On 12/29/2015 06:28 PM, Stefan Weil wrote:
Am 29.12.2015 um 11:13 schrieb Cao jin:
merge three lines into one line
Signed-off-by: Cao jin
---
hw/xen/Makefile.objs | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/hw/xen/Makefile.objs b/hw/xen/Makefile.objs
index a9ad7
merge three lines into one line
Signed-off-by: Cao jin
---
hw/xen/Makefile.objs | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/hw/xen/Makefile.objs b/hw/xen/Makefile.objs
index a9ad7e7..77806f0 100644
--- a/hw/xen/Makefile.objs
+++ b/hw/xen/Makefile.objs
@@ -1,6 +1,4 @@
merge last two lines, keep alphabetic order.
Signed-off-by: Cao jin
---
hw/xen/Makefile.objs | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/hw/xen/Makefile.objs b/hw/xen/Makefile.objs
index a9ad7e7..d367094 100644
--- a/hw/xen/Makefile.objs
+++ b/hw/xen/Makefile.objs
@@ -2
flight 38573 distros-debian-squeeze real [real]
http://osstest.xs.citrite.net/~osstest/testlogs/logs/38573/
Perfect :-)
All tests in this flight passed
baseline version:
flight 38554
jobs:
build-amd64 pass
build-armhf
On 30/12/2015 02:16, Haozhong Zhang wrote:
On 12/30/15 09:35, Haozhong Zhang wrote:
On 12/29/15 15:46, Andrew Cooper wrote:
On 29/12/2015 11:31, Haozhong Zhang wrote:
Pass CPU features CLFLUSHOPT and CLWB into HVM domain so that those two
instructions can be used by guest.
The specification o
On 30/12/2015 01:39, Wen Congyang wrote:
Wen Congyang (5):
remus: don't call stream_continue() when doing failover
remus: don't write xenstore data if it fails
tools/libxc: don't send end record if remus fails
tools/libxl: remove unused function libxl__domain_save_device_model()
A
On 30/12/2015 01:39, Wen Congyang wrote:
stream_continue() is used for migration to read emulator
xenstore data and emulator context. For remus, if we do
failover, we have read it in the checkpoint cycle, and
we only need to complete the stream.
Signed-off-by: Wen Congyang
Reviewed-by: Andrew
On 30/12/2015 01:39, Wen Congyang wrote:
If what fails?
Given the content of this patch in the context of the previous one, I
presume you are wishing to avoid re-sending the emulator state after
libxl__xc_domain_save_done() completes, but under what circumstances
will this occur?
Signed-of
On 30/12/2015 05:25, Wen Congyang wrote:
On 12/30/2015 12:11 PM, Doug Goldstein wrote:
On 12/29/15 8:39 PM, Wen Congyang wrote:
We may use non-root user to run qemu, and the qemu needs to write
save file to /var/lib/xen. So we should allow all user to create
a file under the directory /var/lib/
On 30/12/2015 01:39, Wen Congyang wrote:
Signed-off-by: Wen Congyang
Reviewed-by: Andrew Cooper
While looking at this code, what about error handling for the postcopy()
callback just out of context?
---
tools/libxc/xc_sr_save.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
di
Pass CPU features CLFLUSHOPT and CLWB into HVM domain so that those two
instructions can be used by guest.
The specification of above two instructions can be found in
https://software.intel.com/sites/default/files/managed/0d/53/319433-022.pdf
Signed-off-by: Haozhong Zhang
---
tools/libxc/xc_cpu
Pass PCOMMIT CPU feature into HMV domain. Currently, we do not intercept
pcommit instruction for L1 guest, and allow L1 to intercept pcommit
instruction for L2 guest.
The specification of pcommit instruction can be found in
https://software.intel.com/sites/default/files/managed/0d/53/319433-022.pd
I split the previous patch series "[PATCH 0/4] add support for vNVDIMM"
into two parts. This is the first part that enables clflushopt/clwb/pcommit
instructions for HVM guests.
[The second part will be sent separately after v1 patches get reviewed.]
Changes in v2:
* Refactor modifications in hvm
On 30/12/2015 11:48, Haozhong Zhang wrote:
Pass CPU features CLFLUSHOPT and CLWB into HVM domain so that those two
instructions can be used by guest.
The specification of above two instructions can be found in
https://software.intel.com/sites/default/files/managed/0d/53/319433-022.pdf
Signed-of
On 30/12/2015 11:48, Haozhong Zhang wrote:
Pass PCOMMIT CPU feature into HMV domain. Currently, we do not intercept
pcommit instruction for L1 guest, and allow L1 to intercept pcommit
instruction for L2 guest.
The specification of pcommit instruction can be found in
https://software.intel.com/si
Hello!
We are going to use XenGT on Intel Atom based board(VTC-1010, with 4GB RAM).
For this purpose we use next repos:
xen - https://github.com/01org/Igvtg-xen
dom0 (ubuntu linux, 1024MB or 2048MB ) -
https://github.com/01org/Igvtg-kernel
domU (android-x86, rest memory excluding xen heap, xen, ab
drivers/xen/xenbus/xenbus_comms.c uses
full memory barriers to communicate with the other side.
For guests compiled with CONFIG_SMP, smp_wmb and smp_mb
would be sufficient, so mb() and wmb() here are only needed if
a non-SMP guest runs on an SMP host.
Switch to __smp_XXX barriers which serve this
include/xen/interface/io/ring.h uses
full memory barriers to communicate with the other side.
For guests compiled with CONFIG_SMP, smp_wmb and smp_mb
would be sufficient, so mb() and wmb() here are only needed if
a non-SMP guest runs on an SMP host.
Switch to __smp_XXX barriers which serve this e
On 12/30/2015 06:38 PM, Andrew Cooper wrote:
> On 30/12/2015 01:39, Wen Congyang wrote:
>>
>> Wen Congyang (5):
>>remus: don't call stream_continue() when doing failover
>>remus: don't write xenstore data if it fails
>>tools/libxc: don't send end record if remus fails
>>tools/libxl:
On 12/30/2015 07:11 PM, Andrew Cooper wrote:
> On 30/12/2015 01:39, Wen Congyang wrote:
>> Signed-off-by: Wen Congyang
>
> Reviewed-by: Andrew Cooper
>
> While looking at this code, what about error handling for the postcopy()
> callback just out of context?
We don't handle it now. IIRC, migr
What does Qemu log tell you about below error?
libxl: error: libxl_dm.c:1531:device_model_spawn_outcome: domain 1 device
model: spawn failed (rc=-3)
In the meantime, it’d be helpful if you can capture serial console output. If
error comes from XenGT driver, there should be some useful informat
On 12/30/2015 06:47 PM, Andrew Cooper wrote:
> On 30/12/2015 01:39, Wen Congyang wrote:
>
> If what fails?
>
> Given the content of this patch in the context of the previous one, I presume
> you are wishing to avoid re-sending the emulator state after
> libxl__xc_domain_save_done() completes, b
This patch adds several functions to take multiplication, division and
shifting involving 64-bit integers. Those functions are derived from
Linux kernel and will be used by later patches to calculate scaling
ratio and scaled TSC.
Signed-off-by: Haozhong Zhang
---
Changes in v3:
(addressing Boris
This patch implements a common function hvm_scale_tsc() to scale TSC by
using TSC scaling information collected by architecture code.
Signed-off-by: Haozhong Zhang
Reviewed-by: Kevin Tian (except the mul64 part)
---
Changes in v3:
(addressing Boris Ostrovsky's comments)
* Remove unnecessary as
Both VMX and SVM save/load vcpu's TSC when saving/loading vcpu's
context, so this patch moves saving/loading vcpu's TSC to the common
functions hvm_[save|load]_cpu_ctxt().
Signed-off-by: Haozhong Zhang
Acked-by: Jan Beulich
Acked-by: Kevin Tian
Reviewed-by: Boris Ostrovsky
---
xen/arch/x86/hv
This patchset adds support for VMX TSC scaling feature which is
available on Intel Skylake Server CPU. The specification of VMX TSC
scaling can be found at
http://www.intel.com/content/www/us/en/processors/timestamp-counter-scaling-virtualization-white-paper.html
VMX TSC scaling allows guest TSC w
This patch uses hvm_funcs.tsc_scaling_supported instead of the
architecture code to detect the TSC scaling support.
Signed-off-by: Haozhong Zhang
Acked-by: Jan Beulich
Reviewed-by: Kevin Tian
Reviewed-by: Boris Ostrovsky
---
xen/arch/x86/time.c | 5 ++---
1 file changed, 2 insertions(+), 3 de
This patch makes the pvclock return the scaled host TSC and
corresponding scaling parameters to HVM domains if guest TSC is not
emulated and TSC scaling is enabled.
Signed-off-by: Haozhong Zhang
---
Changes in v3:
(addressing Boris Ostrovsky's comments)
* No changes in fact. tsc_set_info() does
Now every caller passes an already scaled offset to
svm_set_tsc_offset(), so it's not necessary to recalculate a scaled TSC
offset in svm_set_tsc_offset().
Signed-off-by: Haozhong Zhang
Reviewed-by: Boris Ostrovsky
---
Changes in v3:
(addressing Boris Ostrovsky's comments)
* Move declaration o
Both VMX TSC scaling and SVM TSC ratio use the 64-bit TSC scaling ratio,
but the number of fractional bits of the ratio is different between VMX
and SVM. This patch adds the architecture code to collect the number of
fractional bits and other related information into fields of struct
hvm_function_t
The existing hvm_[set|get]_guest_tsc_fixed() calculate the guest TSC by
adding the TSC offset to the host TSC. When the TSC scaling is enabled,
the host TSC should be scaled first. This patch adds the scaling logic
to those two functions.
Reviewed-by: Boris Ostrovsky
Signed-off-by: Haozhong Zhang
When TSC_MODE_PVRDTSCP is used for a HVM container and TSC scaling is
available, use the non-zero value of argument gtsc_khz of tsc_set_info()
as the guest TSC frequency rather than using the host TSC
frequency. Otherwise, TSC scaling will not be able get the correct ratio
between the host and gues
This patch adds a field tsc_scaling_ratio in struct hvm_vcpu to
record the TSC scaling ratio, and sets it up when tsc_set_info() is
called for a vcpu or when a vcpu is restored or reset.
Before applying the TSC scaling ratio to CPU, we check its validity in
tsc_set_info(). If an invalid ratio is g
When the TSC mode of a HVM container is TSC_MODE_DEFAULT or
TSC_MODE_PVRDTSCP and no TSC emulation is used, the existing
tsc_get_info() uses the host TSC frequency (cpu_khz) as the guest TSC
frequency. However, tsc_set_info() may set the guest TSC frequency to a
value different than the host. In or
Signed-off-by: Haozhong Zhang
---
Changes in v3:
(addressing Kevin Tian's comments)
* Reorganize words to address Kevin's comments.
docs/man/xl.cfg.pod.5 | 14 +-
docs/misc/tscmode.txt | 21 +
2 files changed, 34 insertions(+), 1 deletion(-)
diff --git a/docs/m
This patch adds the initialization and setup code for VMX TSC scaling.
Signed-off-by: Haozhong Zhang
Acked-by: Kevin Tian
---
xen/arch/x86/hvm/vmx/vmcs.c| 12 +---
xen/arch/x86/hvm/vmx/vmx.c | 15 +++
xen/include/asm-x86/hvm/vmx/vmcs.h | 7 +++
3 files c
On 2015/11/27 22:30, Stefano Stabellini wrote:
> On Tue, 17 Nov 2015, shannon.z...@linaro.org wrote:
>> > From: Shannon Zhao
>> >
>> > Create a few EFI memory descriptors to tell Dom0 the RAM region
>> > information, ACPI table regions and EFI tables reserved resions.
>> >
>> > Signed-off-by:
37 matches
Mail list logo
