Hi,
I just noticed that Nested VMX got broken (at least in my tests) by commit
46199f33c29533e7ad2a7d2128dc30175d1d4157.
The specific change causing the problem was:
@@ -2220,7 +2216,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32
msr_index, u64 data)
break;
Changlong:
Thanks to David's review, there are some changes:
- add kvm-events compile-depend files to tools/perf/MANIFEST
- fix some typos and little clean up
- rebase it on -tip tree
The output example is following:
#./perf kvm-events report --event mmio --vcpu 3
Analyze events for VCPU 3:
They will be needed by 'perf kvm-events'
Signed-off-by: Xiao Guangrong xiaoguangr...@linux.vnet.ibm.com
---
arch/x86/include/asm/kvm_host.h | 36 ---
arch/x86/include/asm/svm.h | 205 +--
arch/x86/include/asm/vmx.h | 125
'perf kvm-events' will use kvm_exit and kvm_mmio(read...) to calculate
mmio read emulated time for the old kernel, in order to trace mmio read
event more exactly, we add kvm_mmio_begin to trace the time when mmio read
begins
Also, add kvm_mmio_done to trace the time when mmio/pio is completed
Add 'perf kvm-events' support to analyze kvm vmexit/mmio/ioport smartly
Usage:
- trace kvm events:
perf kvm-events record, or, if other tracepoints are also
interesting, we can append the events like this:
perf kvm-events record -e timer:*
- show the result:
perf kvm-events report
The
Il 05/03/2012 18:35, Avi Kivity ha scritto:
The I/O handlers would still use the qemu mutex, no? we'd just protect
the select() (taking the mutex from before releasing the global lock,
and reacquiring it afterwards).
Yes, that could work, but it is _really_ ugly.
Yes, it is...
* Xiao Guangrong xiaoguangr...@linux.vnet.ibm.com wrote:
The output example is following:
#./perf kvm-events report --event mmio --vcpu 3
So we already have 'perf kvm':
usage: perf kvm [options] {top|record|report|diff|buildid-list}
which is a sub-namespace for all things KVM
On 2012-03-06 08:49, Liu, Jinsong wrote:
Jan,
Any comments? I feel some confused about your point 'disable cpuid feature
for older machine types by default': are you planning a common approach for
this common issue, or, you just ask me a specific solution for the tsc
deadline timer case?
On 03/06/2012 07:30 AM, Michael Ellerman wrote:
On Mon, 2012-03-05 at 14:29 +0200, Avi Kivity wrote:
If some vcpus are created before KVM_CREATE_IRQCHIP, then
irqchip_in_kernel() and vcpu-arch.apic will be inconsistent, leading
to potential NULL pointer dereferences.
Fix by:
-
Thanks for your review, Ingo!
On 03/06/2012 05:07 PM, Ingo Molnar wrote:
So, your new tool has a similar workflow to:
perf kvm record
perf kvm report
but differs from it in terms of events used and in terms of
reported output.
To me it appears that your tool is basically pretty
Hi all,
I'm trying to use a hid device inside qemu/kvm without success.
My host OS is Ubuntu and the guest is a Windows XP.
I have disabled apparmor to have, hopefully, less problems.
Inside the Windows XP Device Manager I see the Human Interface
Device listed but I'm not really able to use it.
On 03/06/2012 01:13 PM, Maja Massarini wrote:
Hi all,
I'm trying to use a hid device inside qemu/kvm without success.
My host OS is Ubuntu and the guest is a Windows XP.
I have disabled apparmor to have, hopefully, less problems.
Inside the Windows XP Device Manager I see the Human
On 03/06/2012 10:33 AM, Nadav Har'El wrote:
Hi,
I just noticed that Nested VMX got broken (at least in my tests) by commit
46199f33c29533e7ad2a7d2128dc30175d1d4157.
The specific change causing the problem was:
@@ -2220,7 +2216,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32
On Sat, Mar 03, 2012 at 02:21:48PM +0900, Takuya Yoshikawa wrote:
We have seen some problems of the current implementation of
get_dirty_log() which uses synchronize_srcu_expedited() for updating
dirty bitmaps; e.g. it is noticeable that this sometimes gives us ms
order of latency when we use
Shared MSRs (MSR_*STAR and related) are stored in both vmx-guest_msrs
and in the CPU registers, but vmx_set_msr() only updated memory. Prior
to 46199f33c2953, this didn't matter, since we called vmx_load_host_state(),
which scheduled a vmx_save_host_state(), which re-synchronized the CPU
state,
3.3-rc1+ loaded MSR_STAR too lazily, breaking workloads
that play with this MSR (or related MSRs) like nested vmx.
Verify that it is loaded eagerly.
Signed-off-by: Avi Kivity a...@redhat.com
---
x86/msr.c | 18 ++
1 files changed, 18 insertions(+), 0 deletions(-)
diff --git
On Mon, Mar 5, 2012 at 4:44 PM, Martin Mailand mar...@tuxadero.com wrote:
Am 05.03.2012 17:35, schrieb Stefan Hajnoczi:
1. Test on i7 Laptop with Cpu governor ondemand.
v0.14.1
bw=63492KB/s iops=15873
bw=63221KB/s iops=15805
v1.0
bw=36696KB/s iops=9173
bw=37404KB/s
On Tue, Mar 06, 2012, Avi Kivity wrote about [PATCH] KVM: VMX: Fix delayed
load of shared MSRs:
Shared MSRs (MSR_*STAR and related) are stored in both vmx-guest_msrs
and in the CPU registers, but vmx_set_msr() only updated memory. Prior
to 46199f33c2953, this didn't matter, since we called
On Mon, 2012-03-05 at 17:53 +0100, Lennert Buytenhek wrote:
net/dsa currently configures any switch chips in the system to do
auto-learning.
So we clearly need the (user configurable) knob to turn on/off learning.
I think it should also be upto the admin to decide whether the learning
On Tue, Mar 06, 2012 at 08:42:26AM -0500, jamal wrote:
net/dsa currently configures any switch chips in the system to do
auto-learning.
So we clearly need the (user configurable) knob to turn on/off learning.
Why so? (I think the switch chips should just never do learning at
all..)
On Mon, Mar 05, 2012 at 07:45:22PM -0800, John Fastabend wrote:
Also if there are embedded switches with learning capabilities they
might want to trigger events to user space. In this case having
a protocol type makes user space a bit easier to manage. I've
added Lennert so maybe he can
Hi Martin,
On 05.03.2012 17:13, Martin Mailand wrote:
Am 10.02.2012 15:36, schrieb Dongsu Park:
Recently I observed performance regression regarding virtio-blk,
especially different IO bandwidths between qemu-kvm 0.14.1 and 1.0.
So I want to share the benchmark results, and ask you what the
Juan Quintela quint...@redhat.com wrote:
Hi
Please send in any agenda items you are interested in covering.
As there are any topic, tomorow call gets cancelled.
Happy hacking, Juan.
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to
The code which checks whether to inject a pagefault to L1 or L2 (in
nested VMX) was wrong, incorrect in how it checked the PF_VECTOR bit.
Thanks to Dan Carpenter for spotting this.
Signed-off-by: Nadav Har'El n...@il.ibm.com
Reported-by: Dan Carpenter dan.carpen...@oracle.com
---
Marcelo Tosatti mtosa...@redhat.com wrote:
+ spin_lock(kvm-mmu_lock);
It is not clear why mmu_lock is needed. Dropping it across the xchg loop
should be similar to srcu implementation, in that concurrent updates
will be visible only on the next get_dirty call? Well, it is necessary
The spec (Vol 3C, Chapter 34.1) regarding the IA32_FEATURE_CONTROL MSR says
Therefore the lock bit must be set after configuring support for Intel
Virtualization Technology and prior to transferring control to an option ROM or
the OS. and regarding bit 2: This bit enables VMX for system
On Tue, Mar 06, 2012 at 11:43:17PM +0900, Takuya Yoshikawa wrote:
Marcelo Tosatti mtosa...@redhat.com wrote:
+ spin_lock(kvm-mmu_lock);
It is not clear why mmu_lock is needed. Dropping it across the xchg loop
should be similar to srcu implementation, in that concurrent updates
will
On Tue, 2012-03-06 at 13:50 +0200, Avi Kivity wrote:
What version of qemu-kvm are you using? In general 1.0+ is much better
than its predecessors.
I was using qemu-kvm-0.12.3 and in another host qemu-kvm-0.14.1.
Now I have just compiled QEMU emulator version 1.0,1 and nothing has
changed.
I
On 03/06/2012 05:02 PM, Julian Stecklina wrote:
The spec (Vol 3C, Chapter 34.1) regarding the IA32_FEATURE_CONTROL MSR says
Therefore the lock bit must be set after configuring support for Intel
Virtualization Technology and prior to transferring control to an option ROM
or the OS. and
Marcelo Tosatti mtosa...@redhat.com wrote:
If we do not mind scanning the bitmap twice, we can decouple the
xchg loop and write protection, but it will be a bit slower, and in
any case we need to hold mmu_lock until TLB is flushed.
Why is it necessary to scan twice? Simply continuing to
Thus spake Avi Kivity a...@redhat.com:
On 03/06/2012 05:02 PM, Julian Stecklina wrote:
The spec (Vol 3C, Chapter 34.1) regarding the IA32_FEATURE_CONTROL MSR says
Therefore the lock bit must be set after configuring support for Intel
Virtualization Technology and prior to transferring
On Wed, Mar 07, 2012 at 12:23:17AM +0900, Takuya Yoshikawa wrote:
Marcelo Tosatti mtosa...@redhat.com wrote:
If we do not mind scanning the bitmap twice, we can decouple the
xchg loop and write protection, but it will be a bit slower, and in
any case we need to hold mmu_lock until TLB
On 02/28/2012 03:19 PM, Jan Kiszka wrote:
PCI 2.3 allows to generically disable IRQ sources at device level. This
enables us to share legacy IRQs of such devices with other host devices
when passing them to a guest.
The new IRQ sharing feature introduced here is optional, user space has
to
On 2012-03-06 16:34, Avi Kivity wrote:
On 02/28/2012 03:19 PM, Jan Kiszka wrote:
PCI 2.3 allows to generically disable IRQ sources at device level. This
enables us to share legacy IRQs of such devices with other host devices
when passing them to a guest.
The new IRQ sharing feature
On Tue, Mar 06, 2012, Avi Kivity wrote about Re: [PATCH] KVM: Enable
VMX-related bits in MSR_IA32_FEATURE_CONTROL.:
case MSR_IA32_FEATURE_CONTROL:
- *pdata = 0;
+/*
+ * If nested VMX is enabled, set the lock bit (bit 0)
+ *
On 03/06/2012 05:41 PM, Jan Kiszka wrote:
On 2012-03-06 16:34, Avi Kivity wrote:
On 02/28/2012 03:19 PM, Jan Kiszka wrote:
PCI 2.3 allows to generically disable IRQ sources at device level. This
enables us to share legacy IRQs of such devices with other host devices
when passing them to a
On Tue, Feb 28, 2012 at 02:19:54PM +0100, Jan Kiszka wrote:
PCI 2.3 allows to generically disable IRQ sources at device level. This
enables us to share legacy IRQs of such devices with other host devices
when passing them to a guest.
The new IRQ sharing feature introduced here is optional,
Am Dienstag, den 06.03.2012, 17:47 +0200 schrieb Nadav Har'El:
On Tue, Mar 06, 2012, Avi Kivity wrote about Re: [PATCH] KVM: Enable
VMX-related bits in MSR_IA32_FEATURE_CONTROL.:
case MSR_IA32_FEATURE_CONTROL:
- *pdata = 0;
+/*
+ * If nested
* Xiao Guangrong xiaoguangr...@linux.vnet.ibm.com wrote:
Thanks for your review, Ingo!
On 03/06/2012 05:07 PM, Ingo Molnar wrote:
So, your new tool has a similar workflow to:
perf kvm record
perf kvm report
but differs from it in terms of events used and in terms of
On Tue, Mar 06, 2012, Nadav Har'El wrote about Re: [PATCH] KVM: Enable
VMX-related bits in MSR_IA32_FEATURE_CONTROL.:
2. handle_vmon() does not check the previous setting of this MSR.
If the guest (or its BIOS) doesn't set both FEATURE_CONTROL_LOCKED
and
https://bugzilla.kernel.org/show_bug.cgi?id=42829
--- Comment #14 from Steve stefan.bo...@gmail.com 2012-03-06 19:35:14 ---
Please could someone have a look on this issue ?
Thank you for your time.
--
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
--- You are
From: Stuart Yoder stuart.yo...@freescale.com
-version 7 of this patchset
-version 7 changes
KVM: PPC: epapr: Factor out the epapr init
-used ENODEV return code in epapr_paravirt_init
-improved error checkign logic as per review comments
-fixed spelling errors
KVM: PPC:
From: Liu Yu-B13201 yu@freescale.com
from the kvm guest paravirt init code.
Signed-off-by: Liu Yu yu@freescale.com
Signed-off-by: Stuart Yoder stuart.yo...@freescale.com
---
arch/powerpc/include/asm/epapr_hcalls.h |2 +
arch/powerpc/kernel/Makefile|1 +
From: Liu Yu-B13201 yu@freescale.com
And add a new flag definition in kvm_ppc_pvinfo to indicate
whether host support EV_IDLE hcall.
Signed-off-by: Liu Yu yu@freescale.com
Signed-off-by: Stuart Yoder stuart.yo...@freescale.com
---
arch/powerpc/include/asm/Kbuild |1 +
From: Liu Yu-B13201 yu@freescale.com
If the guest hypervisor node contains has-idle property.
Signed-off-by: Liu Yu yu@freescale.com
Signed-off-by: Stuart Yoder stuart.yo...@freescale.com
---
arch/powerpc/include/asm/epapr_hcalls.h | 11 ++-
arch/powerpc/kernel/epapr_hcalls.S
From: Liu Yu-B13201 yu@freescale.com
Discard the old way that invoke hypercall,
instead, use epapr paravirt.
Signed-off-by: Liu Yu yu@freescale.com
Signed-off-by: Stuart Yoder stuart.yo...@freescale.com
---
arch/powerpc/include/asm/epapr_hcalls.h | 22 +-
On 03/06/12 13:59, Stefan Hajnoczi wrote:
On Mon, Mar 5, 2012 at 4:44 PM, Martin Mailandmar...@tuxadero.com wrote:
Am 05.03.2012 17:35, schrieb Stefan Hajnoczi:
1. Test on i7 Laptop with Cpu governor ondemand.
v0.14.1
bw=63492KB/s iops=15873
bw=63221KB/s iops=15805
v1.0
Those patches make migration of IPv6 address work, old code
only support to parse IPv4 address/port, use getaddrinfo()
to get socket addresses infomation.
Last two patches are about spliting IPv6 host/port.
Changes from v1:
- split different changes to small patches, it will be easier to review
Use tcp_server_start in those two functions:
tcp_start_incoming_migration()
net_socket_listen_init()
Signed-off-by: Amos Kong ak...@redhat.com
---
migration-tcp.c | 21 +
net/socket.c| 23 +++
2 files changed, 8 insertions(+), 36 deletions(-)
Introduce tcp_server_start() by moving original code in
tcp_start_incoming_migration().
Signed-off-by: Amos Kong ak...@redhat.com
---
net.c | 28
qemu_socket.h |2 ++
2 files changed, 30 insertions(+), 0 deletions(-)
diff --git a/net.c b/net.c
index
Introduce tcp_client_start() by moving original code in
tcp_start_outgoing_migration().
Signed-off-by: Amos Kong ak...@redhat.com
---
net.c | 41 +
qemu_socket.h |1 +
2 files changed, 42 insertions(+), 0 deletions(-)
diff --git a/net.c
Use tcp_client_start() in those two functions:
tcp_start_outgoing_migration()
net_socket_connect_init()
Changes from v2:
- return real error in net_socket_connect_init(), not always -1
Signed-off-by: Amos Kong ak...@redhat.com
---
migration-tcp.c | 39 +++
Migrating with IPv6 address exists problem, gethostbyname()/inet_aton()
could not translate IPv6 address/port simply, so use getaddrinfo()
in tcp_start_common to translate network address and service.
We can get an address list by getaddrinfo().
Userlevel IPv6 Programming Introduction:
int parse_host_port(struct sockaddr_in *saddr, const char *str)
Parsed address info will be restored into 'saddr', it only support ipv4.
This function is used by net_socket_mcast_init() and net_socket_udp_init().
int parse_host_port_info(struct addrinfo *result, const char *str)
Parsed address
IPv6 address contains colons, parse will be wrong.
[2312::8274]:5200
Signed-off-by: Amos Kong ak...@redhat.com
---
net.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/net.c b/net.c
index 2518e5f..d6ce1fa 100644
--- a/net.c
+++ b/net.c
@@ -84,7 +84,7 @@ static int
That method of representing an IPv6 address with a port is
discouraged because of its ambiguity. Referencing to RFC5952,
the recommended format is:
[2312::8274]:5200
For IPv6 brackets must be mandatory if you require a port.
test status: Successed
listen side: qemu-kvm -incoming
There are some repeated code for tcp_server_start()
and tcp_client_start().
Signed-off-by: Amos Kong ak...@redhat.com
---
net.c | 83 -
1 files changed, 46 insertions(+), 37 deletions(-)
diff --git a/net.c b/net.c
index
On 31.01.2012, at 02:17, Takuya Yoshikawa wrote:
Added s390 and ppc developers to Cc,
(2012/01/30 14:35), Takuya Yoshikawa wrote:
Some members of kvm_memory_slot are not used by every architecture.
This patch is the first step to make this difference clear by
introducing
We can know the guest is paniced when the guest runs on xen.
But we do not have such feature on kvm.
Another purpose of this feature is: management app(for example:
libvirt) can do auto dump when the guest is crashed. If management
app does not do auto dump, the guest's user can do dump by hand
The implementation is the same as xen:
register panic notifier, and call hypercall when the guest
is paniced.
Signed-off-by: Wen Congyang we...@cn.fujitsu.com
---
arch/x86/kernel/kvm.c| 12
include/linux/kvm_para.h |1 +
2 files changed, 13 insertions(+), 0 deletions(-)
This patch introduces new request bit KVM_REQ_GUEST_PANICED.
If this bit is set, set vcpu's exit_reason to KVM_EXIT_GUEST_PANICED.
And then the user space can know the guest paniced.
Signed-off-by: Wen Congyang we...@cn.fujitsu.com
---
arch/x86/kvm/x86.c | 11 +++
When the host knows the guest is paniced, it will set
exit_reason to KVM_EXIT_GUEST_PANICED. So if qemu receive
this exit_reason, we can send a event to tell management
application that the guest is paniced and set the guest
status to RUN_STATE_PANICED.
Signed-off-by: Wen Congyang
On 03/06/2012 06:58 PM, Wen Congyang wrote:
When the host knows the guest is paniced, it will set
exit_reason to KVM_EXIT_GUEST_PANICED. So if qemu receive
this exit_reason, we can send a event to tell management
application that the guest is paniced and set the guest
status to
At 03/07/2012 10:40 AM, Eric Blake Wrote:
On 03/06/2012 06:58 PM, Wen Congyang wrote:
When the host knows the guest is paniced, it will set
exit_reason to KVM_EXIT_GUEST_PANICED. So if qemu receive
this exit_reason, we can send a event to tell management
application that the guest is paniced
Alexander Graf ag...@suse.de wrote:
This patch is the first step to make this difference clear by
introducing kvm_memory_slot::arch; lpage_info is moved into it.
I am planning to move rmap stuff into arch next if this patch is accepted.
Please let me know if you have some opinion
https://bugzilla.kernel.org/show_bug.cgi?id=42829
--- Comment #15 from Jason Wang jasow...@redhat.com 2012-03-07 05:41:09 ---
(In reply to comment #14)
Please could someone have a look on this issue ?
Thank you for your time.
Hello Steve:
According to you bisect result, maybe the issue
Hi All,
This is KVM upstream test result against kvm.git
4f324a1bdfba2a29bbd5485e72ba2b4adeb8147c based on kernel 3.3.0-rc5, and
qemu-kvm.git b5ed4b6f6f0d31e0d8210f4b444ba67bfa5d6de2.
We found no new bug and no bug got fixed in the past two weeks.
New issue(0):
Fixed issue(0):
Old issue
On 03/07/2012 01:12 AM, Ingo Molnar wrote:
Since 'perf stat' is not yet used and the output of your tool
looks quite perf stat alike, why not use that name and
standardize all these workflows?
Okay, thanks for your advise, Ingo!
Is the fallowing patch good to you?
Hi Aashish,
Following is an example of the linux code where it uses lwarx and stcwx.
1: lwarx %0,0,%3 # atomic_add\n\
add %0,%2,%0\n
PPC405_ERR77(0,%3)
stwcx. %0,0,%3 \n\
bne-1b
As you would notice after stcwx it checks for equal bit in the
On 03/06/2012 02:30 PM, Aashish Mittal wrote:
I'm thinking of emulating the lwarx and stwcx instruction as follows
1) to emulate lwarx i will just do a load word instruction .
In order to emulate lwarx correctly, i will need to setup a global
reservation structure, which has a reservation
From: Stuart Yoder stuart.yo...@freescale.com
-version 7 of this patchset
-version 7 changes
KVM: PPC: epapr: Factor out the epapr init
-used ENODEV return code in epapr_paravirt_init
-improved error checkign logic as per review comments
-fixed spelling errors
KVM: PPC:
From: Liu Yu-B13201 yu@freescale.com
And add a new flag definition in kvm_ppc_pvinfo to indicate
whether host support EV_IDLE hcall.
Signed-off-by: Liu Yu yu@freescale.com
Signed-off-by: Stuart Yoder stuart.yo...@freescale.com
---
arch/powerpc/include/asm/Kbuild |1 +
From: Liu Yu-B13201 yu@freescale.com
If the guest hypervisor node contains has-idle property.
Signed-off-by: Liu Yu yu@freescale.com
Signed-off-by: Stuart Yoder stuart.yo...@freescale.com
---
arch/powerpc/include/asm/epapr_hcalls.h | 11 ++-
arch/powerpc/kernel/epapr_hcalls.S
From: Liu Yu-B13201 yu@freescale.com
Discard the old way that invoke hypercall,
instead, use epapr paravirt.
Signed-off-by: Liu Yu yu@freescale.com
Signed-off-by: Stuart Yoder stuart.yo...@freescale.com
---
arch/powerpc/include/asm/epapr_hcalls.h | 22 +-
74 matches
Mail list logo
