On Thu, 2014-07-24 at 14:22 +0800, Wei Yang wrote:
> This patch set enables the SRIOV on POWER8.
Hi Bjorn !
There are 4 patches in there to the generic code, but so far not much
review from your side of the fence :-)
How do you want to proceed ?
Cheers,
Ben.
> The gerneral idea is put each VF
Hello Scott,
On 07/31/2014 12:28 AM, Scott Wood wrote:
> On Wed, 2014-07-30 at 23:35 -0500, Emil Medve wrote:
>> Hello Scott,
>>
>>
>> On 07/30/2014 09:30 PM, Scott Wood wrote:
>>> On Wed, 2014-07-30 at 16:52 -0500, Emil Medve wrote:
+ mdio0: mdio fc000 {
+
On Wed, 2014-07-30 at 23:35 -0500, Emil Medve wrote:
> Hello Scott,
>
>
> On 07/30/2014 09:30 PM, Scott Wood wrote:
> > On Wed, 2014-07-30 at 16:52 -0500, Emil Medve wrote:
> >> + mdio0: mdio fc000 {
> >> + };
> >
> > Why is the empty nod
On Wed, 2014-07-30 at 23:37 -0500, Jain Priyanka-B32167 wrote:
>
> -Original Message-
> From: Wood Scott-B07421
> Sent: Thursday, July 31, 2014 1:43 AM
> To: Jain Priyanka-B32167
> Cc: devicet...@vger.kernel.org; linuxppc-dev@lists.ozlabs.org; Aggrwal
> Poonam-B10812; Kushwaha Prabhakar-
Hello Scott,
On 07/30/2014 09:30 PM, Scott Wood wrote:
> On Wed, 2014-07-30 at 16:52 -0500, Emil Medve wrote:
>> Hello Scott,
>>
>>
>> On 07/29/2014 02:58 PM, Scott Wood wrote:
>>> On Mon, 2014-07-28 at 06:51 +, Emil Medve wrote:
Hello Scott,
Scott Wood freescale.com> wri
-Original Message-
From: Wood Scott-B07421
Sent: Thursday, July 31, 2014 1:43 AM
To: Jain Priyanka-B32167
Cc: devicet...@vger.kernel.org; linuxppc-dev@lists.ozlabs.org; Aggrwal
Poonam-B10812; Kushwaha Prabhakar-B32579
Subject: Re: [2/2] powerpc/fsl-booke: Add initial T1042RDB_PI board s
reproduce: make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
>> sound/soc/fsl/fsl_asrc.c:563:28: sparse: restricted snd_pcm_format_t
>> degrades to integer
>> sound/soc/fsl/fsl_asrc.c:570:28: sparse: restricted snd_pcm_format_t
>> degrades to integer
vim +563 sound/soc/
On Wed, 2014-07-30 at 16:52 -0500, Emil Medve wrote:
> Hello Scott,
>
>
> On 07/29/2014 02:58 PM, Scott Wood wrote:
> > On Mon, 2014-07-28 at 06:51 +, Emil Medve wrote:
> >> Hello Scott,
> >>
> >>
> >> Scott Wood freescale.com> writes:
> >>> On Wed, 2014-07-16 at 15:17 -0500, Shruti Kanetkar
Hello Scott,
On 07/29/2014 02:58 PM, Scott Wood wrote:
> On Mon, 2014-07-28 at 06:51 +, Emil Medve wrote:
>> Hello Scott,
>>
>>
>> Scott Wood freescale.com> writes:
>>> On Wed, 2014-07-16 at 15:17 -0500, Shruti Kanetkar wrote:
+ mdio fd000 {
+
On Wed, Jul 09, 2014 at 09:54:11AM +0530, Priyanka Jain wrote:
> diff --git a/arch/powerpc/boot/dts/t104xrdb.dtsi
> b/arch/powerpc/boot/dts/t104xrdb.dtsi
> index 9aaefa5..e7e765f 100644
> --- a/arch/powerpc/boot/dts/t104xrdb.dtsi
> +++ b/arch/powerpc/boot/dts/t104xrdb.dtsi
> @@ -57,7 +57,8 @@
>
Nicolin Chen wrote:
DPCM needs extra dapm routes in the machine driver to route audio
between Front-End and Back-End. In order to differ the stream names
in the route map from CODECs, we here add specific stream names to
SSI driver so that we can implement ASRC via DPCM to it.
Signed-off-by: Nic
From: Peter Zijlstra
3.12-stable review patch. If anyone has any objections, please let me know.
===
commit 4badad352a6bb202ec68afa7a574c0bb961e5ebc upstream.
The optimistic spin code assumes regular stores and cmpxchg() play nice;
this is found to not be true for at least: parisc
The Freescale Generic ASoC Sound Card is a general ASoC DAI Link driver that
can be used, ideally, for all Freescale CPU DAI drivers and external CODECs.
The idea of this generic sound card is a bit like ASoC Simple Card. However,
for Freescale SoCs (especially those released in recent years), mos
On 07/30/2014 07:31 PM, Alexey Kardashevskiy wrote:
> This defines and implements VFIO IOMMU API required to support
> Dynamic DMA windows defined in the SPAPR specification. The ioctl handlers
> implement host-size part of corresponding RTAS calls:
> - VFIO_IOMMU_SPAPR_TCE_QUERY - ibm,query-pe-dma
This defines list_for_each_entry_rcu_notrace which uses
new list_entry_rcu_notrace which uses rcu_dereference_raw_notrace instead
of rcu_dereference_raw whici allows us using
list_for_each_entry_rcu_notrace when MMU is off (real mode).
Signed-off-by: Alexey Kardashevskiy
---
include/linux/rculis
Modern IBM POWERPC systems support multiple IOMMU tables per PE
so we need a more reliable way (compared to container_of()) to get
a PE pointer from the iommu_table struct pointer used in IOMMU functions.
At the moment IOMMU group data points to an iommu_table struct. This
introduces a spapr_tce_i
This defines and implements VFIO IOMMU API required to support
Dynamic DMA windows defined in the SPAPR specification. The ioctl handlers
implement host-size part of corresponding RTAS calls:
- VFIO_IOMMU_SPAPR_TCE_QUERY - ibm,query-pe-dma-window;
- VFIO_IOMMU_SPAPR_TCE_CREATE - ibm,create-pe-dma-w
SPAPR defines an interface to create additional DMA windows dynamically.
"Dynamically" means that the window is not allocated at the guest start
and the guest can request it later. In practice, existing linux guests
check for the capability and if it is there, they create+map one big DMA
window as
This makes use of the it_page_size from the iommu_table struct
as page size can differ.
This replaces missing IOMMU_PAGE_SHIFT macro in commented debug code
as recently introduced IOMMU_PAGE_XXX macros do not include
IOMMU_PAGE_SHIFT.
Signed-off-by: Alexey Kardashevskiy
---
drivers/vfio/vfio_io
There are helpers to account locked pages in locked_vm counter, this
reuses these helpers in VFIO-SPAPR-IOMMU driver.
While we are here, update the comment explaining why RLIMIT_MEMLOCK
might be required to be bigger than entire guest RAM.
Signed-off-by: Alexey Kardashevskiy
---
Changes:
v4:
* a
This adds a iommu_table_ops struct and puts pointer to it into
the iommu_table struct. This moves tce_build/tce_free/tce_get/tce_flush
callbacks from ppc_md to the new struct where they really belong to.
This adds an extra @ops parameter to iommu_init_table() to make sure
that we do not leave any
At the moment writing new TCE value to the IOMMU table fails with EBUSY
if there is a valid entry already. However PAPR specification allows
the guest to write new TCE value without clearing it first.
This adds a set_and_get() callback to iommu_table_ops which does the same
thing as set() plus it
The previous patch introduced iommu_table_ops::set_and_get() callback
which effectively disabled VFIO on pseries. This implements set_and_get()
for pseries/lpar so VFIO can work under pHyp again.
Since set_and_get() callback must return old TCE, it has to do H_GET_TCE
for every TCE being replaced,
This adds missing locks in iommu_take_ownership()/
iommu_release_ownership().
This marks all pages busy in iommu_table::it_map in order to catch
errors if there is an attempt to use this table while ownership over it
is taken.
This only clears TCE content if there is no page marked busy in it_map
At the moment pnv_pci_ioda_tce_invalidate() gets the PE pointer via
container_of(tbl). Since we are going to have to add Dynamic DMA windows
and that means having 2 IOMMU tables per PE, this is not going to work.
This implements pnv_pci_ioda(1|2)_tce_invalidate as a pnv_ioda_pe callback.
This add
At the moment the iommu_table struct has a set_bypass() which enables/
disables DMA bypass on IODA2 PHB. This is exposed to POWERPC IOMMU code
which calls this callback when external IOMMU users such as VFIO are
about to get over a PHB.
Since the set_bypass() is not really an iommu_table function
There is a couple of commented debug prints which still use
IOMMU_PAGE_SHIFT() which is not defined for POWERPC anymore, replace
them with it_page_shift.
Signed-off-by: Alexey Kardashevskiy
Reviewed-by: Gavin Shan
---
arch/powerpc/kernel/iommu.c | 4 ++--
1 file changed, 2 insertions(+), 2 dele
At the moment pages used for TCE tables (not pages addressed by TCEs) are
not counter in locked_vm counter so a malicious userspace tool can
call ioctl(KVM_CREATE_SPAPR_TCE) as many times as RLIMIT_NOFILE and
lock a lot of memory.
This adds counting for pages used for TCE tables.
This counts the
This adds 2 helpers to change the locked_vm counter:
- try_increase_locked_vm - may fail if new locked_vm value will be greater
than the RLIMIT_MEMLOCK limit;
- decrease_locked_vm.
These will be used by drivers capable of locking memory by userspace
request. For example, VFIO can use it to check i
At the moment spapr_tce_tables is not protected against races. This makes
use of RCU-variants of list helpers. As some bits are executed in real
mode, this makes use of just introduced list_for_each_entry_rcu_notrace().
This converts release_spapr_tce_table() to a RCU scheduled handler.
Signed-of
This prepares existing upstream kernel for DDW (Dynamic DMA windows) and
adds actual DDW support for VFIO.
This patchset does not contain any in-kernel acceleration stuff.
This patchset does not enable DDW for emulated devices.
Changes:
v4:
* addressed Ben's comments
* big rework with moving tc
I am getting this crash on a Powerpc system using 3.16.0-rc7 kernel plus
some patches related to perf (24x7 counters) that Cody Schafer posted here:
https://lkml.org/lkml/2014/5/27/768
I don't get the crash on an unpatched kernel though.
I have been staring at the perf event patches, bu
32 matches
Mail list logo
