On Wed, Feb 4, 2015 at 12:15 AM, Paolo Bonzini pbonz...@redhat.com wrote:
On 03/02/2015 16:46, Wincy Van wrote:
v1 --- v2:
Use spin lock to ensure vmcs12 is safe when doing nested
posted interrupt delivery.
v2 --- v3:
1. Add a new field in nested_vmx to avoid the spin lock in v2.
From: Al Viro v...@zeniv.linux.org.uk
it has just verified that it asks no more than the length of the
first segment of iovec.
And with that the last user of stuff in lib/iovec.c is gone.
RIP.
Cc: Michael S. Tsirkin m...@redhat.com
Cc: Nicholas A. Bellinger n...@linux-iscsi.org
Cc:
From: Al Viro v...@zeniv.linux.org.uk
Cc: Michael S. Tsirkin m...@redhat.com
Cc: kvm@vger.kernel.org
Cc: virtualizat...@lists.linux-foundation.org
Signed-off-by: Al Viro v...@zeniv.linux.org.uk
---
drivers/vhost/net.c | 82 +++--
On Tue, 03 Feb 2015 16:22:32 +0100
Paolo Bonzini pbonz...@redhat.com wrote:
On 03/02/2015 16:16, Thomas Huth wrote:
Actually, I'd prefer to keep the virtual in the defines for the type
of operation below: When it comes to s390 storage keys, we likely might
need some calls for reading
On Tue, Feb 03, 2015 at 11:56:16PM +, Al Viro wrote:
On Tue, Feb 03, 2015 at 06:29:59AM +, Nicholas A. Bellinger wrote:
+* Copy over the virtio-scsi request header, which when
+* ANY_LAYOUT is enabled may span multiple iovecs, or a
+* single iovec
On Wed, Feb 4, 2015 at 3:06 AM, Nerijus Baliunas
neri...@users.sourceforge.net wrote:
On Tue, 3 Feb 2015 18:07:57 +0400 Andrey Korolyov and...@xdel.ru wrote:
Have you tried to disable turbo mode (assuming you have new enough CPU
model) and fix frequency via frequency governor` settings? If it
From: Al Viro v...@zeniv.linux.org.uk
just advance the msg.msg_iter and be done with that.
Cc: Michael S. Tsirkin m...@redhat.com
Cc: kvm@vger.kernel.org
Cc: virtualizat...@lists.linux-foundation.org
Signed-off-by: Al Viro v...@zeniv.linux.org.uk
---
drivers/vhost/net.c | 9 +
1 file
From: Al Viro v...@zeniv.linux.org.uk
Cc: Michael S. Tsirkin m...@redhat.com
Cc: kvm@vger.kernel.org
Cc: virtualizat...@lists.linux-foundation.org
Signed-off-by: Al Viro v...@zeniv.linux.org.uk
---
drivers/vhost/vhost.c | 6 --
include/linux/uio.h | 1 -
lib/iovec.c | 25
On 03/02/2015 10:11, Wincy Van wrote:
@@ -8468,6 +8484,38 @@ static void vmx_start_preemption_timer(struct
kvm_vcpu *vcpu)
ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
}
Hi Wincy, the patch is corrupted here. Also it has spaces instead of
tabs earlier. Please
Juan Quintela quint...@redhat.com wrote:
Hi
Please, send any topic that you are interested in covering.
Thanks, Juan.
Call details:
As there are no agenda, call got cancelled.
Could I do anything to improve the chances to have a call? Time change,
call for agenda timing, etc? Just
On 03/02/2015 15:07, Wincy Van wrote:
Ouch, my bad, gmail cut the lines which is over 78 chars.
Since gmail is GFWed(VPN does not work, and I have a web proxy), I
was sending the patches to my gmail via git-send-email with other mail
and forwarding them to the community.
Yeah, forwarding is
On Tue, 03 Feb 2015 14:04:43 +0100
Paolo Bonzini pbonz...@redhat.com wrote:
On 03/02/2015 13:11, Thomas Huth wrote:
On s390, we've got to make sure to hold the IPTE lock while accessing
virtual memory. So let's add an ioctl for reading and writing virtual
memory to provide this feature for
Hmm having second thoughts here.
Will this modify the iov in vq-iov?
If yes, how will recvmsg fill it?
OK that was just me misunderstanding what the
function does. As it doesn't modify the iovec itself,
I think there's no issue, my ack stands.
--
To unsubscribe from this list: send the line
Outreach Program for Women is renaming to Outreachy. The new website
is: http://outreachy.org/
What is Outreachy?
Outreachy helps people from underrepresented groups join the open
source community
through a 12-week full-time paid internship.
The format is similar to Google Summer of Code.
On 03/02/2015 16:16, Thomas Huth wrote:
Actually, I'd prefer to keep the virtual in the defines for the type
of operation below: When it comes to s390 storage keys, we likely might
need some calls for reading and writing to physical memory, too. Then
we could simply extend this ioctl instead
On 03/02/2015 16:18, Radim Krčmář wrote:
(I see the same code in handle_ept_violation(), but wasn't that needed
just because of a hardware error?)
That was how I read it initially, but actually that means: this
statement could be broken if the processor has that erratum.
+static void
2015-01-28 10:54+0800, Kai Huang:
This patch adds PML support in VMX. A new module parameter 'enable_pml' is
added
(+module_param_named(pml, enable_pml, bool, S_IRUGO);)
to allow user to enable/disable it manually.
Signed-off-by: Kai Huang kai.hu...@linux.intel.com
---
diff --git
+ * copy_from_iter() is modifying the iovecs as copies over
+ * req_size bytes into req, so the returned out_iter.iov[0]
+ * will contain the correct start + offset of the outgoing
+ * WRITE payload, if DMA_TO_DEVICE is set.
+
On Mon, Feb 02, 2015 at 07:59:37AM +, Al Viro wrote:
From: Al Viro v...@zeniv.linux.org.uk
it has just verified that it asks no more than the length of the
first segment of iovec.
And with that the last user of stuff in lib/iovec.c is gone.
RIP.
Cc: Michael S. Tsirkin
On Mon, Feb 02, 2015 at 07:59:34AM +, Al Viro wrote:
From: Al Viro v...@zeniv.linux.org.uk
Cc: Michael S. Tsirkin m...@redhat.com
Cc: kvm@vger.kernel.org
Signed-off-by: Al Viro v...@zeniv.linux.org.uk
Acked-by: Michael S. Tsirkin m...@redhat.com
But, can you pls copy
On Tue, Feb 3, 2015 at 10:02 PM, Paolo Bonzini pbonz...@redhat.com wrote:
On 03/02/2015 10:17, Wincy Van wrote:
+static int vmx_accomp_nested_posted_interrupt(struct kvm_vcpu *vcpu)
Replace accomp with complete.
Will do.
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int
On Tue, Feb 03, 2015 at 04:21:54PM +0100, Michael S. Tsirkin wrote:
Hmm having second thoughts here.
Will this modify the iov in vq-iov?
If yes, how will recvmsg fill it?
OK that was just me misunderstanding what the
function does. As it doesn't modify the iovec itself,
I think there's
To enable nested apicv support, we need per-cpu vmx
control MSRs:
1. If in-kernel irqchip is enabled, we can enable nested
posted interrupt, we should set posted intr bit in
the nested_vmx_pinbased_ctls_high.
2. If in-kernel irqchip is disabled, we can not enable
nested posted
With virtual interrupt delivery, the hardware prevent KVM from
the low efficiency interrupt inject way. In nested vmx, it is
a important feature, we can reduce much more nested-vmexit,
especially in high throughput scenes.
Signed-off-by: Wincy Van fanwenyi0...@gmail.com
---
arch/x86/kvm/vmx.c |
2015-01-28 10:54+0800, Kai Huang:
This patch adds new kvm_x86_ops dirty logging hooks to enable/disable dirty
logging for particular memory slot, and to flush potentially logged dirty GPAs
before reporting slot-dirty_bitmap to userspace.
kvm x86 common code calls these hooks when they are
2015-02-03 16:39+0100, Paolo Bonzini:
On 03/02/2015 16:18, Radim Krčmář wrote:
(I see the same code in handle_ept_violation(), but wasn't that needed
just because of a hardware error?)
That was how I read it initially, but actually that means: this
statement could be broken if the
Currently, if L1 enables MSR_BITMAP, we will emulate this feature,
all of L2's msr access is intercepted by L0. Since many features
like virtualize x2apic mode has a complicated logic and it is
difficult for us to emulate, we should use hardware and merge
the bitmap.
This patch introduces
2015-01-28 10:54+0800, Kai Huang:
This patch changes the second parameter of kvm_mmu_slot_remove_write_access
from
'slot id' to 'struct kvm_memory_slot *' to align with kvm_x86_ops dirty
logging
hooks, which will be introduced in further patch.
Better way is to change second parameter of
We can reduce apic register virtualization cost with this feature,
it is also a requirement for virtual interrupt delivery and posted
interrupt processing.
Signed-off-by: Wincy Van fanwenyi0...@gmail.com
---
arch/x86/kvm/vmx.c | 39 +++
1 files changed, 35
v1 --- v2:
Use spin lock to ensure vmcs12 is safe when doing nested
posted interrupt delivery.
v2 --- v3:
1. Add a new field in nested_vmx to avoid the spin lock in v2.
2. Drop send eoi to L1 when doing nested interrupt delivery.
3. Use hardware MSR bitmap to enable nested virtualize
If vcpu has a interrupt in vmx non-root mode, we will
kick that vcpu to inject interrupt timely. With posted
interrupt processing, the kick intr is not needed, and
interrupts are fully taken care of by hardware.
In nested vmx, this feature avoids much more vmexits
than non-nested vmx.
This patch
On 03/02/2015 16:46, Wincy Van wrote:
v1 --- v2:
Use spin lock to ensure vmcs12 is safe when doing nested
posted interrupt delivery.
v2 --- v3:
1. Add a new field in nested_vmx to avoid the spin lock in v2.
2. Drop send eoi to L1 when doing nested interrupt delivery.
3. Use
When L2 is using x2apic, we can use virtualize x2apic mode to
gain higher performance, especially in apicv case.
This patch also introduces nested_vmx_check_apicv_controls
for the nested apicv patches.
Signed-off-by: Wincy Van fanwenyi0...@gmail.com
---
arch/x86/kvm/vmx.c | 114
On 03/02/2015 10:17, Wincy Van wrote:
+static int vmx_accomp_nested_posted_interrupt(struct kvm_vcpu *vcpu)
Replace accomp with complete.
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int max_irr;
+ void *vapic_page;
+ u16 status;
+
+ if
On 03/02/2015 14:25, Nerijus Baliunas wrote:
It did not help. Today that commecrial application detects 2400, although
Control Panel - System shows 2.20 GHz.
So my question again - is it possible to patch qemu-kvm that it shows some
constant frequency to the guest? But the answer is probably
On Tue, Feb 3, 2015 at 9:57 PM, Paolo Bonzini pbonz...@redhat.com wrote:
On 03/02/2015 10:11, Wincy Van wrote:
@@ -8468,6 +8484,38 @@ static void vmx_start_preemption_timer(struct
kvm_vcpu *vcpu)
ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
}
Hi Wincy, the
It did not help. Today that commecrial application detects 2400, although
Control Panel - System shows 2.20 GHz.
So my question again - is it possible to patch qemu-kvm that it shows some
constant frequency to the guest? But the answer is probably not, because
I don't know how the application
tl;dr:
This patch adds a new ioctl to KVM on s390x for reading and writing from/to
virtual guest memory, to take account of the so-called IPTE-lock on s390x
(a locking mechanism for the host to walk MMU tables of the guest).
Long story:
Certain instruction interception handlers in QEMU have to
On s390, we've got to make sure to hold the IPTE lock while accessing
virtual memory. So let's add an ioctl for reading and writing virtual
memory to provide this feature for userspace, too.
Signed-off-by: Thomas Huth th...@linux.vnet.ibm.com
Reviewed-by: Dominik Dingel din...@linux.vnet.ibm.com
On 03/02/2015 13:11, Thomas Huth wrote:
The userspace (QEMU) then can simply call this ioctl when it wants
to read or write from/to virtual guest memory. Then kernel then takes
the IPTE-lock, walks the MMU table of the guest to find out the
physical address that corresponds to the virtual
On 03/02/2015 13:11, Thomas Huth wrote:
On s390, we've got to make sure to hold the IPTE lock while accessing
virtual memory. So let's add an ioctl for reading and writing virtual
memory to provide this feature for userspace, too.
Signed-off-by: Thomas Huth th...@linux.vnet.ibm.com
Am 03.02.2015 um 13:59 schrieb Paolo Bonzini:
On 03/02/2015 13:11, Thomas Huth wrote:
The userspace (QEMU) then can simply call this ioctl when it wants
to read or write from/to virtual guest memory. Then kernel then takes
the IPTE-lock, walks the MMU table of the guest to find out the
On Tue, 23 Dec 2014 15:40:22 +0100 Paolo Bonzini pbonz...@redhat.com wrote:
A commercial application running on Windows (kvm guest) detects CPU as:
CPU_0: CPU0, Intel64 Family 6 Model 42 Stepping 1, 64, 64, 2200,
078BFBFD000206A1, 10753, CPU 0
After some time, without reboot, it detects
On Tue, Feb 03, 2015 at 11:05:15AM +, David Vrabel wrote:
On 27/01/15 01:51, Luis R. Rodriguez wrote:
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+ return
2015-01-28 10:54+0800, Kai Huang:
This patch adds new mmu layer functions to clear/set D-bit for memory slot,
and
to write protect superpages for memory slot.
In case of PML, CPU logs the dirty GPA automatically to PML buffer when CPU
updates D-bit from 0 to 1, therefore we don't have to
On Tue, Feb 03, 2015 at 06:29:55AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
Required for ANY_LAYOUT support when the incoming virtio-scsi response
header + fixed size sense buffer payload may span more than a single
iovec entry.
This changes
On 02.02.15 at 22:06, bhelg...@google.com wrote:
I applied this to pci/msi for v3.20, thanks! I reworked the changelog as
follows; let me know if it still doesn't make things clear:
Thanks, looks good to me now.
Jan
--
To unsubscribe from this list: send the line unsubscribe kvm in
the body
On Tue, Feb 03, 2015 at 06:30:01AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
With the new ANY_LAYOUT logic in place for vhost_scsi_handle_vqal(),
there is no longer a reason to keep around the legacy code with
!ANY_LAYOUT assumptions.
Go ahead and
On Tue, Feb 03, 2015 at 06:30:02AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
With the recent removal of MSG_*_TAG defines in commit 68d81f40,
vhost-scsi is now using TCM_*_TAG and doesn't depend upon host
side scsi_tcq.h definitions anymore.
Cc:
On Tue, Feb 03, 2015 at 06:30:03AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
There is a large amount of code that still references the original
'tcm_vhost' naming conventions, instead of modern 'vhost_scsi'.
Go ahead and do a global rename to make
On 27/01/15 01:51, Luis R. Rodriguez wrote:
+#ifndef CONFIG_PREEMPT
+extern struct { char _entry[32]; } preemptible_hypercall_page[];
+
+static inline bool xen_is_preemptible_hypercall(struct pt_regs *regs)
+{
+ return !user_mode_vm(regs)
+ regs-ip = (unsigned
On Tue, Feb 03, 2015 at 06:29:59AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
This patch adds ANY_LAYOUT support with a new vqs[].vq.handle_kick()
callback in vhost_scsi_handle_vqal().
It calculates data_direction + exp_data_len for the new
On Tue, Feb 03, 2015 at 06:29:59AM +, Nicholas A. Bellinger wrote:
+ * Copy over the virtio-scsi request header, which when
+ * ANY_LAYOUT is enabled may span multiple iovecs, or a
+ * single iovec may contain both the header + outgoing
+
On Tue, 3 Feb 2015 18:07:57 +0400 Andrey Korolyov and...@xdel.ru wrote:
Have you tried to disable turbo mode (assuming you have new enough CPU
model) and fix frequency via frequency governor` settings? If it
helps, it can be an ugly hack with pre-up/post-up libvirt actions,
though you`d
v1 --- v2:
Use spin lock to ensure vmcs12 is safe when doing nested
posted interrupt delivery.
v2 --- v3:
1. Add a new field in nested_vmx to avoid the spin lock in v2.
2. Drop send eoi to L1 when doing nested interrupt delivery.
3. Use hardware MSR bitmap to enable nested virtualize
Currently, if L1 enables MSR_BITMAP, we will emulate this feature,
all of L2's msr access is intercepted by L0. Since many features
like virtualize x2apic mode has a complicated logic and it is
difficult for us to emulate, we should use hardware and merge
the bitmap.
This patch introduces
We can reduce apic register virtualization cost with this feature,
it is also a requirement for virtual interrupt delivery and posted
interrupt processing.
Signed-off-by: Wincy Van fanwenyi0...@gmail.com
---
arch/x86/kvm/vmx.c | 39 +++
1 files changed, 35
With virtual interrupt delivery, the hardware prevent KVM from
the low efficiency interrupt inject way. In nested vmx, it is
a important feature, we can reduce much more nested-vmexit,
especially in high throughput scenes.
Signed-off-by: Wincy Van fanwenyi0...@gmail.com
---
arch/x86/kvm/vmx.c |
On Tue, Feb 03, 2015 at 06:29:54AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
Hi MST, Paolo, Al Co,
Here is -v3 for adding vhost/scsi ANY_LAYOUT + VERSION_1 host feature
bit support.
It adds a new vhost_virtqueue -handle_kick() callback to
In virtio 1.0 mode, when mergeable buffers are enabled on a big-endian
host, num_buffers wasn't byte-swapped correctly, so large incoming
packets got corrupted.
To fix, fill it in within hdr - this also makes sure it gets
the correct type.
Signed-off-by: Michael S. Tsirkin m...@redhat.com
---
On Mon, Feb 02, 2015 at 07:59:36AM +, Al Viro wrote:
From: Al Viro v...@zeniv.linux.org.uk
Cc: Michael S. Tsirkin m...@redhat.com
Cc: kvm@vger.kernel.org
Signed-off-by: Al Viro v...@zeniv.linux.org.uk
---
So this made me notice a bug in vhost introduced in 3.19.
I sent a patch for
When L2 is using x2apic, we can use virtualize x2apic mode to
gain higher performance, especially in apicv case.
This patch also introduces nested_vmx_check_apicv_controls
for the nested apicv patches.
Signed-off-by: Wincy Van fanwenyi0...@gmail.com
---
arch/x86/kvm/vmx.c | 114
To enable nested apicv support, we need per-cpu vmx
control MSRs:
1. If in-kernel irqchip is enabled, we can enable nested
posted interrupt, we should set posted intr bit in
the nested_vmx_pinbased_ctls_high.
2. If in-kernel irqchip is disabled, we can not enable
nested posted
On Mon, Feb 02, 2015 at 07:59:35AM +, Al Viro wrote:
From: Al Viro v...@zeniv.linux.org.uk
just advance the msg.msg_iter and be done with that.
Cc: Michael S. Tsirkin m...@redhat.com
Cc: kvm@vger.kernel.org
Signed-off-by: Al Viro v...@zeniv.linux.org.uk
Nice.
Acked-by: Michael S.
If vcpu has a interrupt in vmx non-root mode, we will
kick that vcpu to inject interrupt timely. With posted
interrupt processing, the kick intr is not needed, and
interrupts are fully taken care of by hardware.
In nested vmx, this feature avoids much more vmexits
than non-nested vmx.
This patch
On Tue, Feb 03, 2015 at 06:29:58AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
This patch adds ANY_LAYOUT prerequisites logic for accepting a set of
protection + data payloads via iov_iter. Also includes helpers for
calcuating SGLs + invoking
On Tue, Feb 03, 2015 at 06:30:00AM +, Nicholas A. Bellinger wrote:
From: Nicholas Bellinger n...@linux-iscsi.org
Signal support of VIRTIO_F_ANY_LAYOUT + VIRTIO_F_VERSION_1 feature bits
required for virtio-scsi 1.0 spec layout requirements.
Cc: Michael S. Tsirkin m...@redhat.com
Cc:
On 03/02/15 00:24, Luis R. Rodriguez wrote:
As I waited I decided to finally install a 32-bit OS but I found now
that as of Xen commit 5d1181a5 which went upstream as of xen 4.3 Xen
no longer supports 32-bit for x86.
You don't need a 32-bit hypervisor to run 32-bit dom0 or domUs.
David
--
On Mon, Feb 02, 2015 at 07:59:36AM +, Al Viro wrote:
From: Al Viro v...@zeniv.linux.org.uk
Cc: Michael S. Tsirkin m...@redhat.com
Cc: kvm@vger.kernel.org
Signed-off-by: Al Viro v...@zeniv.linux.org.uk
---
drivers/vhost/net.c | 79
++---
69 matches
Mail list logo