diff options
author | Eric W. Biederman <ebiederm@xmission.com> | 2007-06-01 09:46:33 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-06-01 17:18:27 +0200 |
commit | 78b7611c4a1e3ff008abc4751b566cb533d68f3d (patch) | |
tree | 569b5ae011f3c6a38406a95d3f8b8f61d358ab16 /drivers | |
parent | msi: fix the ordering of msix irqs (diff) | |
download | linux-78b7611c4a1e3ff008abc4751b566cb533d68f3d.tar.xz linux-78b7611c4a1e3ff008abc4751b566cb533d68f3d.zip |
msi: mask the msix vector before we unmap it
With these two lines in the reverse order the drives/block/ccis.c was
oopsing in msi_free_irqs. Silly us calling writel on an area after
we unmap it.
BUG: unable to handle kernel paging request at virtual address f8b2200c
printing eip:
c01e9cc7
*pdpt = 0000000000003001
*pde = 0000000037e48067
*pte = 0000000000000000
Oops: 0002 [#1]
SMP
Modules linked in: cciss ipv6 parport_pc lp parport autofs4 i2c_dev i2c_core
sunrpc loop dm_multipath button battery asus_acpi ac tg3 floppy sg dm_snapshot
dm_zero dm_mirror ext3 jbd dm_mod ata_piix libata mptsas scsi_transport_sas
mptspi scsi_transport_spi mptscsih mptbase sd_mod scsi_mod
CPU: 1
EIP: 0060:[<c01e9cc7>] Not tainted VLI
EFLAGS: 00010286 (2.6.22-rc2-gd2579053 #1)
EIP is at msi_free_irqs+0x81/0xbe
eax: f8b22000 ebx: f71f3180 ecx: f7fff280 edx: c1886eb8
esi: f7c4e800 edi: f7c4ec48 ebp: 00000002 esp: f5a0dec8
ds: 007b es: 007b fs: 00d8 gs: 0033 ss: 0068
Process rmmod (pid: 5286, ti=f5a0d000 task=c47d2550 task.ti=f5a0d000)
Stack: 00000002 f8b72294 00000400 f8b69ca7 f8b6bc6c 00000002 00000000 00000000
00000000 00000000 00000000 f5a997f4 f8b69d61 f7c5a4b0 f7c4e848 f7c4e848
f7c4e800 f7c4e800 f8b72294 f7c4e848 f8b72294 c01e3cdf f7c4e848 c024c469
Call Trace:
[<f8b69ca7>] cciss_shutdown+0xae/0xc3 [cciss]
[<f8b69d61>] cciss_remove_one+0xa5/0x178 [cciss]
[<c01e3cdf>] pci_device_remove+0x16/0x35
[<c024c469>] __device_release_driver+0x71/0x8e
[<c024c56e>] driver_detach+0xa0/0xde
[<c024bc5c>] bus_remove_driver+0x27/0x41
[<c01e3ef3>] pci_unregister_driver+0xb/0x13
[<f8b6a343>] cciss_cleanup+0xf/0x51 [cciss]
[<c0139ced>] sys_delete_module+0x110/0x135
[<c0104c7a>] sysenter_past_esp+0x5f/0x85
Here's a patch that just reverses the 2 lines of code as Eric suggests. Please
consider this for inclusion.
Signed-off-by: Mike Miller <mike.miller@hp.com>
Signed-off-by: Chase Maupin <chase.maupin@hp.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/pci/msi.c | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 61c46d66c01e..be1df85e5e2d 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -558,12 +558,12 @@ static int msi_free_irqs(struct pci_dev* dev) list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) { if (entry->msi_attrib.type == PCI_CAP_ID_MSIX) { - if (list_is_last(&entry->list, &dev->msi_list)) - iounmap(entry->mask_base); - writel(1, entry->mask_base + entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET); + + if (list_is_last(&entry->list, &dev->msi_list)) + iounmap(entry->mask_base); } list_del(&entry->list); kfree(entry); |