We may need to convert the endianness of the data we read from/write
to 'buf', so let's use {get,put}_unaligned_le32() to do that. Failure
to do so can result in accessing invalid memory, leading to a
segfault. Stephen Rothwell noticed this bug while cross-building an
x86_64 allmodconfig kernel on PowerPC.
We need to read from and write to 'buf' a byte at a time otherwise
it's possible we'll perform an unaligned access, which can lead to bus
errors when cross-building an x86 kernel on risc architectures.
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Nick Bowler <nbowler@elliptictech.com>
Tested-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Link: http://lkml.kernel.org/r/1330436245-24875-6-git-send-email-matt@console-pimps.org
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Currently tools/build has access to all the kernel headers in
$(srctree). This is unnecessary and could potentially allow
tools/build to erroneously include kernel headers when it should only
be including userspace-exported headers.
Unfortunately, mkcpustr still needs access to some of the asm kernel
headers, so explicitly special case that hostprog.
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Link: http://lkml.kernel.org/r/1330436245-24875-5-git-send-email-matt@console-pimps.org
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
There are various hostprogs in the kernel that are rolling their own
implementations of {get,put}_unaligned_le*(). Copy the byteshift
headers from include/linux/unaligned so that they can all use a single
implementation.
This requires changing some of the data types to the userspace
exported ones (u32 -> __u32, etc).
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Link: http://lkml.kernel.org/r/1330436245-24875-2-git-send-email-matt@console-pimps.org
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-fixes:
GFS2: Read resource groups on mount
GFS2: Ensure rindex is uptodate for fallocate
GFS2: Read in rindex if necessary during unlink
GFS2: Fix race between lru_list and glock ref count
IOMMU fixes for Linux 3.3-rc5
All the fixes are for the OMAP IOMMU driver. The first patch is the
biggest one. It fixes the calls of the function omap_find_iovm_area() in
the omap-iommu-debug module which expects a 'struct device' parameter
since commit fabdbca instead of an omap_iommu handle. The
omap-iommu-debug code still passed the handle to the function which
caused a crash.
The second patch fixes a NULL pointer dereference in the OMAP code and
the third patch makes sure that the omap-iommu is initialized before the
omap-isp driver, which relies on the iommu. The last patch is only a
workaround until defered probing is implemented.
* tag 'iommu-fixes-v3.3-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
ARM: OMAP: make iommu subsys_initcall to fix builtin omap3isp
iommu/omap: fix NULL pointer dereference
iommu/omap: fix erroneous omap-iommu-debug API calls
This patch sorts the ordered write list for GFS2 writes.
This increases the throughput for simultaneous writes.
For example, if you have ten processes, all doing:
dd if=/dev/zero of=/mnt/gfs2/fileX
on different files, the throughput will be much better.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
The FITRIM ioctl provides an alternative way to send discard requests to
the underlying device. Using the discard mount option results in every
freed block generating a discard request to the block device. This can
be slow, since many block devices can only process discard requests of
larger sizes, and also such operations can be time consuming.
Rather than using the discard mount option, FITRIM allows a sweep of the
filesystem on an occasional basis, and also to optionally avoid sending
down discard requests for smaller regions.
In GFS2 FITRIM will work at resource group granularity. There is a flag
for each resource group which keeps track of which resource groups have
been trimmed. This flag is reset whenever a deallocation occurs in the
resource group, and set whenever a successful FITRIM of that resource
group has taken place. This helps to reduce repeated discard requests
for the same block ranges, again improving performance.
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
gfs2_log_get_buf() and gfs2_log_fake_buf() are both used
only in lops.c, so move them next to their callers and they
can then become static.
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
The stats are divided into two sets: those relating to the
super block and those relating to an individual glock. The
super block stats are done on a per cpu basis in order to
try and reduce the overhead of gathering them. They are also
further divided by glock type.
In the case of both the super block and glock statistics,
the same information is gathered in each case. The super
block statistics are used to provide default values for
most of the glock statistics, so that newly created glocks
should have, as far as possible, a sensible starting point.
The statistics are divided into three pairs of mean and
variance, plus two counters. The mean/variance pairs are
smoothed exponential estimates and the algorithm used is
one which will be very familiar to those used to calculation
of round trip times in network code.
The three pairs of mean/variance measure the following
things:
1. DLM lock time (non-blocking requests)
2. DLM lock time (blocking requests)
3. Inter-request time (again to the DLM)
A non-blocking request is one which will complete right
away, whatever the state of the DLM lock in question. That
currently means any requests when (a) the current state of
the lock is exclusive (b) the requested state is either null
or unlocked or (c) the "try lock" flag is set. A blocking
request covers all the other lock requests.
There are two counters. The first is there primarily to show
how many lock requests have been made, and thus how much data
has gone into the mean/variance calculations. The other counter
is counting queueing of holders at the top layer of the glock
code. Hopefully that number will be a lot larger than the number
of dlm lock requests issued.
So why gather these statistics? There are several reasons
we'd like to get a better idea of these timings:
1. To be able to better set the glock "min hold time"
2. To spot performance issues more easily
3. To improve the algorithm for selecting resource groups for
allocation (to base it on lock wait time, rather than blindly
using a "try lock")
Due to the smoothing action of the updates, a step change in
some input quantity being sampled will only fully be taken
into account after 8 samples (or 4 for the variance) and this
needs to be carefully considered when interpreting the
results.
Knowing both the time it takes a lock request to complete and
the average time between lock requests for a glock means we
can compute the total percentage of the time for which the
node is able to use a glock vs. time that the rest of the
cluster has its share. That will be very useful when setting
the lock min hold time.
The other point to remember is that all times are in
nanoseconds. Great care has been taken to ensure that we
measure exactly the quantities that we want, as accurately
as possible. There are always inaccuracies in any
measuring system, but I hope this is as accurate as we
can reasonably make it.
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Probe function of s3c2410 watchdog calls request_irq before initializing
required value (wdt_count). This incurs resetting watchdog counter value
and watchdog-reboot during booting up.
This patch addresses such an issue by calling request_irq later.
Error handling in probe function and calling oder in remove function are
also revised accordingly.
Reported-by: Chanwoo Park <cw00.choi@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
1. address has to be page aligned.
2. set_memory_x uses page size argument, not size.
Bug causes with following commit:
commit da28179b4e90dda56912ee825c7eaa62fc103797
Author: Mingarelli, Thomas <Thomas.Mingarelli@hp.com>
Date: Mon Nov 7 10:59:00 2011 +0100
watchdog: hpwdt: Changes to handle NX secure bit in 32bit path
commit e67d668e14 upstream.
This patch makes use of the set_memory_x() kernel API in order
to make necessary BIOS calls to source NMIs.
Signed-off-by: Maxim Uvarov <maxim.uvarov@oracle.com>
Signed-off-by: Wim Van Sebroeck <wim@iguana.be>
Cc: stable <stable@vger.kernel.org>
The user may wish to set their own value (for real cross compiles). Since the
top level Makefile initialises CROSS_COMPILE to empty by default, we must
check it for being empty (rather than for being defined) before we override.
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
The existing numactl website is no longer working. Change website information
of numactl/libnuma utility. And, Rearrange tab space for readability.
Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
unix_may_send hook has the prototype:
int (*unix_may_send) (struct socket *sock, struct socket *other)
so the documentation is wrongly referring to the second argument as @sock.
Signed-off-by: Javier Martinez Canillas <javier@dowhile0.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
The text for version 1.1 of the Open Sofware license doesn't seem
to be available anywhere on http://www.opensource.org/ any more.
Replace it with an URL on fedora.org.
Thanks to Randy Dunlap for his advise choosing the most
appropriate replacement URL.
Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Fix broken link in Documentation/filesystem, replacing
ftp://ftp.uk.linux.org/pub/linux/sct/fs/jfs/journal-design.ps.gz
by a URL on http://kernel.org
Thanks to Randy Dunlap for his advise on the best replacement
URL to use.
Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
those routines have everything we need to map/unmap
USB requests and it's better to use them.
Tested-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
those routines have everything we need to map/unmap
USB requests and it's better to use them.
In order to achieve that, we had to add a simple
change on how we allocate and use our setup buffer;
we cannot allocate it from coherent anymore otherwise
the generic map/unmap routines won't be able to easily
know that the GetStatus request already has a DMA
address.
Signed-off-by: Felipe Balbi <balbi@ti.com>
such utilities are currently duplicated on all UDC
drivers basically with the same structure. Let's group
all implementations into one generic implementation
and get rid of that duplication.
Signed-off-by: Felipe Balbi <balbi@ti.com>
This patch updates device tree binding documentation to add digital
microphone to PAZ00 board.
Signed-off-by: Leon Romanovsky <leon@leon.nu>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Align mpc8610_hpcd with p1022_ds on getting codec node by just calling
of_parse_phandle. The bonus point of doing that is we can save
exporting get_node_by_phandle_name() when we consolidate the common
bits between mpc8610_hpcd and p1022_ds into a module, which can be
shared by more machine drivers added later.
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Acked-by: Timur Tabi <timur@freescale.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
The second parameter of function get_dma_channel is actually a property
name rather than a compatible string, so rename it for less confusing.
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Acked-by: Timur Tabi <timur@freescale.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
