From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/kvm/include/linux/kvm.h b/kvm/include/linux/kvm.h
index 5b4b90c..ca93871 100644
--- a/kvm/include/linux/kvm.h
+++ b/kvm/include/linux/kvm.h
@@ -463,7 +463,7 @@ struct kvm_trace_rec {
#define
From: Gleb Natapov g...@redhat.com
Also use enable/disable bit from ACPI MADT entries to track CPU hot
plug. This removes assumptions about APIC ids from AML code and simplify
cpu hotplug handling.
Signed-off-by: Gleb Natapov g...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git
From: Glauber Costa glom...@redhat.com
This patch separates all i8259 specific kvm implementation
in separate functions. This way, qemu can have an i8259 device
free from any kvm interference. kvm can have a simpler code path
(we may even be able to compile out qemu's pic in the future if
we want
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/include-compat/linux/eventfd.h b/include-compat/linux/eventfd.h
new file mode 100644
index 000..c3580fb
--- /dev/null
+++ b/include-compat/linux/eventfd.h
@@ -0,0 +1 @@
+/* Dummy file */
--
To unsubscribe
From: Avi Kivity a...@redhat.com
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/Makefile b/Makefile
index f51b491..95e4c81 100644
--- a/Makefile
+++ b/Makefile
@@ -37,8 +37,13 @@ include $(MAKEFILE_PRE)
.PHONY: sync
+KVM_VERSION_GIT = $(if $(and $(filter kvm-devel,$(KVM_VERSION)), \
From: Avi Kivity a...@redhat.com
kvm_svm.h is only included from svm.c, so fold it in.
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h
deleted file mode 100644
index 39fddc0..000
--- a/arch/x86/kvm/kvm_svm.h
+++ /dev/null
@@ -1,54 +0,0
From: Gregory Haskins ghask...@novell.com
We invoke kfree() on a data member instead of the structure. This works today
because the kvm_io_device is the first element of the private structure, but
this could change in the future, so lets clean this up.
Signed-off-by: Gregory Haskins
From: Stephen Rothwell s...@canb.auug.org.au
Fixes a couple of warnings like this one:
WARNING: arch/powerpc/kvm/kvm-440.o(.text+0x1e8c): Section mismatch in
reference from the function kvmppc_44x_exit() to the function
.exit.text:kvmppc_booke_exit()
The function kvmppc_44x_exit() references a
From: Gregory Haskins ghask...@novell.com
We currently publish the i8254 resources to the pio_bus before the devices
are fully initialized. Since we hold the pit_lock, its probably not
a real issue. But lets clean this up anyway.
Reported-by: Avi Kivity a...@redhat.com
Signed-off-by: Gregory
From: Gregory Haskins ghask...@novell.com
We modernize the io_device code so that we use container_of() instead of
dev-private, and move the vtable to a separate ops structure
(theoretically allows better caching for multiple instances of the same
ops structure)
Signed-off-by: Gregory Haskins
From: Avi Kivity a...@redhat.com
vmx_set_cr3() will call vmx_tlb_flush(), which will flush the ept context.
So there is no need to call ept_sync_context() explicitly.
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 25f1239..5607de8 100644
---
From: Avi Kivity a...@redhat.com
Instead of reading the PDPTRs from memory after every exit (which is slow
and wrong, as the PDPTRs are stored on the cpu), sync the PDPTRs from
memory to the VMCS before entry, and from the VMCS to memory after exit.
Do the same for cr3.
Signed-off-by: Avi Kivity
From: Avi Kivity a...@redhat.com
Instead of reloading the pdptrs on every entry and exit (vmcs writes on vmx,
guest memory access on svm) extract them on demand.
Signed-off-by: Avi Kivity a...@redhat.com
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index
This patch separates all i8259 specific kvm implementation
in separate functions. This way, qemu can have an i8259 device
free from any kvm interference. kvm can have a simpler code path
(we may even be able to compile out qemu's pic in the future if
we want to), and everybody gets happy.
On Thu, May 14, 2009 at 4:10 PM, Michael Goldish mgold...@redhat.com wrote:
Hi Jason,
We already have patches that implement similar functionality here in
TLV, as mentioned in the to-do list (item #4 under 'Framework').
They're not yet committed upstream because they're still quite fresh.
On Mon, Jun 1, 2009 at 8:33 PM, Uri Lublin u...@redhat.com wrote:
On 05/10/2009 08:15 PM, sudhir kumar wrote:
Hi Uri,
Any comments?
-- Forwarded message --
From: sudhir kumarsmalik...@gmail.com
The kvm-autotest shows the following PASS results for migration,
while the VM
On Mon, Jun 01, 2009 at 04:22:03PM +0300, Avi Kivity wrote:
+static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+ switch (reg) {
+ case VCPU_EXREG_PDPTR:
+ BUG_ON(!npt_enabled);
+ load_pdptrs(vcpu, vcpu-arch.cr3);
+ break;
+
Joerg Roedel wrote:
On Mon, Jun 01, 2009 at 04:22:03PM +0300, Avi Kivity wrote:
+static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+ switch (reg) {
+ case VCPU_EXREG_PDPTR:
+ BUG_ON(!npt_enabled);
+ load_pdptrs(vcpu, vcpu-arch.cr3);
On Monday 01 June 2009 21:22:02 Avi Kivity wrote:
Instead of reading the PDPTRs from memory after every exit (which is slow
and wrong, as the PDPTRs are stored on the cpu), sync the PDPTRs from
memory to the VMCS before entry, and from the VMCS to memory after exit.
Do the same for cr3.
Sheng Yang wrote:
On Monday 01 June 2009 21:22:02 Avi Kivity wrote:
Instead of reading the PDPTRs from memory after every exit (which is slow
and wrong, as the PDPTRs are stored on the cpu), sync the PDPTRs from
memory to the VMCS before entry, and from the VMCS to memory after exit.
Do the
On Tuesday 02 June 2009 17:26:27 Avi Kivity wrote:
Sheng Yang wrote:
On Monday 01 June 2009 21:22:02 Avi Kivity wrote:
Instead of reading the PDPTRs from memory after every exit (which is
slow and wrong, as the PDPTRs are stored on the cpu), sync the PDPTRs
from memory to the VMCS before
On Tue, Jun 02, 2009 at 12:09:17PM +0300, Avi Kivity wrote:
Joerg Roedel wrote:
On Mon, Jun 01, 2009 at 04:22:03PM +0300, Avi Kivity wrote:
+static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+ switch (reg) {
+ case VCPU_EXREG_PDPTR:
+
Joerg Roedel wrote:
On Tue, Jun 02, 2009 at 12:09:17PM +0300, Avi Kivity wrote:
Joerg Roedel wrote:
On Mon, Jun 01, 2009 at 04:22:03PM +0300, Avi Kivity wrote:
+static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+ switch (reg) {
+ case
Sheng Yang wrote:
No, no, not with the new code. For CPU can load pdptrs if EPT enabled with PAE
from VM exit, there should not be necessary load it explicitly. So I estimate
the ept_load_pdptr() in exit handler, and put it in CR0 handling. Just tried
to optimize load-pdptr according to the
Matteo Signorini wrote:
Hi!
I have a problem with both kvm pmemsave and memsave functions.
(I know that both invoke the cpu_physical_memory_rw function)
I'm trying to dump a guest physical memory region (sys_call_table for example).
I know that , for example, the sys_call_table is stored at
On Tuesday 02 June 2009 17:46:39 Avi Kivity wrote:
Sheng Yang wrote:
No, no, not with the new code. For CPU can load pdptrs if EPT enabled
with PAE from VM exit, there should not be necessary load it explicitly.
So I estimate the ept_load_pdptr() in exit handler, and put it in CR0
Stephen Rothwell wrote:
Fixes a couple of warnings like this one:
WARNING: arch/powerpc/kvm/kvm-440.o(.text+0x1e8c): Section mismatch in
reference from the function kvmppc_44x_exit() to the function
.exit.text:kvmppc_booke_exit()
The function kvmppc_44x_exit() references a function in an exit
Gregory Haskins wrote:
(This is v3 of the series, applies to kvm.git/master:7ff90748)
This is in prep for some more substantial mmio/pio work for iosignalfd,
coming later.
[ Changelog:
v3:
*) Addressed feedback from Chris Wright w.r.t. patch 2/3
*) Rebased to
Sheng Yang wrote:
On Tuesday 02 June 2009 17:46:39 Avi Kivity wrote:
Sheng Yang wrote:
No, no, not with the new code. For CPU can load pdptrs if EPT enabled
with PAE from VM exit, there should not be necessary load it explicitly.
So I estimate the ept_load_pdptr() in exit handler, and
Gleb Natapov wrote:
Also use enable/disable bit from ACPI MADT entries to track CPU hot
plug. This removes assumptions about APIC ids from AML code and simplify
cup hotplug handling.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from
Avi Kivity wrote:
Zhang, Xiantao wrote:
Fine to me. But seems the change in qemu_iovec_from_buffer is lost in
this patch or that change is also not unnecessary ?
I think the fixed unmap handles that case. Can you test to make sure?
Avi and I went through the code and verified that it was
On Tuesday 02 June 2009 18:16:14 Avi Kivity wrote:
Sheng Yang wrote:
On Tuesday 02 June 2009 17:46:39 Avi Kivity wrote:
Sheng Yang wrote:
No, no, not with the new code. For CPU can load pdptrs if EPT enabled
with PAE from VM exit, there should not be necessary load it
explicitly. So I
Sheng Yang wrote:
Yes, you are right. Quite beautiful. :)
Thanks :)
It's basically a continuation of RIP/RSP caching. I plan to continue it
for cr0/cr3.
Sorry for misunderstood the meaning of on demand without looking at the
patch carefully...
Looks fine now. Thanks!
BTW: one extra
Avi Kivity wrote:
+
static void svm_set_vintr(struct vcpu_svm *svm)
{
svm-vmcb-control.intercept |= 1ULL INTERCEPT_VINTR;
@@ -2286,12 +2298,6 @@ static int handle_exit(struct kvm_run
*kvm_run, struct kvm_vcpu *vcpu)
}
vcpu-arch.cr0 = svm-vmcb-save.cr0;
Using cpu_index for this purpose work only by luck.
Signed-off-by: Gleb Natapov g...@redhat.com
diff --git a/kvm-tpr-opt.c b/kvm-tpr-opt.c
index 246e08d..bdbc742 100644
--- a/kvm-tpr-opt.c
+++ b/kvm-tpr-opt.c
@@ -220,13 +220,29 @@ static int bios_is_mapped(CPUState *env, uint64_t rip)
return
Gleb Natapov wrote:
Using cpu_index for this purpose work only by luck.
Applied, thanks.
--
error compiling committee.c: too many arguments to function
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body of a message to majord...@vger.kernel.org
More majordomo
Glauber Costa wrote:
There's nothing kvm specific in get_cpu function. Remove it from
kvm ifdef. Buy us a cleaner code, and may help us with any attempt
of integrating this on the future.
Signed-off-by: Glauber Costa glom...@redhat.com
---
hw/acpi.c | 12 +++-
1 files changed, 3
Glauber Costa wrote:
This patch separates all i8259 specific kvm implementation
in separate functions. This way, qemu can have an i8259 device
free from any kvm interference. kvm can have a simpler code path
(we may even be able to compile out qemu's pic in the future if
we want to), and
On Thu, May 28, 2009 at 12:54:46PM +0300, Gleb Natapov wrote:
Archs are free to use vcpu_id as they see fit. For x86 it is used as
vcpu's apic id. New ioctl is added to configure boot vcpu id that was
assumed to be 0 till now.
Signed-off-by: Gleb Natapov g...@redhat.com
---
On Sun, May 31, 2009 at 11:22:58AM +0300, Avi Kivity wrote:
ehrha...@linux.vnet.ibm.com wrote:
From: Christian Ehrhardt ehrha...@linux.vnet.ibm.com
*updates in v6*
- ensure the wait_on_bit waiter is notified
- move the reset of requests to kvm_vcpu_release to drop them early
*updates in
On Tue, Jun 02, 2009 at 09:38:08AM -0300, Marcelo Tosatti wrote:
@@ -2223,6 +2226,10 @@ static long kvm_vm_ioctl(struct file *filp,
r = kvm_irqfd(kvm, data.fd, data.gsi, data.flags);
break;
}
+ case KVM_SET_BOOT_CPU_ID:
+ kvm-bsp_vcpu_id = arg;
On vcpu creation cookie is returned which is used in future communication.
Signed-off-by: Gleb Natapov g...@redhat.com
diff --git a/cpu-defs.h b/cpu-defs.h
index 1e071e7..5f541e0 100644
--- a/cpu-defs.h
+++ b/cpu-defs.h
@@ -147,6 +147,7 @@ struct KVMCPUState {
int stop;
int stopped;
Marcelo Tosatti wrote:
On Sun, May 31, 2009 at 11:22:58AM +0300, Avi Kivity wrote:
ehrha...@linux.vnet.ibm.com wrote:
From: Christian Ehrhardt ehrha...@linux.vnet.ibm.com
*updates in v6*
- ensure the wait_on_bit waiter is notified
- move the reset of requests to kvm_vcpu_release to
From: Christian Ehrhardt ehrha...@linux.vnet.ibm.com
As requested this is a rebased patch on top of the already applied v3
of the patch series.
*updates to already applied version*
- ensure allocations (might_sleep) are out of atomic context
- centralize consumption of vcpu-request bits
To
From: Christian Ehrhardt ehrha...@de.ibm.com
As requested this is a rebased patch on top of the already applied v3
of the patch series.
*updates to already applied version*
- ensure the wait_on_bit waiter is notified
- move the reset of requests to kvm_vcpu_release to drop them early
- ensure
From: Christian Ehrhardt ehrha...@linux.vnet.ibm.com
As requested this is a rebased patch on top of the already applied v3
of the patch series.
*updates to applied version*
- ensure the wait_on_bit waiter is notified
- ensure dropping vcpu all requests while freeing a vcpu
- kickout only
From: Christian Ehrhardt ehrha...@linux.vnet.ibm.com
As requested this is a rebased patch on top of the already applied v3
of the patch series.
kvm on s390 formerly ignored vcpu-cpu.
This patch adds set/unset vcpu-cpu in kvm_arch_vcpu_load/put to allow
further architecture unification e.g. let
Avi Kivity wrote:
Gregory Haskins wrote:
irqfd lets you create an eventfd based file-desriptor to inject
interrupts
to a kvm guest. We associate one gsi per fd for fine-grained routing.
Sorry, getting to userspace a little late in the game.
Np.. I need to re-work this for the POLLHUP
Resending. Incorporated a minor fix pointed out by Isaku Yamahata.
Here is the port of MSI-X support patches to upstream qemu.
Please comment or commit.
This patchset adds generic support for MSI-X, adds implementation in
APIC, and uses MSI-X in virtio-net. At Paul's suggestion, I use stl_phy
to
Change much of hw/pci to use symbolic constants and a table-driven
design: add a mask table with writable bits set and readonly bits unset.
Detect change by comparing original and new registers.
This makes it easy to support capabilities where read-only/writeable
bit layout differs between
Add routines to manage PCI capability list. First user will be MSI-X.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/pci.c | 98 --
hw/pci.h | 18 +++-
2 files changed, 106 insertions(+), 10 deletions(-)
diff
Add inline routines for convenient access to pci devices
with correct (little) endianness. Will be used by MSI-X support.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/pci.h | 30 +++---
1 files changed, 27 insertions(+), 3 deletions(-)
diff --git a/hw/pci.h
Add functions implementing MSI-X support. First user will be virtio-pci.
Note that platform must set a flag to declare MSI supported.
For PC this will be set by APIC.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
Makefile.target |2 +-
hw/msix.c | 423
Add support for capability bits in save/restore for pci.
These will be used for MSI, where the capability might
be present or not as requested by user, which does not
map well into a single version number.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/pci.c | 14 --
Add global flag to disable MSI-X by default. This is useful primarily
to make images loadable by older qemu (without msix). Even when MSI-X
is disabled by flag, you can still load images that have MSI-X enabled.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/msix.c |3 +++
Implement MSI support in APIC. Note that MSI and MMIO APIC registers
are at the same memory location, but actually not on the global bus: MSI
is on PCI bus, APIC is connected directly to the CPU. We map them on the
global bus at the same address which happens to work because MSI
registers are
Make it possible to resize PCI regions. This will be used by virtio
with MSI-X, where the region size depends on whether MSI-X is enabled,
and can change across load/save.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/pci.c | 54
Extend virtio to support many interrupt vectors, and rearrange code in
preparation for multi-vector support (mostly move reset out to bindings,
because we will have to reset the vectors in transport-specific code).
Actual bindings in pci, and use in net, to follow.
Load and save are not connected
This enables actual support for MSI-X in virtio PCI.
First user will be virtio-net.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/virtio-pci.c | 152 --
1 files changed, 112 insertions(+), 40 deletions(-)
diff --git
Request up to 3 vectors in virtio-net. Actual bindings might supply
less.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/virtio-net.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/hw/virtio-net.c b/hw/virtio-net.c
index 60aa6da..6118fe3 100644
---
Implement bindings for virtio save/load. Use them in virtio pci.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/virtio-pci.c | 49 -
hw/virtio.c | 31 ++-
hw/virtio.h |4
3 files changed,
Add pci_get/set_byte to keep *_word and *_long access functions company.
They are unused for now.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
hw/pci.h | 12
1 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/hw/pci.h b/hw/pci.h
index 4072f16..e1e4fb4 100644
(Applies to kvm.git/master:25deed73)
Please see the header for 2/2 for a description. This patch series has
been fully tested and appears to be working correctly. I have it as an RFC
for now because it needs Davide's official submission/SOB for patch 1/2, and
it should get some eyeballs/acks on
From: Davide Libenzi davi...@xmailserver.org
Return-path: davi...@xmailserver.org
Received: from novell.com ([:::130.57.1.153])
by soto.provo.novell.com with ESMTP; Wed, 27 May 2009 13:35:04 -0600
Received: from x35.xmailserver.org not authenticated [64.71.152.41]
by
Assigning an irqfd object to a kvm object creates a relationship that we
currently manage by having the kvm oject acquire/hold a file* reference to
the underlying eventfd. The lifetime of these objects is properly maintained
by decoupling the two objects whenever the irqfd is closed or kvm is
Hi, Jes
Have you verified whether it works for you ? You may run kernel build in
the guest with 4 vcpus, if it can be done successfully without any error, it
should be Okay I think, otherwise, we may need to investigate it further. :)
Xiantao
-Original Message-
irqfd lets you create an eventfd based file-desriptor to inject interrupts
to a kvm guest. We associate one gsi per fd for fine-grained routing.
[note: this is meant to work in conjunction with the POLLHUP version of
irqfd, which has not yet been accepted into kvm.git]
[ Changelog:
v8:
Gregory Haskins wrote:
irqfd lets you create an eventfd based file-desriptor to inject interrupts
to a kvm guest. We associate one gsi per fd for fine-grained routing.
[note: this is meant to work in conjunction with the POLLHUP version of
irqfd, which has not yet been accepted into
On Tue, Jun 02, 2009 at 11:15:28AM -0400, Gregory Haskins wrote:
(Applies to kvm.git/master:25deed73)
Please see the header for 2/2 for a description. This patch series has
been fully tested and appears to be working correctly. I have it as an RFC
for now because it needs Davide's official
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 11:15:28AM -0400, Gregory Haskins wrote:
(Applies to kvm.git/master:25deed73)
Please see the header for 2/2 for a description. This patch series has
been fully tested and appears to be working correctly. I have it as an RFC
for now
I had a VM running Linux. While running that SAS installer the kernel
ran out of memory and killed the installer. After that, any attempt to
run a binary inside the VM produced cannot execute binary file. The
log (inside the VM) also showed messages like
Buffer I/O error on device hda1, logical
On Tue, Jun 02, 2009 at 12:14:15PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 11:15:28AM -0400, Gregory Haskins wrote:
(Applies to kvm.git/master:25deed73)
Please see the header for 2/2 for a description. This patch series has
been fully tested
Ross Boylan wrote:
I had a VM running Linux. While running that SAS installer the kernel
ran out of memory and killed the installer. After that, any attempt to
run a binary inside the VM produced cannot execute binary file. The
log (inside the VM) also showed messages like
Buffer I/O error on
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 12:14:15PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 11:15:28AM -0400, Gregory Haskins wrote:
(Applies to kvm.git/master:25deed73)
Please see the header for 2/2 for a description.
On Tue, Jun 02, 2009 at 12:34:12PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 12:14:15PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 11:15:28AM -0400, Gregory Haskins wrote:
(Applies to
On Tue, Jun 02, 2009 at 07:59:49PM +0300, Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 12:34:12PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 12:14:15PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009
On Tue, 2009-06-02 at 19:27 +0300, Avi Kivity wrote:
Ross Boylan wrote:
I had a VM running Linux. While running that SAS installer the kernel
ran out of memory and killed the installer. After that, any attempt to
run a binary inside the VM produced cannot execute binary file. The
log
On Tue, 2 Jun 2009, Gregory Haskins wrote:
@@ -64,12 +101,28 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int
sync, void *key)
{
struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
- /*
- * The wake_up is called with interrupts disabled. Therefore we
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 12:34:12PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 12:14:15PM -0400, Gregory Haskins wrote:
Michael S. Tsirkin wrote:
On Tue, Jun 02, 2009 at 11:15:28AM -0400,
Davide Libenzi wrote:
On Tue, 2 Jun 2009, Gregory Haskins wrote:
@@ -64,12 +101,28 @@ irqfd_wakeup(wait_queue_t *wait, unsigned mode, int
sync, void *key)
{
struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
-/*
- * The wake_up is called with interrupts
On Tue, Jun 02, 2009 at 11:15:38AM -0400, Gregory Haskins wrote:
Assigning an irqfd object to a kvm object creates a relationship that we
currently manage by having the kvm oject acquire/hold a file* reference to
the underlying eventfd. The lifetime of these objects is properly maintained
by
Paul E. McKenney wrote:
On Tue, Jun 02, 2009 at 11:15:38AM -0400, Gregory Haskins wrote:
Assigning an irqfd object to a kvm object creates a relationship that we
currently manage by having the kvm oject acquire/hold a file* reference to
the underlying eventfd. The lifetime of these
In the same way as the previous i8259 patch, this patch cleans up
the apic and ioapic code to provide an implementation that is kvm free.
This reduces the impact of kvm on normal qemu. Also, provides a simpler
code base for kvm devices.
--
To unsubscribe from this list: send the line
This is not kvm specific, and should do fine in plain qemu
Signed-off-by: Glauber Costa glom...@redhat.com
---
hw/apic.c |3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/hw/apic.c b/hw/apic.c
index 86aa6b6..2eddba0 100644
--- a/hw/apic.c
+++ b/hw/apic.c
@@ -467,8 +467,7
provide functions to query and reset the state of sipi and
init in cpu's apic. This way we can move the kvm specific functions
out of the apic path.
Signed-off-by: Glauber Costa glom...@redhat.com
---
cpu-defs.h |2 --
hw/apic.c | 49 -
Also, provide a kvm_apic that does not depend highly on common code.
Signed-off-by: Glauber Costa glom...@redhat.com
---
hw/apic.c | 249 ++--
hw/pc.c|7 ++-
hw/pc.h|1 +
qemu-kvm-x86.c |5 +-
4 files changed,
Also, provide a kvm_ioapic that does not depend highly on common code.
Signed-off-by: Glauber Costa glom...@redhat.com
---
hw/ioapic.c | 162 +-
hw/pc.c |7 ++-
hw/pc.h |1 +
3 files changed, 110 insertions(+), 60
Glauber Costa wrote:
This is not kvm specific, and should do fine in plain qemu
This is fine with plain qemu already. The problem, IIUC, is that
in-kernel kvm irqchip does not have a chance to remove the halted state
again. Did you test the effect of this patch on that scenario? What
makes it
I've been looking at how KVM handles windows guests, and I am a little
concerned with the CPU overhead. My test case is as follows:
I am running 4 instances of a J2EE benchmark. Each instance needs one
application server and one DB server. 8 VMs in total are used.
I have the same App and
On Tue, Jun 02, 2009 at 10:35:47PM +0200, Jan Kiszka wrote:
Glauber Costa wrote:
This is not kvm specific, and should do fine in plain qemu
This is fine with plain qemu already. The problem, IIUC, is that
in-kernel kvm irqchip does not have a chance to remove the halted state
again. Did
Andrew Theurer wrote:
I've been looking at how KVM handles windows guests, and I am a little
concerned with the CPU overhead. My test case is as follows:
I am running 4 instances of a J2EE benchmark. Each instance needs one
application server and one DB server. 8 VMs in total are used.
I
- Unsync pages contain writable sptes in the rmap.
- rmaps do not exclusively contain writable sptes anymore.
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
Index: kvm/arch/x86/kvm/mmu.c
===
--- kvm.orig/arch/x86/kvm/mmu.c
+++
update_pte sets nonleaf sptes as notrap, so either it or the audit code
is broken.
Choose the audit code.
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
Index: kvm/arch/x86/kvm/mmu.c
===
--- kvm.orig/arch/x86/kvm/mmu.c
+++
Some updates to the MMU audit code.
The third patch is guessy because I could not find the notrap spte
documentation, all I can see is the page-fault error code mask and match
fields in the VMCS, but can't see the link of that to sptes. Can someone
point it out please?
--
--
To unsubscribe
- Fail early in case gfn_to_pfn returns is_error_pfn.
- For the pre pte write case, avoid spurious gva is valid but spte is notrap
messages (the emulation code does the guest write first, so this particular
case is OK).
Signed-off-by: Marcelo Tosatti mtosa...@redhat.com
Index:
Under testing, count_writable_mappings returns a value that is 2 integers
larger than what count_rmaps returns.
Suspicion is that either of the two functions is counting a duplicate (either
positively or negatively).
Modifying check_writable_mappings_rmap to check for rmap existance on
all
On Tue, Jun 2, 2009 at 4:38 PM, Avi Kivity a...@redhat.com wrote:
Andrew Theurer wrote:
P.S. Here is the qemu cmd line for the windows VMs:
/usr/local/bin/qemu-system-x86_64 -name newcastle-xdbt01 -hda
/dev/disk/by-id/scsi-3600a0b8f1eb1074f4a02b08a
Use: -drive
Javier Guerra wrote:
On Tue, Jun 2, 2009 at 4:38 PM, Avi Kivity a...@redhat.com wrote:
Andrew Theurer wrote:
P.S. Here is the qemu cmd line for the windows VMs:
/usr/local/bin/qemu-system-x86_64 -name newcastle-xdbt01 -hda
/dev/disk/by-id/scsi-3600a0b8f1eb1074f4a02b08a
Glauber Costa wrote:
On Tue, Jun 02, 2009 at 10:35:47PM +0200, Jan Kiszka wrote:
Glauber Costa wrote:
This is not kvm specific, and should do fine in plain qemu
This is fine with plain qemu already. The problem, IIUC, is that
in-kernel kvm irqchip does not have a chance to remove the halted
On Wed, Jun 03, 2009 at 12:01:00AM +0200, Jan Kiszka wrote:
Glauber Costa wrote:
On Tue, Jun 02, 2009 at 10:35:47PM +0200, Jan Kiszka wrote:
Glauber Costa wrote:
This is not kvm specific, and should do fine in plain qemu
This is fine with plain qemu already. The problem, IIUC, is that
1 - 100 of 114 matches
Mail list logo