From: Boris Derzhavets <bderzhavets@xxxxxxxxx>
Subject: Re: [fedora-virt] Re: [Fedora-xen] Dom0 kernels
To: fedora-xen@xxxxxxxxxx, fedora-virt@xxxxxxxxxx, "M A Young" <m.a.young@xxxxxxxxxxxx>
Cc: xen-devel@xxxxxxxxxxxxx
Date: Wednesday, August 26, 2009, 2:50 AM

With rpm upgraded can load Dom0. However, dmesg report contains :-

Initializing cgroup subsys cpuset
Initializing cgroup subsys cpu
Linux version 2.6.31-0.1.2.58.rc7.git1.xendom0.fc11.x86_64 (root@ServerXenSRC) (gcc version 4.4.0 20090506 (Red Hat 4.4.0-4) (GCC) ) #1 SMP Wed Aug 26 08:14:58 MSD 2009
Command line: root=/dev/mapper/vg_serverxensrc-LogVol00 ro console=tty0
KERNEL supported cpus:
Intel GenuineIntel
AMD AuthenticAMD
Centaur CentaurHauls
BIOS-provided physical RAM map:
Xen: 0000000000000000 - 000000000009ec00 (usable)
Xen: 000000000009ec00 - 0000000000100000 (reserved)
Xen: 0000000000100000 - 00000000cff80000 (usable)
Xen: 00000000cff80000 - 00000000cff8e000 (ACPI data)
Xen: 00000000cff8e000 - 00000000cffe0000 (ACPI NVS)
Xen: 00000000cffe0000 - 00000000d0000000 (reserved)
Xen: 00000000fee00000 - 00000000fee01000 (reserved)
Xen: 00000000ffe00000 - 0000000100000000 (reserved)
Xen: 0000000100000000 - 00000001f1a6b000 (usable)
DMI 2.4 present.
AMI BIOS detected: BIOS may corrupt low RAM, working around it.
e820 update range: 0000000000000000 - 0000000000010000 (usable) ==> (reserved)
last_pfn = 0x1f1a6b max_arch_pfn = 0x400000000
last_pfn = 0xcff80 max_arch_pfn = 0x400000000
initial memory mapped : 0 - 20000000
init_memory_mapping: 0000000000000000-00000000cff80000
0000000000 - 00cff80000 page 4k
kernel direct mapping tables up to cff80000 @ 100000-785000
init_memory_mapping: 0000000100000000-00000001f1a6b000
0100000000 - 01f1a6b000 page 4k

. . . . . . .

======================================================
[ INFO: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected ]
2.6.31-0.1.2.58.rc7.git1.xendom0.fc11.x86_64 #1
------------------------------------------------------
khubd/28 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
(&retval->lock){......}, at: [<ffffffff8112a240>] dma_pool_alloc+0x45/0x321

and this task is already holding:
(&ehci->lock){-.....}, at: [<ffffffff813d4654>] ehci_urb_enqueue+0xb4/0xd5c
which would create a new lock dependency:
(&ehci->lock){-.....} -> (&retval->lock){......}

but this new dependency connects a HARDIRQ-irq-safe lock:
(&ehci->lock){-.....}
... which became HARDIRQ-irq-safe at:
[<ffffffff8109908b>] __lock_acquire+0x254/0xc0e
[<ffffffff81099b33>] lock_acquire+0xee/0x12e
[<ffffffff8150b987>] _spin_lock+0x45/0x8e
[<ffffffff813d325c>] ehci_irq+0x41/0x441
[<ffffffff813b7e5f>] usb_hcd_irq+0x59/0xcc
[<ffffffff810ca810>] handle_IRQ_event+0x62/0x148
[<ffffffff810ccda3>] handle_level_irq+0x90/0xf9
[<ffffffff81017078>] handle_irq+0x9a/0xba
[<ffffffff8130a0c6>] xen_evtchn_do_upcall+0x10c/0x1bd
[<ffffffff8101527e>] xen_do_hypervisor_callback+0x1e/0x30
[<ffffffffffffffff>] 0xffffffffffffffff

to a HARDIRQ-irq-unsafe lock:
(purge_lock){+.+...}
... which became HARDIRQ-irq-unsafe at:
... [<ffffffff810990ff>] __lock_acquire+0x2c8/0xc0e
[<ffffffff81099b33>] lock_acquire+0xee/0x12e
[<ffffffff8150b987>] _spin_lock+0x45/0x8e
[<ffffffff811233a4>] __purge_vmap_area_lazy+0x63/0x198
[<ffffffff81124c74>] vm_unmap_aliases+0x18f/0x1b2
[<ffffffff8100eeb3>] xen_alloc_ptpage+0x5a/0xa0
[<ffffffff8100ef97>] xen_alloc_pte+0x26/0x3c
[<ffffffff81118381>] __pte_alloc_kernel+0x6f/0xdd
[<ffffffff811241a1>] vmap_page_range_noflush+0x1c5/0x315
[<ffffffff81124332>] map_vm_area+0x41/0x6b
[<ffffffff8112448b>] __vmalloc_area_node+0x12f/0x167
[<ffffffff81124553>] __vmalloc_node+0x90/0xb5
[<ffffffff811243c8>] __vmalloc_area_node+0x6c/0x167
[<ffffffff81124553>] __vmalloc_node+0x90/0xb5
[<ffffffff811247ca>] __vmalloc+0x28/0x3e
[<ffffffff818504c9>] alloc_large_system_hash+0x12f/0x1fb
[<ffffffff81852b4e>] vfs_caches_init+0xb8/0x140
[<ffffffff8182b061>] start_kernel+0x3ef/0x44c
[<ffffffff8182a2d0>] x86_64_start_reservations+0xbb/0xd6
[<ffffffff8182e6d1>] xen_start_kernel+0x5ab/0x5b2
[<ffffffffffffffff>] 0xffffffffffffffff

other info that might help us debug this:

2 locks held by khubd/28:
#0: (usb_address0_mutex){+.+...}, at: [<ffffffff813b2e82>] hub_port_init+0x8c/0x7ee
#1: (&ehci->lock){-.....}, at: [<ffffffff813d4654>] ehci_urb_enqueue+0xb4/0xd5c

the HARDIRQ-irq-safe lock's dependencies:
-> (&ehci->lock){-.....} ops: 0 {
IN-HARDIRQ-W at:
[<ffffffff8109908b>] __lock_acquire+0x254/0xc0e
[<ffffffff81099b33>] lock_acquire+0xee/0x12e
[<ffffffff8150b987>] _spin_lock+0x45/0x8e
[<ffffffff813d325c>] ehci_irq+0x41/0x441
[<ffffffff813b7e5f>] usb_hcd_irq+0x59/0xcc
[<ffffffff810ca810>] handle_IRQ_event+0x62/0x148
[<ffffffff810ccda3>] handle_level_irq+0x90/0xf9

. . . . . .

Jeremy's current version is rc6. I believe this issue has been noticed at xen-devel.
Boris

-----Inline Attachment Follows-----

--
Fedora-xen mailing list
Fedora-xen@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/fedora-xen

Attachment: dmesg.log.gz
Description: GNU Zip compressed data

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel