David Howells [Thu, 10 May 2007 10:15:23 +0000 (03:15 -0700)]
AFS: further write support fixes
Further fixes for AFS write support:
(1) The afs_send_pages() outer loop must do an extra iteration if it ends
with 'first == last' because 'last' is inclusive in the page set
otherwise it fails to send the last page and complete the RxRPC op under
some circumstances.
(2) Similarly, the outer loop in afs_pages_written_back() must also do an
extra iteration if it ends with 'first == last', otherwise it fails to
clear PG_writeback on the last page under some circumstances.
Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
slub: support concurrent local and remote frees and allocs on a slab
Avoid atomic overhead in slab_alloc and slab_free
SLUB needs to use the slab_lock for the per cpu slabs to synchronize with
potential kfree operations. This patch avoids that need by moving all free
objects onto a lockless_freelist. The regular freelist continues to exist
and will be used to free objects. So while we consume the
lockless_freelist the regular freelist may build up objects.
If we are out of objects on the lockless_freelist then we may check the
regular freelist. If it has objects then we move those over to the
lockless_freelist and do this again. There is a significant savings in
terms of atomic operations that have to be performed.
We can even free directly to the lockless_freelist if we know that we are
running on the same processor. So this speeds up short lived objects.
They may be allocated and freed without taking the slab_lock. This is
particular good for netperf.
In order to maximize the effect of the new faster hotpath we extract the
hottest performance pieces into inlined functions. These are then inlined
into kmem_cache_alloc and kmem_cache_free. So hotpath allocation and
freeing no longer requires a subroutine call within SLUB.
[I am not sure that it is worth doing this because it changes the easy to
read structure of slub just to reduce atomic ops. However, there is
someone out there with a benchmark on 4 way and 8 way processor systems
that seems to show a 5% regression vs. Slab. Seems that the regression is
due to increased atomic operations use vs. SLAB in SLUB). I wonder if
this is applicable or discernable at all in a real workload?]
Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Olaf Hering [Sat, 5 May 2007 21:17:13 +0000 (23:17 +0200)]
firewire: Provide module aliase for backwards compatibility.
This patch loads fw-sbp2 if sbp2 is still in the config file. So one can
go back and forth between releases without worry about the root
filesystem drivers.
Signed-off-by: Kristian Hoegsberg <krh@redhat.com>
Existing mkinitrd scripts still have to be adapted, unless they grok
module aliases.
Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Ivo van Doorn [Mon, 12 Jun 2006 14:17:04 +0000 (16:17 +0200)]
CRC ITU-T V.41
This will add the CRC calculation according
to the CRC ITU-T V.41 to the kernel lib/ folder.
This code has been derived from the rt2x00 driver,
currently found only in the wireless-dev tree, but
this library is generic and could be used by more
drivers who currently use their own implementation.
Signed-off-by: Ivo van Doorn <IvDoorn@gmail.com>
Also useful for the new firewire stack.
Signed-off-by: Kristian Hoegsberg <krh@redhat.com> Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
[S390] Kconfig: use common Kconfig files for s390.
Disband drivers/s390/Kconfig, use the common Kconfig files. The s390
specific config options from drivers/s390/Kconfig are moved to the
respective common Kconfig files.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cornelia Huck [Thu, 10 May 2007 13:45:42 +0000 (15:45 +0200)]
[S390] cio: Get rid of _ccw_device_get_device_number().
The function shouldn't have existed in the first place (not MSS-aware).
Introduce a new function ccw_device_get_id() that extracts the
ccw_dev_id structure of a ccw device and convert all users of
_ccw_device_get_device_number to ccw_device_get_id.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Paul Mackerras [Thu, 10 May 2007 12:17:18 +0000 (22:17 +1000)]
[POWERPC] Fix compile error with kexec and CONFIG_SMP=n
Commit 2f4dfe206a2fc07099dfad77a8ea2f4b4ae2140f moved the definition
of hard_smp_processor_id() for the UP case from include/linux/smp.h
to include/asm/smp.h. However, include/linux/smp.h only includes
include/asm/smp.h in the SMP case, so code that wants to use
hard_smp_processor_id() has to include <asm/smp.h> explicitly to
be sure of getting the definition.
Paul Mackerras [Wed, 9 May 2007 11:47:15 +0000 (21:47 +1000)]
[POWERPC] Fix incorrect calculation of I/O window addresses
My patch "Cope with PCI host bridge I/O window not starting at 0"
introduced a bug in the calculation of the virtual addresses for the
I/O windows of PCI host bridges other than the first, because it
didn't account for the fact that hose->io_resource gets offset so that
it reflects the range of global I/O port numbers assigned to the
bridge. This fixes it and simplifies get_bus_io_range() in the
process.
Ishizaki Kou [Wed, 9 May 2007 07:34:08 +0000 (17:34 +1000)]
[POWERPC] celleb: Fix support for multiple PCI domains
Celleb has multiple PCI host bridges (phbs). Previous boot logic gives
non-overlapped bus IDs between PCI host bridges so you can identify
PHB by bus ID. But newer boot logic gives same bus ID between PHBs (it
gives bus ID 0 as root bus.) So we have to set 'phb->buid' as
non-zero.
Signed-off-by: Kou Ishizaki <kou.ishizaki@toshiba.co.jp> Signed-off-by: Paul Mackerras <paulus@samba.org>
acpi,msi-laptop: Fall back to EC polling mode for MSI laptop specific EC commands
The ACPI EC that is used in MSI laptops knows some non-standard
commands for changing the screen brighntess and a few other things,
which are used by the msi-laptop.c driver. Unfortunately for these
commands no GPE events for IBF and OBF are triggered. Since nowadays
the EC code uses the ec_intr=1 mode by default, this causes these
operations to timeout, although they don't fail. In result, all
operations that you can do with the msi-laptop.c driver take more or
less 1s to complete, which is awfully slow.
In one of the more recent kernels (2.6.20?) the EC subsystem has been
revamped. With that change the EC timeout has been increased. before
that increase the MSI EC accesses were slow -- but not *that* slow,
hence I took notice of this limitation of the MSI EC hardware only very
recently.
The standard EC operations on the MSI EC as defined in the ACPI spec
support GPE events properly.
The following patch adds a new argument "force_poll" to the
ec_transaction() function (and friends). If set to 1, the function
will poll for IBF/OBF even if ec_intr=1 is enabled. If set to 0 the
current behaviour is used. The msi-laptop driver is modified to make
use of this new flag, so that OBF/IBF is polled for the special MSI EC
transactions -- but only for them.
Signed-off-by: Lennart Poettering <mzxreary@0pointer.de> Acked-by: Alexey Starikovskiy <aystarik@gmail.com> Signed-off-by: Len Brown <len.brown@intel.com>
Kumar Gala [Thu, 10 May 2007 04:44:58 +0000 (23:44 -0500)]
[POWERPC] CPM_UART: Removed __init from cpm_uart_init_portdesc to fix warning
cpm_uart_init_portdesc is referenced from non-init code and thus we were
getting the following warning:
WARNING: drivers/built-in.o - Section mismatch: reference to .init.text:cpm_uart_init_portdesc from .text between 'cpm_uart_init' (at offset 0x18020) and 'cpm_uart_drv_remove'
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Timur Tabi [Tue, 8 May 2007 19:46:36 +0000 (14:46 -0500)]
[POWERPC] Change rheap functions to use ulongs instead of pointers
The rheap allocation functions return a pointer, but the actual value is based
on how the heap was initialized, and so it can be anything, e.g. an offset
into a buffer. A ulong is a better representation of the value returned by
the allocation functions.
This patch changes all of the relevant rheap functions to use a unsigned long
integers instead of a pointer. In case of an error, the value returned is
a negative error code that has been cast to an unsigned long. The caller can
use the IS_ERR_VALUE() macro to check for this.
All code which calls the rheap functions is updated accordingly. Macros
IS_MURAM_ERR() and IS_DPERR(), have been deleted in favor of IS_ERR_VALUE().
Also added error checking to rh_attach_region().
Signed-off-by: Timur Tabi <timur@freescale.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Jason Jin [Wed, 2 May 2007 21:53:38 +0000 (16:53 -0500)]
[POWERPC] 86xx: Enable the AC97 interface on 8641D board.
HD interface and AC97 interface share some pins and they are enabled at
the same time, In order to use AC97 interface, we need to disable the HD
interface first.
Signed-off-by:Jason Jin<jason.jin@freescale.com> Acked-by: Jon Loeliger <jdl@freescale.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
ACPI: created a dedicated workqueue for notify() execution
HP nx6125/nx6325/... machines have a _GPE handler with an infinite
loop sending Notify() events to different ACPI subsystems.
Notify handler in ACPI driver is a C-routine, which may call ACPI
interpreter again to get access to some ACPI variables
(acpi_evaluate_xxx).
On these HP machines such an evaluation changes state of some variable
and lets the loop above break.
In the current ACPI implementation Notify requests are being deferred
to the same kacpid workqueue on which the above GPE handler with
infinite loop is executing. Thus we have a deadlock -- loop will
continue to spin, sending notify events, and at the same time
preventing these notify events from being run on a workqueue. All
notify events are deferred, thus we see increase in memory consumption
noticed by author of the thread. Also as GPE handling is bloked,
machines overheat. Eventually by external poll of the same
acpi_evaluate, kacpid is released and all the queued notify events are
free to run, thus 100% cpu utilization by kacpid for several seconds
or more.
To prevent all these horrors it's needed to not put notify events to
kacpid workqueue by either executing them immediately or putting them
on some other thread. It's dangerous to execute notify events in
place, as it will put several ACPI interpreter stacks on top of each
other (at least 4 in case of nx6125), thus causing kernel stack
overflow.
First attempt to create a new thread was done by Peter Wainwright
He created a bunch of threads, which were stealing work from a kacpid
workqueue.
This patch appeared in 2.6.15 kernel shipped with Ubuntu 6.06 LTS.
Second attempt was done by me, I created a new thread for each Notify
event. This worked OK on HP nx machines, but broke Linus' Compaq
n620c, by producing threads with a speed what they stopped the machine
completely. Thus this patch was reverted from 18-rc2 as I remember.
I re-made the patch to create second workqueue just for notify events,
thus hopping it will not break Linus' machine. Patch was tested on the
same HP nx machines in #5534 and #7122, but I did not received reply
from Linus on a test patch sent to him.
Patch went to 19-rc and was rejected with much fanfare again.
There was 4th patch, which inserted schedule_timeout(1) into deferred
execution of kacpid, if we had any notify requests pending, but Linus
decided that it was too complex (involved either changes to workqueue
to see if it's empty or atomic inc/dec).
Now you see last variant which adds yield() to every GPE execution.
These changes to AML locking were made to allow
Notify handlers to be called on the stack
and not deadlock. However, that scheme turns
out to be flawed and was reverted by the previous commit,
so this commit restores the locking to it previous design.
This commit by itself may cause a regression, but
it is reverted in this order so that subsequent
reverts reverts under this one can be made
without conflict.
Linus Torvalds [Thu, 10 May 2007 02:40:09 +0000 (19:40 -0700)]
Merge branch 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband
* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband:
IB/mlx4: Add a driver Mellanox ConnectX InfiniBand adapters
IB: Put rlimit accounting struct in struct ib_umem
IB/uverbs: Export ib_umem_get()/ib_umem_release() to modules
"It causes an oops when auto-detecting raid arrays, and it doesn't
seem easy to fix.
The array may not be 'open' when do_md_run is called, so
bdev->bd_disk might be NULL, so bd_set_size can oops.
This whole approach of opening an md device before it has been
assembled just seems to get more and more painful. I think I'm going
to have to come up with something clever to provide both backward
comparability with usage expectation, and sane integration into the
rest of the kernel."
Jeff Garzik [Thu, 10 May 2007 01:31:55 +0000 (21:31 -0400)]
Move USB network drivers to drivers/net/usb.
It is preferable to group drivers by usage (net, scsi, ATA, ...) than
by bus. When reviewing drivers, the [PCI|USB|PCMCIA|...] maintainer
is probably less qualified on networking issues than a networking
maintainer. Also, from a practical standpoint, chips often
appear on multiple buses, which is why we do not put drivers into
drivers/pci/net.
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Jeff Garzik <jeff@garzik.org>
Jesse Barnes [Tue, 1 May 2007 21:34:39 +0000 (14:34 -0700)]
Doc Fix: remove mention of combined mode-related kernel parameters
Looks like you removed the combined_mode quirk (yay!) but didn't update
kernel-parameters.txt... might confuse people. Here's a patch to remove
mention of it from the documentation.
Signed-off-by: Jesse Barnes <jesse.barnes@intel.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
Randy Dunlap [Wed, 2 May 2007 00:35:55 +0000 (17:35 -0700)]
libata: fix kernel-doc parameters
Warning(linux-2.6.21-git4//drivers/ata/libata-core.c:904): No description found for parameter 'new_sectors'
Warning(linux-2.6.21-git4//drivers/ata/libata-core.c:941): No description found for parameter 'new_sectors'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
Robert Hancock [Sat, 5 May 2007 21:36:36 +0000 (15:36 -0600)]
sata_nv: fix ADMA freeze/thaw/irq_clear issues
This patch fixes some problems with ADMA-capable controllers with
regard to freeze, thaw and irq_clear libata callbacks. Freeze and
thaw didn't switch the ADMA-specific interrupts on or off, and more
critically the irq_clear function didn't respect the restriction that
the notifier clear registers for both ports have to be written at
the same time even when only one port is being cleared. This could
result in timeouts on one port when error handling (i.e. as a result
of hotplug) occurred on the other port.
As well, this fixes some issues in the interrupt handler: we shouldn't
check any ADMA status if the port has ADMA switched off because of
an ATAPI device, and it also checks to see if any ADMA interrupt has
been raised even when we are in port-register mode.
Signed-off-by: Robert Hancock <hancockr@shaw.ca> Signed-off-by: Jeff Garzik <jeff@garzik.org>
sata_promise: SATAII-150/300 TX4 port numbering fix
There is a known problem with sata_promise on SATAII-150/300 TX4
controller cards: it enumerates drives in an order that differs
from the port numbers printed on the controller cards. However,
Promise's BIOS and Linux driver both get the order right.
I investigated Promise's Linux driver (v1.01.0.23), and found
that it explicitly changes the mapping from logical port number
to ATA engine MMIO address on the SATAII TX4 cards. It does this
on all SATAII TX4 cards, without inspecting revision etc. The
SATAII TX2plus cards continue to use the same mapping that was
used for the first-generation chips.
This patch updates sata_promise to use the new port number to
ATA engine mapping on SATAII TX4 cards, which fixes the drive
enumeration order problem on those cards. Tested on several
1st and 2nd generation TX2plus and TX4 chips.
Signed-off-by: Mikael Pettersson <mikpe@it.uu.se> Signed-off-by: Jeff Garzik <jeff@garzik.org>
The sata_promise error decode update changed pdc_host_intr()
to return and not complete the qc after detecting an error.
Unfortunately not completing the qc:s causes them to always
time out on error, which is wrong and has nasty side-effects.
This patch updates pdc_error_intr() to call ata_port_abort(),
similar to ahci and sata_sil24. Doing this is important as it
makes EH see the original error and not a bogus timeout.
Signed-off-by: Mikael Pettersson <mikpe@it.uu.se> Signed-off-by: Jeff Garzik <jeff@garzik.org>
Paul Walmsley [Wed, 9 May 2007 16:47:16 +0000 (10:47 -0600)]
Fix hang on IBM Token Ring PCMCIA card ejection
Ejecting a PCMCIA IBM Token Ring card that has not had its dev->open()
called will reliably trigger an uninitialized spinlock oops when
spinlock debugging is enabled. The system then hangs, occasionally
softlockup oopsing. Apparently ibmtr.c:tok_interrupt() doesn't expect
to be called before tok_open(), but tok_interrupt() gets called anyway
when the card is ejected. So, set an already-existing flag which
causes tok_interrupt() to bail out early upon card ejection. Tested by
inserting and removing the PCMCIA card several times.
Signed-off-by: Paul Walmsley <paul@booyaka.com> Signed-off-by: Jeff Garzik <jeff@garzik.org>
By default, the skge driver now enables wake on magic and wake on PHY.
This is a bad default (bug), wake on PHY means machine will never shutdown
if connected to a switch.
Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>a Signed-off-by: Jeff Garzik <jeff@garzik.org>