linux-toradex.git/drivers, branch v2.6.27.27

tulip: Fix for MTU problems with 802.1q tagged frames

2009-07-20T03:45:00+00:00

commit 1f8ae0a21d83f43006d7f6d2862e921dbf2eeddd upstream.

The original patch was submitted last year but wasn't discussed or applied
because of missing maintainer's CCs. I only fixed some formatting errors,
but as I saw tulip is very badly formatted and needs further work.

Original description:
This patch fixes MTU problem, which occurs when using 802.1q VLANs. We
should allow receiving frames of up to 1518 bytes in length, instead of
1514.

Based on patch written by Ben McKeegan for 2.4.x kernels. It is archived
at http://www.candelatech.com/~greear/vlan/howto.html#tulip
I've adjusted a few things to make it apply on 2.6.x kernels.

Tested on D-Link DFE-570TX quad-fastethernet card.

Signed-off-by: Tomasz Lemiech 
Signed-off-by: Ivan Vecera 
Signed-off-by: Ben McKeegan 
Acked-by: Grant Grundler 
Cc: Christoph Biedl 
Signed-off-by: David S. Miller

floppy: fix lock imbalance

2009-07-20T03:45:00+00:00

commit 8516a500029890a72622d245f8ed32c4e30969b7 upstream.

A crappy macro prevents us unlocking on a fail path.

Expand the macro and unlock appropriatelly.

Signed-off-by: Jiri Slaby 
Cc: Jens Axboe 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

Fix iommu address space allocation

2009-07-20T03:44:59+00:00

commit a15a519ed6e5e644f5a33c213c00b0c1d3cfe683 upstream.

This fixes kernel.org bug #13584. The IOVA code attempted to optimise
the insertion of new ranges into the rbtree, with the unfortunate result
that some ranges just didn't get inserted into the tree at all. Then
those ranges would be handed out more than once, and things kind of go
downhill from there.

Introduced after 2.6.25 by ddf02886cbe665d67ca750750196ea5bf524b10b
("PCI: iova RB tree setup tweak").

Signed-off-by: David Woodhouse 
Cc: mark gross 
Cc: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

Revert "dm: sysfs skip output when device is being destroyed"

2009-07-20T03:43:27+00:00

This reverts commit 9fad9f263a7065be94bf77519346d0d854ff3b92.

It is really commit 4d89b7b4e4726893453d0fb4ddbb5b3e16353994 that is
being reverted here, it's a patch that should not have been applied to
the .27 tree.

Signed-off-by: Greg Kroah-Hartman

dm: sysfs skip output when device is being destroyed

2009-07-02T23:32:10+00:00

commit 4d89b7b4e4726893453d0fb4ddbb5b3e16353994 upstream.

Do not process sysfs attributes when device is being destroyed.

Otherwise code can cause
  BUG_ON(test_bit(DMF_FREEING, &md->flags));
in dm_put() call.

Signed-off-by: Milan Broz 
Signed-off-by: Alasdair G Kergon 
Signed-off-by: Greg Kroah-Hartman

dm mpath: validate table argument count

2009-07-02T23:32:08+00:00

commit 0e0497c0c017664994819f4602dc07fd95896c52 upstream.

The parser reads the argument count as a number but doesn't check that
sufficient arguments are supplied. This command triggers the bug:

dmsetup create mpath --table "0 `blockdev --getsize /dev/mapper/cr0`
    multipath 0 0 2 1 round-robin 1000 0 1 1 /dev/mapper/cr0
    round-robin 0 1 1 /dev/mapper/cr1 1000"
kernel BUG at drivers/md/dm-mpath.c:530!

Signed-off-by: Mikulas Patocka 
Signed-off-by: Alasdair G Kergon 
Signed-off-by: Greg Kroah-Hartman

dm mpath: validate hw_handler argument count

2009-07-02T23:32:07+00:00

commit e094f4f15f5169526c7200b9bde44b900548a81e upstream.

Fix arg count parsing error in hw handlers.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Alasdair G Kergon 
Signed-off-by: Greg Kroah-Hartman

pcmcia/cm4000: fix lock imbalance

2009-07-02T23:32:02+00:00

commit 69ae59d7d8df14413cf0a97b3e372d7dc8352563 upstream.

Don't return from switch/case, break instead, so that we unlock BKL.

Signed-off-by: Jiri Slaby 
Signed-off-by: Alan Cox 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

PCI PM: Follow PCI_PM_CTRL_NO_SOFT_RESET during transitions from D3

2009-07-02T23:32:00+00:00

commit f62795f1e892ca9269849fa83de97621da7e02c0 upstream.

According to the PCI PM specification (PCI Bus Power Management
Interface Specification, Rev. 1.2, Section 5.4.1) we are supposed to
reinitialize devices that have PCI_PM_CTRL_NO_SOFT_RESET clear during
all transitions from PCI_D3hot to PCI_D0, but we only do it if the
device's current_state field is equal to PCI_UNKNOWN.

This may lead to problems if a device with PCI_PM_CTRL_NO_SOFT_RESET
unset is put into PCI_D3hot at run time by its driver and
pci_set_power_state() is used to put it back into PCI_D0, because in
that case the device will remain uninitialized after
pci_set_power_state() has returned.  Prevent that from happening by
modifying pci_raw_set_power_state() to reinitialize devices with
PCI_PM_CTRL_NO_SOFT_RESET unset during all transitions from D3 to D0.

Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Jesse Barnes 
Signed-off-by: Greg Kroah-Hartman

PCI PM: Fix handling of devices without PM support by pci_target_state()

2009-07-02T23:31:59+00:00

commit d2abdf62882d982c58e7a6b09ecdcfcc28075e2e upstream.

If a PCI device is not power-manageable either by the platform, or
with the help of the native PCI PM interface, pci_target_state() will
return either PCI_D3hot, or PCI_POWER_ERROR for it, depending on
whether or not the device is configured to wake up the system.  Alas,
none of these return values is correct, because each of them causes
pci_prepare_to_sleep() to return error code, although it should
complete successfully in such a case.

Fix this problem by making pci_target_state() always return PCI_D0
for devices that cannot be power managed.

Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Jesse Barnes 
Signed-off-by: Greg Kroah-Hartman