Linux Archive - Bug#648766: kernel crash

Package: linux-image-3.0.0-2-sparc64-smp
Version: 3.0.0-6

Hello,

On my Sunfire 280r there is a sil3112 chip based SATA1 dual port
controller and there are two 1GB HDD on it in stripe and I use XFS on
that stripe.

I use the unstable linux-image kernel because kernel in testing lastly
tried kernel crashed at boot
(http://old.nabble.com/Kernel-3.0-fails-to-boot-on-V240-td32376229.html)

On big workload the kernel (seems) randomly crashing:

[20101.827174] BUG: NMI Watchdog detected LOCKUP on CPU0, ip 0043922c,
registers:
[20101.912687] TSTATE: 0000004480e01607 TPC: 000000000043922c TNPC:
0000000000439230 Y: 00000000 Not tainted

[20102.030413] TPC: <cheetah_xcall_deliver+0x1a8/0x240>
[20102.089769] g0: 0000000000000000 g1: 0000000000000040 g2:
0000000000000001 g3: 000000000001869d
[20102.193937] g4: fffff800fe09b2c0 g5: fffff800022ac000 g6:
fffff800fe0b8000 g7: 0000000000000000
[20102.298106] o0: 0000000000000001 o1: 0000000000000000 o2:
0000000000000000 o3: 0000000000000000
[20102.402274] o4: 0000000000000000 o5: 0000000000000003 sp:
fffff800fe0ba6b1 ret_pc: 000000000043924c

[20102.510610] RPC: <cheetah_xcall_deliver+0x1c8/0x240>
[20102.569985] l0: 000000000000ffff l1: 0000000000000016 l2:
fffff800fe042000 l3: fffff800fe042040
[20102.674152] l4: ffffffffffffffff l5: 0000000000000002 l6:
0000000000000001 l7: 0000000000000000
[20102.778320] i0: 0000000000000050 i1: 0000000000000001 i2:
0000000000000002 i3: 0000000000000060
[20102.882488] i4: 00000000000186a0 i5: 000000000000ffff i6:
fffff800fe0ba771 i7: 0000000000438f34

[20102.986656] I7: <xcall_deliver+0xe8/0x110>
[20103.035612] Call Trace:
[20103.064784] [0000000000438f34] xcall_deliver+0xe8/0x110
[20103.128327] [0000000000439ccc] smp_flush_tlb_pending+0x88/0xa0
[20103.199165] [00000000004490b0] flush_tlb_pending+0x50/0x64
[20103.265829] [0000000000502134] ptep_clear_flush+0x38/0x48
[20103.331459] [00000000004fd6e4] try_to_unmap_one+0xa0/0x420
[20103.398120] [00000000004fe25c] try_to_unmap_anon+0xc4/0x118
[20103.465829] [00000000004fe368] try_to_unmap+0x60/0x9c
[20103.527289] [0000000000510c10] migrate_pages+0x200/0x3d4
[20103.591878] [000000000050b078] compact_zone+0x6c0/0x708
[20103.655415] [000000000050b1f0] compact_zone_order+0x94/0xa8
[20103.723125] [000000000050b26c] try_to_compact_pages+0x68/0xcc
[20103.792926] [00000000004de448] __alloc_pages_direct_compact+0x70/0x12c
[20103.872086] [00000000004de970] __alloc_pages_nodemask+0x46c/0x760
[20103.946044] [0000000000463f84] copy_process+0xac/0xd50
[20104.008545] [0000000000464d40] do_fork+0xec/0x294
[20104.065842] [000000000042b66c] sparc_do_fork+0x30/0x4c
[20104.128333] Call Trace:
[20104.157509] [00000000004209f4] tl0_irq15+0x14/0x20
[20104.215840] [000000000043922c] cheetah_xcall_deliver+0x1a8/0x240
[20104.288757] [0000000000438f34] xcall_deliver+0xe8/0x110
[20104.352298] [0000000000439ccc] smp_flush_tlb_pending+0x88/0xa0
[20104.423134] [00000000004490b0] flush_tlb_pending+0x50/0x64
[20104.489800] [0000000000502134] ptep_clear_flush+0x38/0x48
[20104.555428] [00000000004fd6e4] try_to_unmap_one+0xa0/0x420
[20104.622095] [00000000004fe25c] try_to_unmap_anon+0xc4/0x118
[20104.689802] [00000000004fe368] try_to_unmap+0x60/0x9c
[20104.751260] [0000000000510c10] migrate_pages+0x200/0x3d4
[20104.815845] [000000000050b078] compact_zone+0x6c0/0x708
[20104.879389] [000000000050b1f0] compact_zone_order+0x94/0xa8
[20104.947098] [000000000050b26c] try_to_compact_pages+0x68/0xcc
[20105.016892] [00000000004de448] __alloc_pages_direct_compact+0x70/0x12c
[20105.096059] [00000000004de970] __alloc_pages_nodemask+0x46c/0x760
[20105.170017] [0000000000463f84] copy_process+0xac/0xd50

What could I do?

Cheers,
Tibor

--
To UNSUBSCRIBE, email to debian-kernel-REQUEST@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
Archive: 4EC18DF7.60408@gmail.com">http://lists.debian.org/4EC18DF7.60408@gmail.com