On 03/10/2014 04:03 PM, Michael S. Tsirkin wrote:
On Fri, Mar 07, 2014 at 01:28:27PM +0800, Jason Wang wrote:
We used to stop the handling of tx when the number of pending DMAs
exceeds VHOST_MAX_PEND. This is used to reduce the memory occupation
of both host and guest. But it was too
Hello.
Where i can get help?
I'm using 9p_virtio to provide rootfs for vm sometimes (3 - 6 times in
10 vps starts) when i have massive read/write i get:
[ 2478.288105] PANIC: double fault, error_code: 0x0
[ 2478.301397] CPU: 1 PID: 5268 Comm: bash Not tainted 3.13.6 #3
[ 2478.301397] Hardware
Commit 7b490411c37f (KVM: PPC: Book3S HV: Add new state for
transactional memory) incorrectly added some duplicate code to the
guest exit path because I didn't manage to clean up after a rebase
correctly. This removes the extraneous material. The presence of
this extraneous code causes host
These two patches fix two things in hypervisor-mode KVM for the IBM
POWER server processors. The first patch removes a hunk of extraneous
code that got in as a result of a mistake I made in cleaning up after
rebasing a patch. The second fixes a bug that causes host memory
corruption. Both
Commit 595e4f7e697e (KVM: PPC: Book3S HV: Use load/store_fp_state
functions in HV guest entry/exit) changed the register usage in
kvmppc_save_fp() and kvmppc_load_fp() but omitted changing the
instructions that load and save VRSAVE. The result is that the
VRSAVE value was loaded from a constant
Il 13/03/2014 10:01, Paul Mackerras ha scritto:
These two patches fix two things in hypervisor-mode KVM for the IBM
POWER server processors. The first patch removes a hunk of extraneous
code that got in as a result of a mistake I made in cleaning up after
rebasing a patch. The second fixes a
On Thu, Mar 13, 2014 at 10:50:29AM +0100, Paolo Bonzini wrote:
Il 13/03/2014 10:01, Paul Mackerras ha scritto:
These two patches fix two things in hypervisor-mode KVM for the IBM
POWER server processors. The first patch removes a hunk of extraneous
code that got in as a result of a mistake I
Il 28/02/2014 05:06, Gabriel L. Somlo ha scritto:
+NOTE: For each level-triggered interrupt managed by a virtual ioapic,
+the guest OS may set a polarity value (bit 13 of each corresponding I/O
+redirection table register). The polarity bit defines the relationship
+between an irq line's
Il 13/03/2014 11:54, David Vrabel ha scritto:
On 12/03/14 18:54, Waiman Long wrote:
Locking is always an issue in a virtualized environment as the virtual
CPU that is waiting on a lock may get scheduled out and hence block
any progress in lock acquisition even when the lock has been freed.
One
On Wed, Mar 12, 2014 at 06:20:01PM +0100, Paolo Bonzini wrote:
Il 12/03/2014 11:40, Radim Krčmář ha scritto:
2014-03-11 22:05-0300, Marcelo Tosatti:
On Tue, Mar 11, 2014 at 07:11:18PM +0100, Radim Krčmář wrote:
We always disable cr8 intercept in its handler, but only re-enable it
if handling
On Thu, Mar 13, 2014 at 11:53:04AM +0100, Paolo Bonzini wrote:
Instead of this, I'm adding the following to the KVM_IRQ_LINE ioctl:
+On real hardware, interrupt pins can be active-low or active-high. This
+does not matter for the level field of struct kvm_irq_level: 1 always
+means active
Il 13/03/2014 12:21, David Vrabel ha scritto:
On 12/03/14 18:54, Waiman Long wrote:
This patch adds para-virtualization support to the queue spinlock in
the same way as was done in the PV ticket lock code. In essence, the
lock waiters will spin for a specified number of times (QSPIN_THRESHOLD
=
Il 12/03/2014 19:54, Waiman Long ha scritto:
@@ -807,8 +889,13 @@ void __init kvm_spinlock_init(void)
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
+#ifdef CONFIG_QUEUE_SPINLOCK
+ pv_lock_ops.kick_cpu = kvm_kick_cpu_type;
+ pv_lock_ops.hibernate =
Signed-off-by: Andreas Färber afaer...@suse.de
---
cpu-exec.c | 5 +++--
exec.c | 33 -
gdbstub.c | 8
include/exec/cpu-defs.h | 10 --
include/qom/cpu.h | 10 ++
linux-user/main.c |
On Thu, 2014-03-13 at 20:01 +1100, Paul Mackerras wrote:
These two patches fix two things in hypervisor-mode KVM for the IBM
POWER server processors. The first patch removes a hunk of extraneous
code that got in as a result of a mistake I made in cleaning up after
rebasing a patch. The
On an unhandled IO memory abort, use the kvm_io_bus_* API in order to
handle the MMIO access through any registered read/write callbacks. This
is a dependency for eventfd support (ioeventfd and irqfd).
However, accesses to the VGIC are still left implemented independently,
since the kvm_io_bus_*
KVM on ARM can now advertise support for the ioeventfd capability.
Signed-off-by: Antonios Motakis a.mota...@virtualopensystems.com
Signed-off-by: Nikolay Nikolaev n.nikol...@virtualopensystems.com
---
arch/arm/kvm/arm.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/arm/kvm/arm.c
With an ARM VGIC we have an IRQ chip in the kernel (using the hardware
support), but the irqfd feature is still not available due to a dependency
on IRQ routing. The prototypes of kvm_irqfd and kvm_irqfd_release should
be conditionally compiled depending on HAVE_KVM_IRQ_ROUTING instead of
This enables and compiles the ioeventfd capability of KVM on ARM. The
irqfd feature will not be included in a build, due to the lack of IRQ
routing in the VGIC implementation of KVM.
Signed-off-by: Antonios Motakis a.mota...@virtualopensystems.com
Signed-off-by: Nikolay Nikolaev
2014-03-13 15:52+0200, Gleb Natapov:
On Wed, Mar 12, 2014 at 06:20:01PM +0100, Paolo Bonzini wrote:
Il 12/03/2014 11:40, Radim Krčmář ha scritto:
2014-03-11 22:05-0300, Marcelo Tosatti:
On Tue, Mar 11, 2014 at 07:11:18PM +0100, Radim Krčmář wrote:
We always disable cr8 intercept in its
On Wed, Mar 12, 2014 at 8:15 PM, Luis R. Rodriguez
mcg...@do-not-panic.com wrote:
spin_lock_bh(p-br-lock);
err = br_setport(p, tb);
+ changed = br_stp_recalculate_bridge_id(p-br);
Looks like you only want to check if the mac
Hi,
I'm working on system calls tracing using QEMU KVM.
1. Is it possible to force emulation of instructions when VM is running?
Then I might be able to enable/disable KVM acceleration whenever I want to.
2. I know I can get full trace from QEMU without KVM (log in_asm). For
example during
On 03/13/2014 09:57 AM, Paolo Bonzini wrote:
Il 13/03/2014 12:21, David Vrabel ha scritto:
On 12/03/14 18:54, Waiman Long wrote:
This patch adds para-virtualization support to the queue spinlock in
the same way as was done in the PV ticket lock code. In essence, the
lock waiters will spin for
Am 06.03.2014 18:09, schrieb James Hogan:
From: Sanjay Lal sanj...@kymasys.com
Implement the main KVM arch API for MIPS.
Signed-off-by: Sanjay Lal sanj...@kymasys.com
Signed-off-by: James Hogan james.ho...@imgtec.com
Cc: Aurelien Jarno aurel...@aurel32.net
Cc: Gleb Natapov
Am 06.03.2014 18:09, schrieb James Hogan:
From: Sanjay Lal sanj...@kymasys.com
COP0 emulation is in-kernel for KVM, so inject IRQ2 (I/O) interrupts via
ioctls.
Signed-off-by: Sanjay Lal sanj...@kymasys.com
Signed-off-by: James Hogan james.ho...@imgtec.com
Reviewed-by: Aurelien Jarno
On Wed, 12 Mar 2014 20:15:27 -0700
Luis R. Rodriguez mcg...@do-not-panic.com wrote:
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -150,6 +150,7 @@ struct net_bridge_port
u8 priority;
u8 state;
u16
On 13 March 2014 21:28, Andreas Färber afaer...@suse.de wrote:
int32 is a type used in softfloat that has weird at-least-as-wide
semantics and bit us in the past.
I'm coming round to the opinion that we should just change all
those to int32_t c. I know we had a discussion about efficiency
at
On Tue, Jan 28, 2014 at 08:28:42AM -0800, Christoffer Dall wrote:
The KVM API documentation is not clear about the semantics of the data
field on the mmio struct on the kvm_run struct.
This has become problematic when supporting ARM guests on big-endian
host systems with guests of both
Hello,
I am working on building an Storage Intrusion Detection System(SIDS) App
inside a VM on KVM hypervisor.
I wanted I/O's from other vm's to first contact this App VM and
then finally write to the disk.I went with the network storage as
an option to achieve this objective. But wanted
On Fri, 03/14 04:46, Shiva wrote:
Hello,
I am working on building an Storage Intrusion Detection System(SIDS) App
inside a VM on KVM hypervisor.
I wanted I/O's from other vm's to first contact this App VM and
then finally write to the disk.I went with the network storage as
an
On 03/13/2014 04:51 AM, Christoffer Dall wrote:
On Tue, Mar 11, 2014 at 02:05:38AM +0530, Srivatsa S. Bhat wrote:
Subsystems that want to register CPU hotplug callbacks, as well as perform
initialization for the CPUs that are already online, often do it as shown
below:
These two patches fix two things in hypervisor-mode KVM for the IBM
POWER server processors. The first patch removes a hunk of extraneous
code that got in as a result of a mistake I made in cleaning up after
rebasing a patch. The second fixes a bug that causes host memory
corruption. Both
On Thu, 2014-03-13 at 20:01 +1100, Paul Mackerras wrote:
These two patches fix two things in hypervisor-mode KVM for the IBM
POWER server processors. The first patch removes a hunk of extraneous
code that got in as a result of a mistake I made in cleaning up after
rebasing a patch. The
Previously SPRG3 was marked for use by both VDSO and critical
interrupts (though critical interrupts were not fully implemented).
In commit 8b64a9dfb091f1eca8b7e58da82f1e7d1d5fe0ad (powerpc/booke64:
Use SPRG0/3 scratch for bolted TLB miss crit int), Mihai Caraman
made an attempt to resolve this
While bolted handlers (including e6500) do not need to deal with a TLB
miss recursively causing another TLB miss, nested TLB misses can still
happen with crit/mc/debug exceptions -- so we still need to honor
SPRG_TLB_EXFRAME.
We don't need to spend time modifying it in the TLB miss fastpath,
On Tue, Jan 28, 2014 at 08:28:42AM -0800, Christoffer Dall wrote:
The KVM API documentation is not clear about the semantics of the data
field on the mmio struct on the kvm_run struct.
This has become problematic when supporting ARM guests on big-endian
host systems with guests of both
36 matches
Mail list logo