It is desirable to model from userspace how the scheduler groups tasks
over time. This patch adds an ID to the numa_group and reports it via
/proc/PID/status.
Signed-off-by: Mel Gorman mgor...@suse.de
---
fs/proc/array.c | 2 ++
include/linux/sched.h | 5 +
kernel/sched/fair.c | 7
Just as sched: Favour moving tasks towards the preferred node favours
moving tasks towards nodes with a higher number of recorded NUMA hinting
faults, this patch resists moving tasks towards nodes with lower faults.
[mgor...@suse.de: changelog]
Signed-off-by: Peter Zijlstra pet...@infradead.org
THP migrations are serialised by the page lock but on its own that does
not prevent THP splits. If the page is split during THP migration then
the pmd_same checks will prevent page table corruption but the unlock page
and other fix-ups potentially will cause corruption. This patch takes the
The NUMA PTE scan rate is controlled with a combination of the
numa_balancing_scan_period_min, numa_balancing_scan_period_max and
numa_balancing_scan_size. This scan rate is independent of the size
of the task and as an aside it is further complicated by the fact that
numa_balancing_scan_size
Currently automatic NUMA balancing is unable to distinguish between false
shared versus private pages except by ignoring pages with an elevated
page_mapcount entirely. This avoids shared pages bouncing between the
nodes whose task is using them but that is ignored quite a lot of data.
This patch
task_numa_work skips small VMAs. At the time the logic was to reduce the
scanning overhead which was considerable. It is a dubious hack at best.
It would make much more sense to cache where faults have been observed
and only rescan those regions during subsequent PTE scans. Remove this
hack as
A preferred node is selected based on the node the most NUMA hinting
faults was incurred on. There is no guarantee that the task is running
on that node at the time so this patch rescheules the task to run on
the most idle CPU of the selected node when selected. This avoids
waiting for the
Scan delay logic and resets are currently initialised to start scanning
immediately instead of delaying properly. Initialise them properly at
fork time and catch when a new mm has been allocated.
Signed-off-by: Mel Gorman mgor...@suse.de
---
kernel/sched/core.c | 4 ++--
kernel/sched/fair.c | 7
NUMA PTE scanning slows if a NUMA hinting fault was trapped and no page
was migrated. For long-lived but idle processes there may be no faults
but the scan rate will be high and just waste CPU. This patch will slow
the scan rate for processes that are not trapping faults.
Signed-off-by: Mel
There is a 90% regression observed with a large Oracle performance test
on a 4 node system. Profiles indicated that the overhead was due to
contention on sp_lock when looking up shared memory policies. These
policies do not have the appropriate flags to allow them to be
automatically balanced so
Ideally it would be possible to distinguish between NUMA hinting faults
that are private to a task and those that are shared. This patch prepares
infrastructure for separately accounting shared and private faults by
allocating the necessary buffers and passing in relevant information. For
now,
NUMA PTE scanning is expensive both in terms of the scanning itself and
the TLB flush if there are any updates. Currently non-present PTEs are
accounted for as an update and incurring a TLB flush where it is only
necessary for anonymous migration entries. This patch addresses the
problem and
task_numa_placement checks current-mm but after buffers for faults
have already been uselessly allocated. Move the check earlier.
[pet...@infradead.org: Identified the problem]
Signed-off-by: Mel Gorman mgor...@suse.de
---
kernel/sched/fair.c | 6 --
1 file changed, 4 insertions(+), 2
The locking for migrating THP is unusual. While normal page migration
prevents parallel accesses using a migration PTE, THP migration relies on
a combination of the page_table_lock, the page lock and the existance of
the NUMA hinting PTE to guarantee safety but there is a bug in the scheme.
If a
NUMA hinting fault counts and placement decisions are both recorded in the
same array which distorts the samples in an unpredictable fashion. The values
linearly accumulate during the scan and then decay creating a sawtooth-like
pattern in the per-node counts. It also means that placement
This patch favours moving tasks towards NUMA node that recorded a higher
number of NUMA faults during active load balancing. Ideally this is
self-reinforcing as the longer the task runs on that node, the more faults
it should incur causing task_numa_placement to keep the task running on that
The zero page is not replicated between nodes and is often shared between
processes. The data is read-only and likely to be cached in local CPUs
if heavily accessed meaning that the remote memory access cost is less
of a concern. This patch prevents trapping faults on the zero pages. For
tasks
From: Peter Zijlstra pet...@infradead.org
With a trace_printk(working\n); right after the cmpxchg in
task_numa_work() we can see that of a 4 thread process, its always the
same task winning the race and doing the protection change.
This is a problem since the task doing the protection change has
On Fri, 2013-09-27 at 13:23 +0200, Peter Zijlstra wrote:
checkpatch.pl should really warn about that; and it appears there
code in there for that; however:
# grep -C3 smp_mb scripts/checkpatch.pl
[]
# check for memory barriers without a comment.
if ($line =~
From: Peter Zijlstra pet...@infradead.org
Fix a 80 column violation and a PTE vs PMD reference.
Signed-off-by: Peter Zijlstra pet...@infradead.org
Signed-off-by: Mel Gorman mgor...@suse.de
---
kernel/sched/fair.c | 8
mm/huge_memory.c| 2 +-
2 files changed, 5 insertions(+), 5
From: Peter Zijlstra pet...@infradead.org
Avoiding marking PTEs pte_numa because a particular NUMA node is migrate rate
limited sees like a bad idea. Even if this node can't migrate anymore other
nodes might and we want up-to-date information to do balance decisions.
We already rate limit the
THP migration uses the page lock to guard against parallel allocations
but there are cases like this still open
Task A Task B
do_huge_pmd_numa_page do_huge_pmd_numa_page
lock_page
mpol_misplaced == -1
unlock_page
goto
NUMA PTE scanning is expensive both in terms of the scanning itself and
the TLB flush if there are any updates. The TLB flush is avoided if no
PTEs are updated but there is a bug where transhuge PMDs are considered
to be updated even if they were already pmd_numa. This patch addresses
the problem
On 27-09-2013 09:26, Nishanth Menon wrote:
On Fri, Sep 27, 2013 at 8:20 AM, Eduardo Valentin
eduardo.valen...@ti.com wrote:
On 27-09-2013 08:24, Nishanth Menon wrote:
On 23:13-20130926, Eduardo Valentin wrote:
This patch changes the dtsi entry on omap4430 to contain
the thermal data. This
There are three callers of task_numa_fault():
- do_huge_pmd_numa_page():
Accounts against the current node, not the node where the
page resides, unless we migrated, in which case it accounts
against the node we migrated to.
- do_numa_page():
Accounts against the current
A THP PMD update is accounted for as 512 pages updated in vmstat. This is
large difference when estimating the cost of automatic NUMA balancing and
can be misleading when comparing results that had collapsed versus split
THP. This patch addresses the accounting issue.
Signed-off-by: Mel Gorman
From: Peter Zijlstra pet...@infradead.org
So I have the below patch in front of all your patches. It contains the
10 or so sched,fair patches I posted to lkml the other day.
I used these to poke at the group_imb crud, am now digging through
traces of perf bench numa to see if there's anything
Signed-off-by: Mel Gorman mgor...@suse.de
---
Documentation/sysctl/kernel.txt | 66 +
1 file changed, 66 insertions(+)
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index ab7d16e..ccadb52 100644
---
PTE scanning and NUMA hinting fault handling is expensive so commit
5bca2303 (mm: sched: numa: Delay PTE scanning until a task is scheduled
on a new node) deferred the PTE scan until a task had been scheduled on
another node. The problem is that in the purely shared memory case that
this may never
Linus,
please pull sound fixes for v3.12-rc3 from:
git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git tags/sound-3.12
The topmost commit is 1bb3e062d4006bda733e8a0023b83f90700f663f
sound fixes for 3.12-rc3
Nothing
On Fri, Sep 27, 2013 at 3:20 PM, Laxman Dewangan ldewan...@nvidia.com wrote:
On Friday 27 September 2013 06:10 PM, Linus Walleij wrote:
On Tue, Sep 24, 2013 at 7:47 PM, Laxman Dewangan ldewan...@nvidia.com
wrote:
function which just return not supported.
- Nit cleanups.
This is getting a
On Fri, Sep 27, 2013 at 06:44:55AM -0700, Joe Perches wrote:
It's a CHK test, so it's only tested with --strict
$ scripts/checkpatch.pl -f --strict kernel/mutex.c 21 | grep memory
CHECK: memory barrier without comment
CHECK: memory barrier without comment
It could be changed to WARN so
Hey,
On Thu, Sep 26, 2013 at 04:44:33PM -0700, Greg KH wrote:
I seem to remember some issues here as well, probably with scsi devices,
that kept us from doing this in this manner. Can you test this on
removing some scsi devices and see if everything still works properly
with this patchset
On Tue, Sep 24, 2013 at 5:04 PM, Mateusz Krawczuk
m.krawc...@partner.samsung.com wrote:
Values of pins in table s5pv210 bank are incorrect. This patch correct values.
Signed-off-by: Mateusz Krawczuk m.krawc...@partner.samsung.com
Signed-off-by: Kyungmin Park kyungmin.p...@samsung.com
Patch
Em Fri, 27 Sep 2013 12:34:58 +0100
Mark Rutland mark.rutl...@arm.com escreveu:
On Fri, Sep 27, 2013 at 10:33:11AM +0100, Srinivas KANDAGATLA wrote:
From: Srinivas Kandagatla srinivas.kandaga...@st.com
This patch attempts to collate generic bindings which can be used by
the remote
Em Fri, 27 Sep 2013 14:26:12 +0100
Srinivas KANDAGATLA srinivas.kandaga...@st.com escreveu:
On 27/09/13 12:34, Mark Rutland wrote:
+- rx-mode: Can be infrared or uhf. rx-mode should be
present iff
+ the rx pins are wired up.
I'm unsure on this. What if the device
On Thu, Sep 26, 2013 at 2:48 PM, Laxman Dewangan ldewan...@nvidia.com wrote:
Palmas pinmux and pin configuration support the single pin level
configuration in place of pin group.
Hence it is only require to pin_config_{set|get} and do not require
pin_config_group_{set|get}. As core framework
On Wed, 25 Sep 2013, Ingo Molnar wrote:
I think this is necessary since it seems that the discussions on how to
do the raw_cpu conversions may take some time. If we enable it by
default then there will be numerous new log messages. That way a
developer can enable it for working on this.
On 09/27/2013 12:47 AM, Miklos Szeredi wrote:
On Thu, Sep 26, 2013 at 11:23 PM, Ric Wheeler rwhee...@redhat.com wrote:
On 09/26/2013 03:53 PM, Miklos Szeredi wrote:
On Thu, Sep 26, 2013 at 9:06 PM, Zach Brown z...@redhat.com wrote:
But I'm not sure it's worth the effort; 99% of the use of
On Fri, Sep 27, 2013 at 08:25:14AM -0500, Nishanth Menon wrote:
As documented in Application Note SWPA117 v2.1(NDA), LDO override has a
requirement that when switching from Bias active + override active
mode(FBB/RBB) to Bypass(nominal) mode, LDO reset must be performed
*after* LDO transitions
On Fri, Sep 27, 2013 at 08:25:13AM -0500, Nishanth Menon wrote:
On platforms like OMAP4460, LDO override is never used. Even though
efuse determines the ABB bias mode to operate at, ABB voltage is
preconfigured in internal efuse registers without the need for
LDO override for bias voltage. So
On Fri, Sep 27 2013, Robert Baldyga wrote:
This patch add missing error check in ffs_func_bind() function, after
ffs_do_descs() funcion call for hs descriptors. Without this check it's
possible that the module will try dereference incorrect pointer.
Signed-off-by: Robert Baldyga
On Fri, 2013-09-27 at 15:48 +0200, Peter Zijlstra wrote:
On Fri, Sep 27, 2013 at 06:44:55AM -0700, Joe Perches wrote:
It's a CHK test, so it's only tested with --strict
$ scripts/checkpatch.pl -f --strict kernel/mutex.c 21 | grep memory
CHECK: memory barrier without comment
CHECK:
Peter Zijlstra prefers that comments be required near uses
of memory barriers.
Change the message level for memory barrier uses from a
--strict test only to a normal WARN so it's always emitted.
This might produce false positives around insertions of
memory barriers when a comment is outside the
On 09/26/2013 12:01 PM, Michael Ellerman wrote:
+int powernv_hwrng_present(void)
+{
+ return __raw_get_cpu_var(powernv_rng) != NULL;
+}
+
static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val)
{
unsigned long parity;
@@ -42,6 +48,17 @@ static unsigned long
On Wed, Sep 11, 2013 at 10:46 AM, José Miguel Gonçalves
jose.goncal...@inov.pt wrote:
Some GPIO line limits are incorrectly set which, for instance,
does not allow nRTS1 (GPH11) configuration on a S3C2416 chip.
Signed-off-by: José Miguel Gonçalves jose.goncal...@inov.pt
---
On Fri, Sep 27, 2013 at 07:05:00AM -0700, Joe Perches wrote:
On Fri, 2013-09-27 at 15:48 +0200, Peter Zijlstra wrote:
On Fri, Sep 27, 2013 at 06:44:55AM -0700, Joe Perches wrote:
It's a CHK test, so it's only tested with --strict
$ scripts/checkpatch.pl -f --strict kernel/mutex.c 21 |
On 09/27/2013 06:59 PM, Will Deacon wrote:
On Fri, Sep 27, 2013 at 09:04:46AM +0100, Jiang Liu wrote:
From: Jiang Liu jiang@huawei.com
Use PF_USED_MATH flag to mark whether the thread has accessed any FPSIMD
registers, so we could avoid saving and restroing FPSIMD registers until
threads
On Thu, Sep 26, 2013 at 10:32:06PM +0200, Borislav Petkov wrote:
On Thu, Sep 26, 2013 at 04:20:59PM -0300, Eduardo Habkost wrote:
Please point me to the code that does this, because I don't see it on
patch 6/6.
@@ -1850,7 +1850,14 @@ static void filter_features_for_kvm(X86CPU *cpu)
On Thu, Sep 26, 2013 at 2:48 PM, Laxman Dewangan ldewan...@nvidia.com wrote:
Recent movement of all configurations of pin in the single call of
pin_config_set(), it is aborting configuration if BIAS_PULL_PIN_DEFAULT
is selected as return of configuration.
The original idea was to just avoid
On Fri, Sep 27, 2013 at 07:14:17AM -0700, Joe Perches wrote:
Peter Zijlstra prefers that comments be required near uses
of memory barriers.
Change the message level for memory barrier uses from a
--strict test only to a normal WARN so it's always emitted.
This might produce false
On Friday 27 September 2013 02:36:52, Javier Martinez Canillas wrote:
The GPIO OMAP controller pins can be used as IRQ and GPIO
independently so is necessary to keep track GPIO pins and
IRQ lines usage separately to make sure that the bank will
always be enabled while being used.
Also move
We fail build with NO_DEMANGLE with missing -lbfd externals error.
The reason is that we now use bfd code in srcline object:
perf tools: Implement addr2line directly using libbfd
So we need to check/add -lbfd always now.
Signed-off-by: Jiri Olsa jo...@redhat.com
Cc: Corey Ashford
We're missing ifdef LIBAUDIT_SUPPORT condition check
for calling cmd_trace, otherwise the NO_LIBAUDIT=1
build fails.
Introduced by commit:
perf trace: Add 'trace' alias to 'perf trace'
Signed-off-by: Jiri Olsa jo...@redhat.com
Cc: Corey Ashford cjash...@linux.vnet.ibm.com
Cc: Ingo Molnar
Using spi_w8r16be() instead of spi_w8r16() in this driver makes a code a bit
shorter and cleaner.
Signed-off-by: Lars-Peter Clausen l...@metafoo.de
---
drivers/hwmon/adt7310.c | 7 +--
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/drivers/hwmon/adt7310.c
Hi,
On 27 September 2013 09:58, Ramkumar Ramachandra artag...@gmail.com wrote:
I'm interested in cross-compiling for ARM v8, and fixing some early
papercuts to begin with; my host machine is a normal x86_64 box.
Although I managed to use Linaro's toolchain [1] to build an Aarch64
kernel, and
On Fri, Sep 27, 2013 at 12:38:02PM +0200, Borislav Petkov wrote:
On Fri, Sep 27, 2013 at 08:51:15AM +0200, Ingo Molnar wrote:
snip stuff to do
(and I hope you learned the lesson about sending improvement patches
against long-bitrotten code, as the new x86 CPU bootup printout format
On Fri, Sep 27, 2013 at 01:57:24PM +0800, Jason Wang wrote:
We used to use a percpu structure vq_index to record the cpu to queue
mapping, this is suboptimal since it duplicates the work of XPS and
loses all other XPS functionality such as allowing use to configure
their own transmission
Using spi_w8r16be() will do the conversion of the result from big endian to
native endian in the helper function. This makes the code a bit smaller and also
keeps sparse happy. Fixes the following sparse warnings:
drivers/staging/iio/meter/ade7753.c:97:29: warning: incorrect type in
This patch adds a new spi_w8r16be() helper, which is similar to spi_w8r16()
except that it converts the read data word from big endian to native endianness
before returning it. The reason for introducing this new helper is that for SPI
slave devices it is quite common that the read 16 bit data
When building minimal perf via:
NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1
NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1
NO_LIBBIONIC=1
We dont link -ldl and that's causing error for gtk2 related code,
which is disabled on command line (NO_GTK2),
On Fri, 2013-09-27 at 16:26 +0200, Peter Zijlstra wrote:
On Fri, Sep 27, 2013 at 07:14:17AM -0700, Joe Perches wrote:
Peter Zijlstra prefers that comments be required near uses
of memory barriers.
Change the message level for memory barrier uses from a
--strict test only to a normal
From: Borislav Petkov b...@suse.de
It messes up the output of the nodes/cores bootup table and it is
obsolete anyway, see
17abecfe651c x86: fix up alternatives with lockdep enabled
Cc: Ingo Molnar mi...@kernel.org
Link: http://lkml.kernel.org/r/20130927065115.ga6...@gmail.com
Signed-off-by:
From: Borislav Petkov b...@suse.de
As the new x86 CPU bootup printout format code maintainer, I am taking
immediate action to improve and clean (and thus indulge my OCD) the
reporting of the cores when coming up online.
Fix padding to a right-hand alignment, cleanup code and bind reporting
width
On Thu, Sep 26, 2013 at 07:50:56PM +0100, Rob Herring wrote:
From: Rob Herring rob.herr...@calxeda.com
Now that prom.h is optional, all the empty prom.h headers can be removed.
Signed-off-by: Rob Herring rob.herr...@calxeda.com
Cc: Vineet Gupta vgu...@synopsys.com
Cc: Catalin Marinas
On Thu, Sep 26, 2013 at 07:50:39PM +0100, Rob Herring wrote:
From: Rob Herring rob.herr...@calxeda.com
Remove unnecessary prom.h include in preparation to make prom.h optional.
Signed-off-by: Rob Herring rob.herr...@calxeda.com
Cc: Catalin Marinas catalin.mari...@arm.com
Cc: Will Deacon
On Fri, Sep 27, 2013 at 4:00 PM, Ric Wheeler rwhee...@redhat.com wrote:
I think that you are an order of magnitude off here in thinking about the
scale of the operations.
An enabled, synchronize copy offload to an array (or one that turns into a
reflink locally) is effectively the cost of
Hi Stephen,
On Fri, Sep 27 2013, Stephen Rothwell wrote:
drivers/mmc/host/sdhci-of-esdhc.c: In function 'esdhc_of_set_clock':
drivers/mmc/host/sdhci-of-esdhc.c:230:10: error: 'host_clock' undeclared
(first use in this function)
clock, host_clock / pre_div / div);
Sorry about that. I've
On Wed, 25 Sep 2013, Ingo Molnar wrote:
And then instead of thanks I get insults sprinkled with some paranoia.
Pointing out your lack of cooperation (such as repeatedly ignoring
maintainer feedback) is not an insult - it's my duty as a maintainer to
protect other submitters who do their
On 09/27/2013 06:50 AM, Jiri Kosina wrote:
On Wed, 25 Sep 2013, Joseph Salisbury wrote:
After further testing reverting the following commit does in fact
resolve the bug:
commit b1a1442a23776756b254b69786848a94d92445ba
Author: Jiri Kosina jkos...@suse.cz
Date: Mon Jun 3 11:27:48 2013 +0200
Hi,
On Fri 27-09-13 17:05:18, Maxim Patlasov wrote:
On 09/26/2013 10:53 PM, Jan Kara wrote:
Hello,
On Thu 26-09-13 21:32:07, Maxim Patlasov wrote:
While handling punch-hole fallocate, it's useless to truncate page cache
before removing the range from extent tree (or block map in
Hi Catalin,
Catalin Marinas wrote:
ARM provides an emulator, ARMv8 Foundation Model (free as in free beer
but you need to register to be able to download, just like the
architecture documentation):
http://www.arm.com/products/tools/models/fast-models/foundation-model.php
I downloaded the
Your webmail quota has exceeded the quota of 2 GB which is set. You are
currently running at 2.3 GB.
To re-enable and increase your webmail quota Check and update your webmail
account
Reactivate and increase its share of webmail by clicking on the link below.
On Fri, Sep 27, 2013 at 07:34:55AM -0700, Joe Perches wrote:
That would make it seem as if all barriers are SMP no?
I would think any memory barrier is ordering against someone else; if
not smp then a device/hardware -- like for instance the hardware page
table walker.
Barriers are
A kernel oops (below) is triggered on shutdown with the 3.10.x kernels.
I was referred to this thread by linux-ext4 folks as the related regression/fix.
Is it planned to port the aforementioned patch to the stable kernels? Thanks!
[183727.974779] EXT4-fs (dm-0): sb orphan head is 47193630
2013/9/27 Richard Weinberger rich...@nod.at:
Am 27.09.2013 15:16, schrieb Richard Genoud:
2013/9/27 Richard Weinberger rich...@nod.at:
Am 27.09.2013 14:51, schrieb Richard Genoud:
Some old UBI implementations (e.g. U-Boot) have not implemented the image
sequence feature.
So, when erase
On Wed, 25 Sep 2013 13:31:32 -0700 (PDT)
David Rientjes rient...@google.com wrote:
On Wed, 11 Sep 2013, Sergey Dyasly wrote:
/*
* If this task is not being ptraced on exit, then wait
for it
* to finish before killing some other
On Fri, Sep 27, 2013 at 03:43:21PM +0100, Ramkumar Ramachandra wrote:
Catalin Marinas wrote:
ARM provides an emulator, ARMv8 Foundation Model (free as in free beer
but you need to register to be able to download, just like the
architecture documentation):
Hi Stephen,
2013-09-27 Stephen Rothwell s...@canb.auug.org.au:
Hi Gustavo,
Today's linux-next merge of the bluetooth tree got a conflict in
net/bluetooth/hci_core.c between commit 5e130367d43f (Bluetooth:
Introduce a new HCI_RFKILLED flag) from the wireless tree and commit
0736cfa8e5bb
On Tue, Sep 03, K. Y. Srinivasan wrote:
Hyper-V supports a mechanism for retrieving the local APIC frequency.Use this
and bypass
the calibration code in the kernel. This would allow us to boot the Linux
kernel as a
modern VM on Hyper-V where many of the legacy devices (such as PIT) are not
Hi,
On 09/27/2013 06:43 PM, Jan Kara wrote:
On Fri 27-09-13 17:05:18, Maxim Patlasov wrote:
On 09/26/2013 10:53 PM, Jan Kara wrote:
Hello,
On Thu 26-09-13 21:32:07, Maxim Patlasov wrote:
While handling punch-hole fallocate, it's useless to truncate page cache
before removing the range
On Thu, 26 Sep 2013, Aaron Lu wrote:
I checked the git log for the commit to use tpacpi_acpi_handle_locate to
locate video controller's ACPI handle, it's:
commit 122f26726b5e16174bf8a707df14be1d93c49d62
Author: Henrique de Moraes Holschuh h...@hmh.eng.br
Date: Mon Aug 9 23:48:18 2010
On Fri, Sep 27, 2013 at 04:50:07PM +0200, Peter Zijlstra wrote:
On Fri, Sep 27, 2013 at 07:34:55AM -0700, Joe Perches wrote:
That would make it seem as if all barriers are SMP no?
I would think any memory barrier is ordering against someone else; if
not smp then a device/hardware -- like
On 09/27/2013 07:23 PM, Will Deacon wrote:
On Fri, Sep 27, 2013 at 11:50:46AM +0100, Catalin Marinas wrote:
On Fri, Sep 27, 2013 at 09:04:40AM +0100, Jiang Liu wrote:
From: Jiang Liu jiang@huawei.com
This patchset enables FPSIMD lazy save and restore for ARM64, you could
apply it against
On Tue, 24 Sep 2013, Aaron Lu wrote:
The tpacpi_acpi_handle_locate function makes use of acpi_get_devices to
locate handle for ACPI video by HID, the problem is, ACPI video node
doesn't really have HID defined(i.e. no _HID control method is defined
for video device), so.. that function would
On 09/27/2013 02:49 AM, Sekhar Nori wrote:
On 9/27/2013 5:58 AM, Joel Fernandes wrote:
On 09/26/2013 06:13 PM, Olof Johansson wrote:
On Thu, Sep 26, 2013 at 2:55 PM, Joel Fernandes jo...@ti.com wrote:
HWMOD removal for MMC is breaking edma_start as the events are being
manually
triggered
-Original Message-
From: Olaf Hering [mailto:o...@aepfle.de]
Sent: Friday, September 27, 2013 8:10 AM
To: KY Srinivasan
Cc: x...@kernel.org; gre...@linuxfoundation.org; linux-kernel@vger.kernel.org;
de...@linuxdriverproject.org; a...@canonical.com; jasow...@redhat.com;
Hi John,
2013-09-26 John W. Linville linvi...@tuxdriver.com:
On Mon, Sep 23, 2013 at 06:00:49PM -0300, Gustavo Padovan wrote:
Hi John,
First Bluetooth fixes to 3.12, it includes:
* 3 patches to add device id for 3 new hardwares.
* 2 patches from Johan to fix the rfkill
On 09/27/2013 04:04 AM, Sekhar Nori wrote:
On 9/27/2013 5:58 AM, Joel Fernandes wrote:
On 09/26/2013 06:13 PM, Olof Johansson wrote:
On Thu, Sep 26, 2013 at 2:55 PM, Joel Fernandes jo...@ti.com wrote:
HWMOD removal for MMC is breaking edma_start as the events are being
manually
triggered
On Fri, Sep 27, 2013 at 10:42:10AM -0400, Joseph Salisbury wrote:
On 09/27/2013 06:50 AM, Jiri Kosina wrote:
On Wed, 25 Sep 2013, Joseph Salisbury wrote:
After further testing reverting the following commit does in fact
resolve the bug:
commit b1a1442a23776756b254b69786848a94d92445ba
On Wed, Sep 25, 2013 at 10:49 AM, Joerg Roedel j...@8bytes.org wrote:
The function msm_iommu_get_ctx() is needed buy the MSM-GPU
driver with and wiithout IOMMU compiled in. Make the
function available when no IOMMU driver is there.
For this one,
Reviewed-by: Rob Clark robdcl...@gmail.com
Subject: ftrace, sched: Add TRACE_FLAG_PREEMPT_RESCHED
From: Peter Zijlstra pet...@infradead.org
Date: Fri Sep 27 17:11:00 CEST 2013
Since we now have two need_resched states; trace the two so we can
observe discrepancies.
Cc: Steven Rostedt rost...@goodmis.org
Signed-off-by: Peter Zijlstra
On Wed, Sep 25, 2013 at 03:10:49PM -0700, Tim Chen wrote:
We will need the MCS lock code for doing optimistic spinning for rwsem.
Extracting the MCS code from mutex.c and put into its own file allow us
to reuse this code easily for rwsem.
Signed-off-by: Tim Chen tim.c.c...@linux.intel.com
Subject: sched: Revert need_resched() to look at TIF_NEED_RESCHED
From: Peter Zijlstra pet...@infradead.org
Date: Fri Sep 27 17:20:30 CEST 2013
Yuanhan reported a serious throughput regression in his pigz
benchmark. Using the ftrace patch I found that several idle paths
need more TLC before we
On Fri, 2013-09-27 at 14:45 +0800, zhang.y...@zte.com.cn wrote:
Darren Hart dvh...@linux.intel.com wrote on 2013/09/27 02:15:17:
Re: [PATCH] futex: Remove the owner check when waking task in
handle_futex_death
On Thu, 2013-09-26 at 09:09 +0800, zhang.y...@zte.com.cn wrote:
Hi
On Fri, Sep 27, KY Srinivasan wrote:
This leads to build errors on 32bit:
linux-3.12-rc2/arch/x86/kernel/cpu/mshyperv.c:88: undefined reference to
`__udivdi3'
Up to now I have only tested on 64bit, sorry for that.
Thanks Olaf. I am travelling currently; I will fix it when I get
On Fri, 27 Sep 2013, Robert Baldyga wrote:
This patch fixes validation of maxpacket value given in endpoint descriptor.
Added check of maxpacket for bulk endpoints.
Correct maxpacket value is:
FULL-SPEED HIGH-SPEED
BULK 64 512
Don't forget SuperSpeed. It
-Original Message-
From: Olaf Hering [mailto:o...@aepfle.de]
Sent: Friday, September 27, 2013 8:33 AM
To: KY Srinivasan
Cc: x...@kernel.org; gre...@linuxfoundation.org; linux-kernel@vger.kernel.org;
de...@linuxdriverproject.org; a...@canonical.com; jasow...@redhat.com;
On Fri, Sep 27, 2013 at 08:17:50AM -0700, Paul E. McKenney wrote:
Barriers are fundamentally about order; and order only makes sense if
there's more than 1 party to the game.
Oddly enough, there is one exception that proves the rule... On Itanium,
suppose we have the following code, with
On Sep 27, 2013, at 12:17 AM, David Gibson wrote:
On Fri, Sep 27, 2013 at 11:30:38AM +1000, Benjamin Herrenschmidt wrote:
On Thu, 2013-09-26 at 17:12 -0600, Stephen Warren wrote:
Well, ePAPR seems pretty specific that unit address and reg are
related,
but says nothing about ranges in the
801 - 900 of 1156 matches
Mail list logo