **request)
 206 {
 207         struct ptlrpc_request *req;
 208         int                    rc;
 209         ENTRY;
 210 
 211         *request = NULL;
 212         req = ptlrpc_request_alloc(class_exp2cliimp(exp), &RQF_MDS_GETATTR);
 213         if (req == NULL)
 214                 RETURN(-ENOMEM);

Whamcloud Community JIRA

[LU-2986] Kernel Oops on ioctl LL_IOC_GET_MDTIDX