[BProc] RPC race condition in kernel 2.4.20

[<gor...@ph...>]

Some of the oops people have been seeing in the 2.4.20 kernels may have
been due to an RPC race condition.  Here's a kernel thread on the topic,
and a couple of ksymoops from my systems:

http://www.ussg.iu.edu/hypermail/linux/kernel/0302.0/1146.html

These oops are from systems running 3.2.5, but the also occurred under
3.2.4.  They appear to be perciptated by simultaneous spikes in CPU and
network (NFS?) load, which happens regularly on compute clusters.  I've
contacted the original poster, who hasn't seen the problem since upgrading
to 2.4.21-rc6.   Has anyone tried bproc on 2.4.21 yet?
======================================================================================
ksymoops 2.4.8 on i686 2.4.20.  Options used
     -V (default)
     -k /proc/ksyms (default)
     -l /proc/modules (default)
     -o /lib/modules/2.4.20/ (default)
     -m /boot/System.map (specified)

Unable to handle kernel NULL pointer dereference at virtual address 00000058
c0303206
*pde = 00000000
Oops: 0000
CPU:    0
EIP:    0010:[<c0303206>]    Not tainted
Using defaults from ksymoops -t elf32-i386 -a i386
EFLAGS: 00010202
eax: 0000002c   ebx: 00000000   ecx: 00000008   edx: 00000001
esi: f7611078   edi: e7bc2480   ebp: f7611000   esp: c2837edc
ds: 0018   es: 0018   ss: 0018
Process swapper (pid: 0, stackpage=c2837000)
Stack: e7bc2480 c03031c0 00000020 00000000 c0304442 e7bc2480 e7bc24d4 c03043c0
       c0123b47 e7bc2480 c2837f0c 00000001 c882a0e4 f7bfbd78 00000000 00000001
       00000020 00000000 c011fafb c0433660 c011f9a1 00000000 00000001 c04095e0
Call Trace:    [<c03031c0>] [<c0304442>] [<c03043c0>] [<c0123b47>] [<c011fafb>]
  [<c011f9a1>] [<c011f72b>] [<c010a8ad>] [<c0106e60>] [<c0106e60>] [<c0106e60>]
  [<c0106e60>] [<c0106e8c>] [<c0106f12>] [<c011af6b>]
Code: 8b 40 2c 83 f8 09 0f 4c c8 b8 01 00 00 00 d3 e0 39 c2 7d 16


>>EIP; c0303206 <xprt_timer+46/e0>   <=====

>>esi; f7611078 <_end+371a0bfc/384b3b84>
>>edi; e7bc2480 <_end+27752004/384b3b84>
>>ebp; f7611000 <_end+371a0b84/384b3b84>
>>esp; c2837edc <_end+23c7a60/384b3b84>

Trace; c03031c0 <xprt_timer+0/e0>
Trace; c0304442 <rpc_run_timer+82/90>
Trace; c03043c0 <rpc_run_timer+0/90>
Trace; c0123b47 <timer_bh+2b7/3f0>
Trace; c011fafb <bh_action+4b/80>
Trace; c011f9a1 <tasklet_hi_action+61/a0>
Trace; c011f72b <do_softirq+7b/e0>
Trace; c010a8ad <do_IRQ+dd/f0>
Trace; c0106e60 <default_idle+0/40>
Trace; c0106e60 <default_idle+0/40>
Trace; c0106e60 <default_idle+0/40>
Trace; c0106e60 <default_idle+0/40>
Trace; c0106e8c <default_idle+2c/40>
Trace; c0106f12 <cpu_idle+52/70>
Trace; c011af6b <call_console_drivers+eb/100>

Code;  c0303206 <xprt_timer+46/e0>
00000000 <_EIP>:
Code;  c0303206 <xprt_timer+46/e0>   <=====
   0:   8b 40 2c                  mov    0x2c(%eax),%eax   <=====
Code;  c0303209 <xprt_timer+49/e0>
   3:   83 f8 09                  cmp    $0x9,%eax
Code;  c030320c <xprt_timer+4c/e0>
   6:   0f 4c c8                  cmovl  %eax,%ecx
Code;  c030320f <xprt_timer+4f/e0>
   9:   b8 01 00 00 00            mov    $0x1,%eax
Code;  c0303214 <xprt_timer+54/e0>
   e:   d3 e0                     shl    %cl,%eax
Code;  c0303216 <xprt_timer+56/e0>
  10:   39 c2                     cmp    %eax,%edx
Code;  c0303218 <xprt_timer+58/e0>
  12:   7d 16                     jge    2a <_EIP+0x2a> c0303230 <xprt_timer+70/e0>
==============================================================================================
 <0>Kernel panic: Aiee, killing interrupt handler!ksymoops 2.4.8 on i686 2.4.20.  Options used
     -V (default)
     -k /proc/ksyms (default)
     -l /proc/modules (default)
     -o /lib/modules/2.4.20/ (default)
     -m /boot/System.map (specified)

Unable to handle kernel NULL pointer dereference at virtual address 00000058
c0303206
*pde = 00000000
Oops: 0000
CPU:    0
EIP:    0010:[<c0303206>]    Not tainted
Using defaults from ksymoops -t elf32-i386 -a i386
EFLAGS: 00010202
eax: 0000002c   ebx: 00000000   ecx: 00000008   edx: 00000001
esi: f75d82b8   edi: f423ee40   ebp: f75d8000   esp: f53f3f24
ds: 0018   es: 0018   ss: 0018
Process blastall (pid: 2246, stackpage=f53f3000)
Stack: f423ee40 c03031c0 00000000 00000000 c0304442 f423ee40 f423ee94 c03043c0
       c0123b47 f423ee40 f53f3f54 00000086 c35a7a98 d901a0e4 00000000 00000001
       00000000 00000000 c011fafb c0433660 c011f9a1 00000000 00000001 c04095e0
Call Trace:    [<c03031c0>] [<c0304442>] [<c03043c0>] [<c0123b47>] [<c011fafb>] [<c011f9a1>] [<c011f72b>] [<c010a8ad>]
Code: 8b 40 2c 83 f8 09 0f 4c c8 b8 01 00 00 00 d3 e0 39 c2 7d 16


>>EIP; c0303206 <xprt_timer+46/e0>   <=====

>>esi; f75d82b8 <_end+37167e3c/384b3b84>
>>edi; f423ee40 <_end+33dce9c4/384b3b84>
>>ebp; f75d8000 <_end+37167b84/384b3b84>
>>esp; f53f3f24 <_end+34f83aa8/384b3b84>

Trace; c03031c0 <xprt_timer+0/e0>
Trace; c0304442 <rpc_run_timer+82/90>
Trace; c03043c0 <rpc_run_timer+0/90>
Trace; c0123b47 <timer_bh+2b7/3f0>
Trace; c011fafb <bh_action+4b/80>
Trace; c011f9a1 <tasklet_hi_action+61/a0>
Trace; c011f72b <do_softirq+7b/e0>
Trace; c010a8ad <do_IRQ+dd/f0>

Code;  c0303206 <xprt_timer+46/e0>
00000000 <_EIP>:
Code;  c0303206 <xprt_timer+46/e0>   <=====
   0:   8b 40 2c                  mov    0x2c(%eax),%eax   <=====
Code;  c0303209 <xprt_timer+49/e0>
   3:   83 f8 09                  cmp    $0x9,%eax
Code;  c030320c <xprt_timer+4c/e0>
   6:   0f 4c c8                  cmovl  %eax,%ecx
Code;  c030320f <xprt_timer+4f/e0>
   9:   b8 01 00 00 00            mov    $0x1,%eax
Code;  c0303214 <xprt_timer+54/e0>
   e:   d3 e0                     shl    %cl,%eax
Code;  c0303216 <xprt_timer+56/e0>
  10:   39 c2                     cmp    %eax,%edx
Code;  c0303218 <xprt_timer+58/e0>
  12:   7d 16                     jge    2a <_EIP+0x2a> c0303230 <xprt_timer+70/e0>

 <0>Kernel panic: Aiee, killing interrupt handler!