>>> On 24.04.15 at 00:20, wrote:
> On 04/21/2015 03:01 AM, Jan Beulich wrote:
>>
>>> + ((++dev_cnt > 0x3f) && hypercall_preempt_check()) )
>>> +break;
>>> +}
>>> +
>>> +if ( (!ret || (ret == -ENODEV)) &&
>>> + __copy_field_to_guest(u_sysc
>>> On 24.04.15 at 03:17, wrote:
> On 2015/4/23 20:59, Jan Beulich wrote:
> On 23.04.15 at 14:32, wrote:
>>> But if you already have one just please ignore this and tell me
>>
>> Here's what I currently have:
>
> Could you resend me this as an attached file? Then I can apply that
> properly
>>> On 24.04.15 at 07:12, wrote:
> On 23/04/2015 22:09, Jan Beulich wrote:
>> >>> On 23.04.16 at 15:31, wrote:
>> > The intel_pstate.c file under xen/arch/x86/acpi/cpufreq/ contains all
>> > the logic for selecting the current P-state. It follows its
>> > implementation in the kernel. Instead of
>>> On 24.04.15 at 08:32, wrote:
> On 04/17/2015 03:37 PM, Jan Beulich wrote:
> On 17.04.15 at 09:23, wrote:
>>> I see. I will do as you suggested:
>>>
>>> ASSERT((v == current) || (!vcpu_runnable(v) && !v->is_running));
>>>
>>> And v != current should be the only case requires the vcpu to be
On 04/24/2015 03:30 PM, Jan Beulich wrote:
On 24.04.15 at 08:32, wrote:
On 04/17/2015 03:37 PM, Jan Beulich wrote:
On 17.04.15 at 09:23, wrote:
I see. I will do as you suggested:
ASSERT((v == current) || (!vcpu_runnable(v) && !v->is_running));
And v != current should be the only case req
>>> On 23.04.15 at 17:46, wrote:
> --- a/xen/arch/x86/hvm/hvm.c
> +++ b/xen/arch/x86/hvm/hvm.c
> @@ -496,7 +496,7 @@ static void hvm_free_ioreq_gmfn(struct domain *d,
> unsigned long gmfn)
> {
> unsigned int i = gmfn - d->arch.hvm_domain.ioreq_gmfn.base;
>
> -clear_bit(i, &d->arch.hvm
We need to flush PML buffer when it's full.
Signed-off-by: Kai Huang
---
xen/arch/x86/hvm/vmx/vmx.c | 4
1 file changed, 4 insertions(+)
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 6c4f78c..f11ac46 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hv
This patch firstly enables EPT A/D bits if PML is used, as PML depends on EPT
A/D bits to work. A bit is set for all present p2m types in middle and leaf EPT
entries, and D bit is set for all writable types in EPT leaf entry, except for
log-dirty type with PML.
With PML, for 4K pages, instead of s
A new 4K page pointer is added to arch_vmx_struct as PML buffer for vcpu. And a
new 'status' field is added to vmx_domain to indicate whether PML is enabled for
the domain or not.
Signed-off-by: Kai Huang
---
xen/include/asm-x86/hvm/vmx/vmcs.h | 8
1 file changed, 8 insertions(+)
diff
PML logs GPA in PML buffer. Original paging_mark_dirty takes MFN as parameter
but it gets guest pfn internally and use guest pfn to as index for looking up
radix log-dirty tree. In flushing PML buffer, calling paging_mark_dirty directly
introduces redundant p2m lookups (gfn->mfn->gfn), therefore we
Using PML, it's possible there are dirty GPAs logged in vcpus' PML buffers
when userspace peek/clear dirty pages, therefore we need to flush them befor
reporting dirty pages to userspace. This applies to both video ram tracking and
paging_log_dirty_op.
This patch adds new p2m layer functions to en
A top level EPT parameter "ept=" and a sub boolean "opt_pml_enabled"
are added to control PML. Other booleans can be further added for any other EPT
related features.
The document description for the new parameter is also added.
Signed-off-by: Kai Huang
---
docs/misc/xen-command-line.markdown |
The patch adds PML definition and feature detection. Note PML won't be detected
if PML is disabled from boot parameter. PML is also disabled in construct_vmcs,
as it will only be enabled when domain is switched to log dirty mode.
Signed-off-by: Kai Huang
---
xen/arch/x86/hvm/vmx/vmcs.c|
It's possible domain still remains in log-dirty mode when it is about to be
destroyed, in which case we should manually disable PML for it.
Signed-off-by: Kai Huang
---
xen/arch/x86/hvm/vmx/vmx.c | 8
1 file changed, 8 insertions(+)
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x8
v2->v3:
- Merged v2 patch 02 (document change) to patch 01 as a single patch, and
changed new parameter description as suggested by Andrew.
- changed vmx_vcpu_flush_pml_buffer to call mark_dirty for all logged GFNs, and
call p2m_change_type_one regardless of return value.
- Added ASSERT for vc
It's possible domain has already been in log-dirty mode when creating vcpu, in
which case we should enable PML for this vcpu if PML has been enabled for the
domain.
Signed-off-by: Kai Huang
---
xen/arch/x86/hvm/vmx/vmx.c | 23 +++
1 file changed, 23 insertions(+)
diff --git
This patch adds help functions to enable/disable PML, and flush PML buffer for
single vcpu and particular domain for further use.
Signed-off-by: Kai Huang
---
xen/arch/x86/hvm/vmx/vmcs.c| 179 +
xen/include/asm-x86/hvm/vmx/vmcs.h | 9 ++
2 files chan
On 23/04/2015 15:27, Jan Beulich wrote:
> >>> On 24.04.15 at 07:12, wrote:
> > On 23/04/2015 22:09, Jan Beulich wrote:
> >> >>> On 23.04.16 at 15:31, wrote:
> >> > The intel_pstate.c file under xen/arch/x86/acpi/cpufreq/ contains
> >> > all the logic for selecting the current P-state. It follows
> -Original Message-
> From: Ian Campbell [mailto:ian.campb...@citrix.com]
> Sent: Thursday, April 23, 2015 7:30 PM
> To: Hu, Robert
> Cc: Pang, LongtaoX; xen-devel@lists.xen.org; ian.jack...@eu.citrix.com;
> wei.l...@citrix.com
> Subject: Re: [OSSTEST Nested PATCH v8 5/7] Add new script
On Fri, Mar 20, Wei Liu wrote:
> +++ b/tools/libxl/libxl_dm.c
> @@ -1438,6 +1438,8 @@ retry_transaction:
>
> spawn->what = GCSPRINTF("domain %d device model", domid);
> spawn->xspath = GCSPRINTF("/local/domain/0/device-model/%d/state",
> domid);
> +spawn->xspath = libxl__device_mo
On Fri, Apr 24, 2015 at 10:49:36AM +0200, Olaf Hering wrote:
> On Fri, Mar 20, Wei Liu wrote:
>
> > +++ b/tools/libxl/libxl_dm.c
> > @@ -1438,6 +1438,8 @@ retry_transaction:
> >
> > spawn->what = GCSPRINTF("domain %d device model", domid);
> > spawn->xspath = GCSPRINTF("/local/domain/0
Reported-by: Olaf Hering
Signed-off-by: Wei Liu
Cc: Ian Campbell
Cc: Ian Jackson
---
tools/libxl/libxl_dm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/tools/libxl/libxl_dm.c b/tools/libxl/libxl_dm.c
index 30c1578..a1011e3 100644
--- a/tools/libxl/libxl_dm.c
+++ b/tools/libxl/libxl_dm.c
Prior to 1a09c5113a ("libxlu: rework internal representation of
setting") empty lists in config files did get accepted. Restore that
behavior.
Signed-off-by: Jan Beulich
--- a/tools/libxl/libxlu_cfg.c
+++ b/tools/libxl/libxlu_cfg.c
@@ -397,7 +397,7 @@ XLU_ConfigValue *xlu__cfg_list_mk(CfgPar
Convert all plain ints and strings which are used for xenbus "state"
files to xenbus_state. This makes it easier to find code which deals
with backend/frontend state changes.
Convert usage of libxl__sprintf to GCSPRINTF.
No change in behaviour is expected by this change, beside a small
increase o
On 23/04/15 17:11, Jan Beulich wrote:
On 22.04.15 at 18:00, wrote:
>> static inline int
>> get_maptrack_handle(
>> struct grant_table *lgt)
>> {
>> +struct vcpu *v = current;
>> int i;
>> grant_handle_thandle;
>> struct grant_mappi
>>> On 24.04.15 at 10:32, wrote:
> On 23/04/2015 15:27, Jan Beulich wrote:
>> >>> On 24.04.15 at 07:12, wrote:
>> > On 23/04/2015 22:09, Jan Beulich wrote:
>> >> >>> On 23.04.16 at 15:31, wrote:
>> >> > The intel_pstate.c file under xen/arch/x86/acpi/cpufreq/ contains
>> >> > all the logic for s
On Fri, Apr 24, Olaf Hering wrote:
> flexarray_append(back, "state");
> -flexarray_append(back, GCSPRINTF("%d", 1));
> +flexarray_append(back, GCSPRINTF("%d", XenbusStateInitialising));
Should all such code be converted to flexarray_append_pair?
To reduce line length a short macro sh
On Fri, Apr 24, 2015 at 09:07:14AM +, Olaf Hering wrote:
> Convert all plain ints and strings which are used for xenbus "state"
> files to xenbus_state. This makes it easier to find code which deals
> with backend/frontend state changes.
>
> Convert usage of libxl__sprintf to GCSPRINTF.
>
> N
Make sure that xen_swiotlb_init allocates buffers that are DMA capable
when at least one memblock is available below 4G. Otherwise we assume
that all devices on the SoC can cope with >4G addresses. We do this on
ARM and ARM64, where dom0 is mapped 1:1, so pfn == mfn in this case.
No functional cha
On Fri, Apr 24, 2015 at 10:04:31AM +0100, Jan Beulich wrote:
> Prior to 1a09c5113a ("libxlu: rework internal representation of
> setting") empty lists in config files did get accepted. Restore that
> behavior.
>
> Signed-off-by: Jan Beulich
>
Thanks for the fix.
Acked-by: Wei Liu
___
On Fri, Apr 24, 2015 at 11:16:00AM +0200, Olaf Hering wrote:
> On Fri, Apr 24, Olaf Hering wrote:
>
> > flexarray_append(back, "state");
> > -flexarray_append(back, GCSPRINTF("%d", 1));
> > +flexarray_append(back, GCSPRINTF("%d", XenbusStateInitialising));
>
> Should all such code be
> -Original Message-
> From: Jan Beulich [mailto:jbeul...@suse.com]
> Sent: 24 April 2015 09:01
> To: Paul Durrant
> Cc: Andrew Cooper; xen-de...@lists.xenproject.org; Keir (Xen.org)
> Subject: Re: [PATCH 1/2] x86/hvm: actually release ioreq server pages
>
> >>> On 23.04.15 at 17:46, wrot
On 24/04/2015 17:11, Jan Beulich wrote:
> >>> On 24.04.15 at 10:32, wrote:
> > On 23/04/2015 15:27, Jan Beulich wrote:
> >> >>> On 24.04.15 at 07:12, wrote:
> >> > On 23/04/2015 22:09, Jan Beulich wrote:
> >> >> >>> On 23.04.16 at 15:31, wrote:
> >> >> > The intel_pstate.c file under xen/arch/x8
>>> On 24.04.15 at 11:09, wrote:
> On 23/04/15 17:11, Jan Beulich wrote:
> On 22.04.15 at 18:00, wrote:
>>> --- a/xen/include/xen/grant_table.h
>>> +++ b/xen/include/xen/grant_table.h
>>> @@ -60,6 +60,8 @@ struct grant_mapping {
>>> u32 ref; /* grant ref */
>>> u16
>>> On 24.04.15 at 11:46, wrote:
> On 24/04/2015 17:11, Jan Beulich wrote:
>> >>> On 24.04.15 at 10:32, wrote:
>> > In the old driver, a powersave governor just sets the CPU to run with
>> > the lowest possible performance state. This one does not exist in the
>> > intel_pstate driver.
>> > The i
On 24/04/15 10:50, Jan Beulich wrote:
On 24.04.15 at 11:09, wrote:
>> On 23/04/15 17:11, Jan Beulich wrote:
>> On 22.04.15 at 18:00, wrote:
--- a/xen/include/xen/grant_table.h
+++ b/xen/include/xen/grant_table.h
@@ -60,6 +60,8 @@ struct grant_mapping {
u32 r
flight 52054 rumpuserxen real [real]
http://logs.test-lab.xenproject.org/osstest/logs/52054/
Regressions :-(
Tests which did not succeed and are blocking,
including tests which could not be run:
build-amd64-rumpuserxen 5 rumpuserxen-build fail REGR. vs. 33866
build-i386-rumpuserxe
On 24/04/2015 17:56, Jan Beulich wrote:
> >>> On 24.04.15 at 11:46, wrote:
> > On 24/04/2015 17:11, Jan Beulich wrote:
> >> >>> On 24.04.15 at 10:32, wrote:
> >> > In the old driver, a powersave governor just sets the CPU to run
> >> > with the lowest possible performance state. This one does not
Signed-off-by: Wei Liu
Cc: Ian Campbell
Cc: Ian Jackson
---
standalone | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/standalone b/standalone
index d8113e4..17fa40c 100755
--- a/standalone
+++ b/standalone
@@ -41,7 +41,7 @@ Options:
-f FLIGHT, --flight=FLIGHTOperate on
>>> On 24.04.15 at 12:07, wrote:
> On 24/04/2015 17:56, Jan Beulich wrote:
>> >>> On 24.04.15 at 11:46, wrote:
>> > On 24/04/2015 17:11, Jan Beulich wrote:
>> >> >>> On 24.04.15 at 10:32, wrote:
>> >> > In the old driver, a powersave governor just sets the CPU to run
>> >> > with the lowest poss
On 24/04/15 10:50, Jan Beulich wrote:
On 24.04.15 at 11:09, wrote:
>> On 23/04/15 17:11, Jan Beulich wrote:
>> On 22.04.15 at 18:00, wrote:
--- a/xen/include/xen/grant_table.h
+++ b/xen/include/xen/grant_table.h
@@ -60,6 +60,8 @@ struct grant_mapping {
u32 r
The result of this command:
git grep -wnl BINDIR | xargs sed -i 's@BINDIR@bindir@g'
Signed-off-by: Olaf Hering
Cc: Ian Jackson
Cc: Stefano Stabellini
Cc: Ian Campbell
Cc: Wei Liu
Cc: George Dunlap
---
Config.mk| 2 +-
config/Paths.mk.in
Replace all private variables in Makefiles with automake variables.
This series is based on 92ff75384bce7a11e27fbfaf0c531e88dd1ab4c7.
Olaf
Olaf Hering (7):
tools: replace private SBINDIR with automake sbindir
tools: replace private BINDIR with automake bindir
tools: replace private PREFIX w
The result of this command:
git grep -wnl INCLUDEDIR | xargs sed -i 's@INCLUDEDIR@includedir@g'
Signed-off-by: Olaf Hering
Cc: Ian Jackson
Cc: Stefano Stabellini
Cc: Ian Campbell
Cc: Wei Liu
---
config/Paths.mk.in| 1 -
tools/Makefile| 14 +++---
The result of this command:
git grep -wnl MANDIR | xargs sed -i 's@MANDIR@mandir@g'
Signed-off-by: Olaf Hering
Cc: Ian Jackson
Cc: Stefano Stabellini
Cc: Ian Campbell
Cc: Wei Liu
---
config/Paths.mk.in | 5 ++---
docs/Makefile | 6 +++---
2 files changed, 5 insertions(+), 6 deletions(-
The result of this command:
git grep -wnl LIBDIR | xargs sed -i 's@LIBDIR@libdir@g'
Signed-off-by: Olaf Hering
Cc: Ian Jackson
Cc: Stefano Stabellini
Cc: Ian Campbell
Cc: Wei Liu
---
Config.mk| 4 ++--
config/Paths.mk.in | 1 -
The result of this command:
git grep -wnl DOCDIR | xargs sed -i 's@DOCDIR@docdir@g'
Signed-off-by: Olaf Hering
Cc: Ian Jackson
Cc: Stefano Stabellini
Cc: Ian Campbell
Cc: Wei Liu
Cc: Samuel Thibault
---
config/Paths.mk.in| 1 -
docs/Makefile | 4 ++--
stubdom/Makefile | 4
Only qemu-traditional expects PREFIX in environment, which is provided
by buildmakevars2shellvars.
Signed-off-by: Olaf Hering
Cc: Ian Jackson
Cc: Stefano Stabellini
Cc: Ian Campbell
Cc: Wei Liu
---
Config.mk | 6 +++---
config/Paths.mk.in | 2 --
2 files changed, 3 insertions(+), 5
The result of this command:
git grep -wnl SBINDIR | xargs sed -i 's@SBINDIR@sbindir@g'
Signed-off-by: Olaf Hering
Cc: Ian Jackson
Cc: Stefano Stabellini
Cc: Ian Campbell
Cc: Wei Liu
Cc: Mukesh Rathor
Cc: Tim Deegan
Cc: Daniel De Graaf
Cc: David Scott
---
Config.mk
On 24/04/15 11:25, Olaf Hering wrote:
> The result of this command:
> git grep -wnl MANDIR | xargs sed -i 's@MANDIR@mandir@g'
>
> Signed-off-by: Olaf Hering
> Cc: Ian Jackson
> Cc: Stefano Stabellini
> Cc: Ian Campbell
> Cc: Wei Liu
In some copious free time during a docs day, we should see
On 24/04/15 09:19, Kai Huang wrote:
> A top level EPT parameter "ept=" and a sub boolean "opt_pml_enabled"
> are added to control PML. Other booleans can be further added for any other
> EPT
> related features.
>
> The document description for the new parameter is also added.
>
> Signed-off-by: Ka
In old X-Gene Storm firmware and DT, secure mode addresses have been
mentioned in GICv2 node. In this case maintenance interrupt is used
instead of EOI HW method.
This patch checks the GIC Distributor Base Address to enable EOI quirk
for old firmware.
Ref:
http://lists.xen.org/archives/html/xen-d
Hello,
I'm a student in computer science, during my internship i have to go
and explore multipathing solution for several hypervisor.
I'm looking into MPTCP (multi-path TCP) this is a extension of TCP
protocols that allows to aggregate the bandwith of several connection.
I'd like tu use MPTCP to a
On 24/04/2015 18:20, Jan Beulich wrote
> >>> On 24.04.15 at 12:07, wrote:
> > On 24/04/2015 17:56, Jan Beulich wrote:
> >> >>> On 24.04.15 at 11:46, wrote:
> >> > On 24/04/2015 17:11, Jan Beulich wrote:
> >> >> >>> On 24.04.15 at 10:32, wrote:
> >> >> I think at the very least from a user interf
Hi,
On Xen-unstable I encountered this non stopping logspam while trying to
shutdown an HVM domain with
pci-passthrough:
(XEN) [2015-04-24 11:55:47.802] io.c:164:d25v0 Weird HVM ioemulation status 1.
(XEN) [2015-04-24 11:55:47.802] domain_crash called from io.c:165
(XEN) [2015-04-24 11:55:47.8
On Fri, Apr 24, Sander Eikelenboom wrote:
> (XEN) [2015-04-24 11:55:47.802] domain_crash called from io.c:165
> Since i haven't seen it before, it's probably hard to replicate.
I see it all time on my beloved ProBook. With an ordinary domU.cfg.
name="fv-13.1-pvscsi"
uuid="4ff34139-8381-4f3b-8c3
>>> On 24.04.15 at 12:21, wrote:
> On 24/04/15 10:50, Jan Beulich wrote:
> On 24.04.15 at 11:09, wrote:
>>> On 23/04/15 17:11, Jan Beulich wrote:
>>> On 22.04.15 at 18:00, wrote:
> --- a/xen/include/xen/grant_table.h
> +++ b/xen/include/xen/grant_table.h
> @@ -60,6 +60,8 @@ s
>>> On 24.04.15 at 13:53, wrote:
> On 24/04/2015 18:20, Jan Beulich wrote
>> >>> On 24.04.15 at 12:07, wrote:
>> > On 24/04/2015 17:56, Jan Beulich wrote:
>> >> >>> On 24.04.15 at 11:46, wrote:
>> >> > On 24/04/2015 17:11, Jan Beulich wrote:
>> >> >> >>> On 24.04.15 at 10:32, wrote:
>> >> >> I
On Fri, Apr 24, 2015 at 10:16:40AM +0100, Stefano Stabellini wrote:
> Make sure that xen_swiotlb_init allocates buffers that are DMA capable
> when at least one memblock is available below 4G. Otherwise we assume
> that all devices on the SoC can cope with >4G addresses. We do this on
> ARM and ARM
On Fri, Apr 24, 2015 at 02:02:36PM +0200, Sander Eikelenboom wrote:
> Hi,
>
> On Xen-unstable I encountered this non stopping logspam while trying to
> shutdown an HVM domain with
> pci-passthrough:
>
> (XEN) [2015-04-24 11:55:47.802] io.c:164:d25v0 Weird HVM ioemulation status 1.
> (XEN) [201
Friday, April 24, 2015, 12:12:32 AM, you wrote:
> On 4/23/15, 12:59, "Sander Eikelenboom" wrote:
>>
>>> On 4/23/15, 08:47, "Jan Beulich" wrote:
>>
>>> On 23.04.15 at 15:31, wrote:
>
> On 4/17/15, 10:27, "Jan Beulich" wrote:
>
>>1aeb1156fa ("x86 don't change affin
On 04/24/2015 03:19 AM, Jan Beulich wrote:
On 24.04.15 at 00:20, wrote:
On 04/21/2015 03:01 AM, Jan Beulich wrote:
+ ((++dev_cnt > 0x3f) && hypercall_preempt_check()) )
+break;
+}
+
+if ( (!ret || (ret == -ENODEV)) &&
+ __copy_field_
>>> On 24.04.15 at 16:05, wrote:
> I see you commited "AMD IOMMU: only translate remapped IO-APIC RTEs" to
> staging,
> any reason why your patch in
> http://lists.xen.org/archives/html/xen-devel/2015-04/msg02253.html
> isn't commited yet ?
>
> (still waiting for an formal ack from someone ? a
Friday, April 24, 2015, 4:12:42 PM, you wrote:
On 24.04.15 at 16:05, wrote:
>> I see you commited "AMD IOMMU: only translate remapped IO-APIC RTEs" to
>> staging,
>> any reason why your patch in
>> http://lists.xen.org/archives/html/xen-devel/2015-04/msg02253.html
>> isn't commited yet ?
Xen L4 entries being uniformly installed into any L4 table and 64-bit
PV kernels running in ring 3 means that user mode was able to see the
read-only M2P presented by Xen to the guests. While apparently not
really representing an exploitable information leak, this still very
certainly was never mea
>>> On 24.04.15 at 10:19, wrote:
> --- a/xen/arch/x86/hvm/vmx/vmcs.c
> +++ b/xen/arch/x86/hvm/vmx/vmcs.c
> @@ -64,6 +64,36 @@ integer_param("ple_gap", ple_gap);
> static unsigned int __read_mostly ple_window = 4096;
> integer_param("ple_window", ple_window);
>
> +static bool_t __read_mostly op
On Fri, 24 Apr 2015, Konrad Rzeszutek Wilk wrote:
> On Fri, Apr 24, 2015 at 10:16:40AM +0100, Stefano Stabellini wrote:
> > Make sure that xen_swiotlb_init allocates buffers that are DMA capable
> > when at least one memblock is available below 4G. Otherwise we assume
> > that all devices on the So
>>> On 23.04.15 at 11:55, wrote:
> @@ -301,6 +304,8 @@ static void set_cpu_sibling_map(int cpu)
> }
> }
> }
> +
> +cpumask_set_cpu(cpu, &socket_to_cpumask[cpu_to_socket(cpu)]);
> }
There is an early return path in this function, which you need to
deal with.
> @@ -
On 24/04/2015 20:57, Jan Beulich wrote
> >>> On 24.04.15 at 13:53, wrote:
> > On 24/04/2015 18:20, Jan Beulich wrote
> >> >>> On 24.04.15 at 12:07, wrote:
> >> > On 24/04/2015 17:56, Jan Beulich wrote:
> >> >> >>> On 24.04.15 at 11:46, wrote:
> >> >> > On 24/04/2015 17:11, Jan Beulich wrote:
> >
On 24/04/15 15:31, Jan Beulich wrote:
> Xen L4 entries being uniformly installed into any L4 table and 64-bit
> PV kernels running in ring 3 means that user mode was able to see the
> read-only M2P presented by Xen to the guests. While apparently not
> really representing an exploitable information
>>> On 23.04.15 at 11:55, wrote:
> struct psr_cmt *__read_mostly psr_cmt;
> +
> +static unsigned long __read_mostly * cat_socket_init_bitmap;
> +static unsigned long __read_mostly * cat_socket_enable_bitmap;
> +static struct psr_cat_socket_info *__read_mostly cat_socket_info;
So the last line lo
>>> On 24.04.15 at 16:56, wrote:
> On 24/04/2015 20:57, Jan Beulich wrote
>> I'm not sure how else to express what I want (no matter how many internal
>> governors the intel_pstate driver has).
>>
>> xenpm set-scaling-governor powersave
>> xenpm set-scaling-governor ondemand
>> xenpm set-scaling-
>>> On 24.04.15 at 16:57, wrote:
> On 24/04/15 15:31, Jan Beulich wrote:
>> Xen L4 entries being uniformly installed into any L4 table and 64-bit
>> PV kernels running in ring 3 means that user mode was able to see the
>> read-only M2P presented by Xen to the guests. While apparently not
>> really
>>> On 23.04.15 at 11:55, wrote:
> --- a/xen/arch/x86/sysctl.c
> +++ b/xen/arch/x86/sysctl.c
> @@ -171,6 +171,24 @@ long arch_do_sysctl(
>
> break;
>
> +case XEN_SYSCTL_psr_cat_op:
> +switch ( sysctl->u.psr_cat_op.cmd )
> +{
> +case XEN_SYSCTL_PSR_CAT_get_l
> On 22 Apr 2015, at 14:04, Ian Jackson wrote:
>
> Lars Kurth writes ("Re: Archiving Xen on ARM and PVOPS subprojects"):
>> Any other votes by committers (in the TO list) before I tally the votes?
>
> +1 to both.
We had several +1's and no -1's. So this vote carries
Lars
>>> On 23.04.15 at 11:55, wrote:
> +int psr_set_l3_cbm(struct domain *d, unsigned int socket, uint64_t cbm)
> +{
> +unsigned int old_cos, cos;
> +struct psr_cat_cbm *map, *find;
I think the variable would better be named found and ...
> +struct psr_cat_socket_info *info;
> +int r
>>> On 23.04.15 at 11:55, wrote:
> Changes in v5:
> * Add spin_lock to protect cbm_map.
> * Add spin_lock to read path aswell.
I don't think the second bullet point is true - there's only a single
spin_lock() invocation being added here afaics.
Jan
_
>>> On 23.04.15 at 11:55, wrote:
> On context switch, write the the domain's Class of Service(COS) to MSR
> IA32_PQR_ASSOC, to notify hardware to use the new COS.
>
> For performance reason, the COS mask for current cpu is also cached in
> the local per-CPU variable.
>
> Signed-off-by: Chao Peng
On 24/04/15 12:26, Benoit L'hoest wrote:
Hello,
I'm a student in computer science, during my internship i have to go
and explore multipathing solution for several hypervisor.
I'm looking into MPTCP (multi-path TCP) this is a extension of TCP
protocols that allows to aggregate the bandwith of sev
On 24/04/2015 23:04, Jan Beulich wrote
> >>> On 24.04.15 at 16:56, wrote:
> > On 24/04/2015 20:57, Jan Beulich wrote
> >> I'm not sure how else to express what I want (no matter how many
> >> internal governors the intel_pstate driver has).
> >>
> >> xenpm set-scaling-governor powersave
> >> xenpm
Signed-off-by: Stefano Stabellini
---
ap-common |5 +++
mfi-common | 19 ++
sg-run-job |5 +++
ts-raisin-build | 104 +++
4 files changed, 133 insertions(+)
create mode 100755 ts-raisin-build
diff --git a/ap-
>>> On 24.04.15 at 17:42, wrote:
> On 24/04/2015 23:04, Jan Beulich wrote
>> >>> On 24.04.15 at 16:56, wrote:
>> > On 24/04/2015 20:57, Jan Beulich wrote
>> >> I'm not sure how else to express what I want (no matter how many
>> >> internal governors the intel_pstate driver has).
>> >>
>> >> xenpm
On 24/04/15 16:07, Jan Beulich wrote:
On 24.04.15 at 16:57, wrote:
>> On 24/04/15 15:31, Jan Beulich wrote:
>>> Xen L4 entries being uniformly installed into any L4 table and 64-bit
>>> PV kernels running in ring 3 means that user mode was able to see the
>>> read-only M2P presented by Xen to
Rearrange code so that the local variable is always initialized and
disposed.
Signed-off-by: Olaf Hering
Cc: Jim Fehlig
---
src/libxl/libxl_driver.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/src/libxl/libxl_driver.c b/src/libxl/libxl_driver.c
index 393f8bd.
>>> On 24.04.15 at 17:54, wrote:
> On 24/04/15 16:07, Jan Beulich wrote:
> On 24.04.15 at 16:57, wrote:
>>> On 24/04/15 15:31, Jan Beulich wrote:
Xen L4 entries being uniformly installed into any L4 table and 64-bit
PV kernels running in ring 3 means that user mode was able to see t
Both attach and detach functions get called only if the type matches.
Signed-off-by: Olaf Hering
Cc: Jim Fehlig
---
src/libxl/libxl_driver.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/src/libxl/libxl_driver.c b/src/libxl/libxl_driver.c
index d76efda..f915f91 100644
--- a/src/libxl
On Fri, Apr 24, 2015 at 03:31:53PM +0100, Stefano Stabellini wrote:
> On Fri, 24 Apr 2015, Konrad Rzeszutek Wilk wrote:
> > On Fri, Apr 24, 2015 at 10:16:40AM +0100, Stefano Stabellini wrote:
> > > Make sure that xen_swiotlb_init allocates buffers that are DMA capable
> > > when at least one memblo
On Fri, Apr 24, 2015 at 03:42:40PM +, Wang, Wei W wrote:
> On 24/04/2015 23:04, Jan Beulich wrote
> > >>> On 24.04.15 at 16:56, wrote:
> > > On 24/04/2015 20:57, Jan Beulich wrote
> > >> I'm not sure how else to express what I want (no matter how many
> > >> internal governors the intel_pstate
On 24/04/2015 23:54, Jan Beulich wrote
> >>> On 24.04.15 at 17:42, wrote:
> > On 24/04/2015 23:04, Jan Beulich wrote
> >> >>> On 24.04.15 at 16:56, wrote:
> >> > On 24/04/2015 20:57, Jan Beulich wrote
> >> >> I'm not sure how else to express what I want (no matter how many
> >> >> internal govern
A guest has no need to touch these parameters and reading
HVM_PARAM_IOREQ_PFN, HVM_PARAM_BUFIOREQ_PFN, or HVM_PARAM_BUFIOREQ_EVTCHN
may cause Xen to create a default ioreq server where one did not already
exist.
Signed-off-by: Paul Durrant
Cc: Keir Fraser
Cc: Jan Beulich
Cc: Andrew Cooper
---
The following 3 patches re-structure the code implementing HVMOP_set_param
and HVMOP_get_param.
Patch #1 gives each operation its own function
Patch #2 splits out checks for getting/setting non-reflexive params and
setting params with change-once semantics, as well as the XSM check into
separate
The subject line should obviously be prefixed [PATCH 0/3], but the content is
at least correct.
Apologies for that,
Paul
> -Original Message-
> From: Paul Durrant [mailto:paul.durr...@citrix.com]
> Sent: 24 April 2015 17:21
> To: xen-de...@lists.xenproject.org
> Cc: Paul Durrant
> Sub
On 25/04/2015 00:15, Konrad Rzeszutek Wilk wrote
> On Fri, Apr 24, 2015 at 03:42:40PM +, Wang, Wei W wrote:
> > On 24/04/2015 23:04, Jan Beulich wrote
> > > >>> On 24.04.15 at 16:56, wrote:
> > > > On 24/04/2015 20:57, Jan Beulich wrote
> > > >> I'm not sure how else to express what I want (n
The level of switch nesting in those ops is getting unreadable. Giving
them their own functions does introduce some code duplication in the
the pre-op checks but the overall result is easier to follow.
This patch is code movement. There is no functional change.
Signed-off-by: Paul Durrant
Cc: Ke
Some parameters can only (validly) be set once. Some cannot be set
by a guest for its own domain. Consolidate these checks, along with
the XSM check, in a new hvm_allow_set_param() function for clarity.
Also, introduce hvm_allow_get_param() for similar reasons.
Signed-off-by: Paul Durrant
Cc: Ke
> On 24 Apr 2015, at 16:22, Lars Kurth wrote:
>
>
>> On 22 Apr 2015, at 14:04, Ian Jackson wrote:
>>
>> Lars Kurth writes ("Re: Archiving Xen on ARM and PVOPS subprojects"):
>>> Any other votes by committers (in the TO list) before I tally the votes?
>>
>> +1 to both.
>
> We had several +1'
On 24/04/15 17:21, Paul Durrant wrote:
> The level of switch nesting in those ops is getting unreadable. Giving
> them their own functions does introduce some code duplication in the
> the pre-op checks but the overall result is easier to follow.
>
> This patch is code movement. There is no functio
On 24/04/15 17:21, Paul Durrant wrote:
> Some parameters can only (validly) be set once. Some cannot be set
> by a guest for its own domain. Consolidate these checks, along with
> the XSM check, in a new hvm_allow_set_param() function for clarity.
>
> Also, introduce hvm_allow_get_param() for simil
flight 51929 seabios real [real]
http://logs.test-lab.xenproject.org/osstest/logs/51929/
Regressions :-(
Tests which did not succeed and are blocking,
including tests which could not be run:
test-amd64-i386-freebsd10-amd64 15 guest-localmigrate.2 fail REGR. vs. 36656
test-amd64-i386-freebsd10
On 04/24/2015 10:09 AM, Boris Ostrovsky wrote:
On 04/24/2015 03:19 AM, Jan Beulich wrote:
On 24.04.15 at 00:20, wrote:
On 04/21/2015 03:01 AM, Jan Beulich wrote:
+ ((++dev_cnt > 0x3f) && hypercall_preempt_check()) )
+break;
+}
+
+if ( (!ret ||
1 - 100 of 126 matches
Mail list logo
