Hi, Roland, Andrew.
Something really sick is going on with combination of utrace, RCU and ia64.
Below are quickly reproducable oops happenning on 8-way SMP,
my lame-o attempts to decode it, and test program itself.
I checked 2.6.21-rc5 which was OK,
2.6.21-rc5 + linux-2.6.21-current-utrace.patch which was bad, and
2.6.21-rc5-mm1 which was also bad.
------------------------------------------------------------
Unable to handle kernel paging request at virtual address 6b6b6b6b6b6b6b6b
expl_ptratt[4391]: Oops 11012296146944 [1]
Modules linked in: autofs4 hidp rfcomm l2cap bluetooth sunrpc 8021q bridge ipv6
xt_length ipt_ttl xt_tcpmss iptable_mangle iptable_filter xt_multiport xt_limit
ipt_tos ipt_REJECT ip_tables x_tables vfat fat button parport_pc lp parport sg
e100 e1000 mii shpchp ide_cd cdrom dm_snapshot dm_zero dm_mirror dm_mod mptsas
mptscsih mptbase scsi_transport_sas sd_mod scsi_mod ext3 jbd ehci_hcd ohci_hcd
uhci_hcd
Pid: 4391, CPU 4, comm: expl_ptratt
psr : 0000121008026018 ifs : 8000000000000389 ip : [<a000000100094881>] Not
tainted
ip is at __rcu_process_callbacks+0x3e1/0x660
unat: 0000000000000000 pfs : 0000000000000389 rsc : 0000000000000003
rnat: 0000000000000000 bsps: 0000000000000000 pr : 0000000000555965
ldrs: 0000000000000000 ccv : 0000000000000000 fpsr: 0009804c0270033f
csd : 0000000000000000 ssd : 0000000000000000
b0 : a0000001000948a0 b6 : a0000001000d9ee0 b7 : a000000100010080
f6 : 1003e6b6b6b6b6b6b6b6b f7 : 1003e0000000003333334
f8 : 1003e0000000000001680 f9 : 1003e0000000000001680
f10 : 1003e0000000000000048 f11 : 1003e0000000000000050
r1 : a000000100d130a0 r2 : 0000000000000003 r3 : 0000000000000001
r8 : e000000468054028 r9 : e000000468054000 r10 : 0000000000000004
r11 : a00000010095a880 r12 : e000000467bcfc30 r13 : e000000467bc8000
r14 : e0000004681452e8 r15 : e000000107f77940 r16 : e000000107f77978
r17 : 0000000000000002 r18 : 000000000000000a r19 : e000000467bc8c34
r20 : 0000000000000020 r21 : e000000108bb2cac r22 : e000000108a8cdc8
r23 : 0000000000000002 r24 : e0000001000065d8 r25 : 6b6b6b6b6b6b6b6b
r26 : e000000108bb2cc0 r27 : 0000000000000002 r28 : 0000000000000002
r29 : 0000000000004000 r30 : 0000000000004000 r31 : 0000000000000011
Call Trace:
[<a000000100012380>] show_stack+0x40/0xa0
sp=e000000467bcf7c0 bsp=e000000467bc9040
[<a000000100012c80>] show_regs+0x840/0x880
sp=e000000467bcf990 bsp=e000000467bc8fe0
[<a000000100034d80>] die+0x1c0/0x2a0
sp=e000000467bcf990 bsp=e000000467bc8f98
[<a0000001005db5b0>] ia64_do_page_fault+0x8d0/0xa00
sp=e000000467bcf9b0 bsp=e000000467bc8f48
[<a00000010000b300>] ia64_leave_kernel+0x0/0x280
sp=e000000467bcfa60 bsp=e000000467bc8f48
[<a000000100094880>] __rcu_process_callbacks+0x3e0/0x660
sp=e000000467bcfc30 bsp=e000000467bc8f00
[<a000000100094b40>] rcu_process_callbacks+0x40/0xa0
sp=e000000467bcfc30 bsp=e000000467bc8ee0
[<a000000100078fd0>] tasklet_action+0x1d0/0x340
sp=e000000467bcfc30 bsp=e000000467bc8eb8
[<a0000001000785b0>] __do_softirq+0xf0/0x240
sp=e000000467bcfc30 bsp=e000000467bc8e40
[<a000000100078770>] do_softirq+0x70/0xc0
sp=e000000467bcfc30 bsp=e000000467bc8dd8
[<a0000001000789c0>] irq_exit+0x80/0xa0
sp=e000000467bcfc30 bsp=e000000467bc8dc0
[<a000000100010030>] ia64_handle_irq+0x250/0x280
sp=e000000467bcfc30 bsp=e000000467bc8d90
[<a00000010000b300>] ia64_leave_kernel+0x0/0x280
sp=e000000467bcfc30 bsp=e000000467bc8d90
[<a0000001005d6940>] _spin_unlock_irqrestore+0x40/0x80
sp=e000000467bcfe00 bsp=e000000467bc8d60
[<a000000100064cf0>] wait_task_inactive+0x90/0x120
sp=e000000467bcfe00 bsp=e000000467bc8d38
[<a0000001000e1a70>] sys_ptrace+0x890/0x1180
sp=e000000467bcfe10 bsp=e000000467bc8cb0
[<a00000010000b0b0>] ia64_trace_syscall+0xd0/0x110
sp=e000000467bcfe30 bsp=e000000467bc8cb0
[<a000000000010620>] __start_ivt_text+0xffffffff00010620/0x400
sp=e000000467bd0000 bsp=e000000467bc8cb0
Kernel panic - not syncing: Aiee, killing interrupt handler!
-------------------------------------------------------------
a0000001000944a0 <__rcu_process_callbacks>:
...
a000000100094830: nop.m 0x0
a000000100094836: cmp.eq p8,p9=0,r39;; # while (list)
a00000010009483c: nop.i 0x0
a000000100094840: (p09) mov r35=1
a000000100094846: nop.m 0x0
a00000010009484c: (p09) br.cond.dptk.few a0000001000948e0
<__rcu_process_callbacks+0x440>
a000000100094850: nop.m 0x0
a000000100094856: nop.i 0x0
a00000010009485c: br.few a000000100094ae0 <__rcu_process_callbacks+0x640>
a000000100094860: nop.m 0x0
a000000100094866: ld8 r34=[r14],8 # r34 = next = list->next
# r14 = &list->func
a00000010009486c: nop.i 0x0;;
a000000100094870: lfetch [r34] # prefetch(next)
a000000100094876: nop.m 0x0
a00000010009487c: nop.i 0x0;;
a000000100094880: ld8 r25=[r14];; # r25 = list->func
a000000100094886: ===> ld8 r26=[r25],8 # something with something
called .opd (?)
# I couldn't understand
a00000010009488c: nop.i 0x0;;
a000000100094890: ld8 r1=[r25]
a000000100094896: mov b6=r26
a00000010009489c: br.call.sptk.many b0=b6;; # list->func()
Looks like place corresponds to function call in rcu_do_batch()
list = rdp->donelist;
while (list) {
next = list->next;
prefetch(next);
list->func(list);
list = next;
...
-------------------------------------------------------------
#include <stdio.h>
#include <unistd.h>
#include <pthread.h>
#include <sys/ptrace.h>
#include <signal.h>
static void *thread_func(void *arg)
{
execl("/proc/self/exe", NULL);
return NULL;
}
int main(int argc, const char *argv[])
{
pthread_t thread;
int pid, n;
if (argv[0] && (pid = fork()))
for (n = 1;; ++n) {
ptrace(PTRACE_ATTACH, pid, NULL, 0);
ptrace(PTRACE_DETACH, pid, NULL, 0);
if (!(n % 100000))
printf("passed: %d\n", n);
}
if (pthread_create(&thread, NULL, thread_func, NULL))
perror("pthread_create");
while (1)
pause();
return 1;
}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
