On 11/20/2012 04:26 AM, Michael S. Tsirkin wrote:
> On Mon, Nov 19, 2012 at 04:53:42PM +0800, Asias He wrote:
>> vhost-blk is an in-kernel virito-blk device accelerator.
>>
>> Due to lack of proper in-kernel AIO interface, this version converts
>> guest's I/O request to bio and use submit_bio() to
- When KVM_RUN ioctl returns with an exit reason requesting a shutdown
of the guest due to a PCI device error detected by AER, shutdown the
guest immediately.
Signed-off-by: Vijay Mohan Pandarathil
---
kvm-all.c | 6 ++
linux-headers/linux/kvm.h | 1 +
2 files changed, 7 inse
- Register a notifier function to be called whenever a PCIe error is
detected by the AER subsystem.
- The notifier function bumps up a global count to keep track of the
error notifications.
- Before guest entry, each vcpu checks if there has been any new
notifications sin
Add support for error containment when a PCI pass-thru device assigned to a KVM
guest encounters an error. This is for PCIe devices/drivers that support AER
functionality. When the OS is notified of an error in a device either
through the firmware first approach or through an interrupt handled by t
- Adds infrastructure support for error notifications from AER subsystem
to other subsystems. The generic notifier_chain functionality is used.
- When the AER rootport driver detects an uncorrected error, invoke the
callbacks registered for notifications as well as mark the device as
tainted.
-
- When an uncorrected recoverable error is reported via an NMI in the
firmware first model of AER, invoke the callbacks registered for
notifications as well as mark the device as tainted.
- Add a new function ghes_mark_dev_err() leveraged from ghes_do_proc()
to identify the dev
VFIO implements platform independent stuff such as
a PCI driver, BAR access (via read/write on a file descriptor
or direct mapping when possible) and IRQ signaling.
The platform dependent part includes IOMMU initialization
and handling.
This patch initializes IOMMU groups based on the IOMMU
config
On Fri, Nov 16, 2012 at 06:12:58PM +0800, zhangyanfei wrote:
> Hello Marcelo,
>
> Any thoughts?
I thought a function call was OK, but its better to have all code in
vmx.c. Please have an atomic notifier in kexec.c (registered by KVM
module via atomic_notifier_chain_register etc).
Other than that
A bug only seen with LTO enabled was reported by Ron Minnich. Since the issue
appears to be a linker issue, we disable LTO by default until it's more stable.
We can still run LTO builds by setting LTO=1.
Reported-by: Ron Minnich
Signed-off-by: Sasha Levin
---
tools/kvm/Makefile | 8 +---
1
On Mon, Nov 19, 2012 at 01:53:44PM +0100, Alexander Graf wrote:
> > +static inline unsigned long slb_pgsize_encoding(unsigned long psize)
> > +{
> > + unsigned long senc = 0;
> > +
> > + if (psize > 0x1000) {
> > + senc = SLB_VSID_L;
> > + if (psize == 0x1)
> > +
The current reexecute_instruction can not well detect the failed instruction
emulation. It allows guest to retry all the instructions except it accesses
on error pfn.
For example, some cases are nested-write-protect - if the page we want to
write is used as PDE but it chains to itself. Under this
On Mon, Nov 19, 2012 at 01:36:42PM +0100, Alexander Graf wrote:
>
> Aren't atomic reads expensive? Doing one on every guest HPTE modification
> (when nobody is listening) sounds quite excessive. Wouldn't it be cheaper to
> just always update the bit?
As Scott said, it's just an ordinary load.
Currently, reexecute_instruction refused to retry all instructions. If
nested npt is used, the emulation may be caused by shadow page, it can
be fixed by dropping the shadow page
Signed-off-by: Xiao Guangrong
---
arch/x86/kvm/x86.c | 14 --
1 files changed, 8 insertions(+), 6 delet
Little cleanup for reexecute_instruction, also use gpa_to_gfn in
retry_instruction
Signed-off-by: Xiao Guangrong
---
arch/x86/kvm/x86.c | 13 ++---
1 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 52ae8b5..7be8452 100644
--- a
The current reexecute_instruction can not well detect the failed instruction
emulation. It allows guest to retry all the instructions except it accesses
on error pfn.
For example, these cases can not be detected:
- for tdp used
currently, it refused to retry all instructions. If nested npt is us
This patchset, based on earlier work by Jeremy Fitzhardinge, implements
paravirtual clock vsyscall support.
It should be possible to implement Xen support relatively easily.
It reduces clock_gettime from 500 cycles to 200 cycles
on my testbox.
v5:
- reduce preempt disable window in kvm_get_wallc
As suggested by John, export time data similarly to how its
done by vsyscall support. This allows KVM to retrieve necessary
information to implement vsyscall support in KVM guests.
Acked-by: John Stultz
Signed-off-by: Marcelo Tosatti
Index: vsyscall/include/linux/pvclock_gtod.h
As requested by Glauber, do not update kvmclock area on vcpu->pcpu
migration, in case the host has stable TSC.
This is to reduce cacheline bouncing.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kvm/x86.c
===
--- vsysca
Originally from Jeremy Fitzhardinge.
We can copy the information directly from "struct pvclock_vcpu_time_info",
remove pvclock_shadow_time.
Reviewed-by: Glauber Costa
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kernel/pvclock.c
=
We want to expose the pvclock shared memory areas, which
the hypervisor periodically updates, to userspace.
For a linear mapping from userspace, it is necessary that
entire page sized regions are used for array of pvclock
structures.
There is no such guarantee with per cpu areas, therefore move
KVM added a global variable to guarantee monotonicity in the guest.
One of the reasons for that is that the time between
1. ktime_get_ts(×pec);
2. rdtscll(tsc);
Is variable. That is, given a host with stable TSC, suppose that
two VCPUs read the same time via ktime_get_ts() above.
Register a notifier for clocksource change event. In case
the host switches to clock other than TSC, disable master
clock usage.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kvm/x86.c
===
--- vsyscall.orig/arch/x86/kvm/x8
Originally from Jeremy Fitzhardinge.
Introduce generic, non hypervisor specific, pvclock initialization
routines.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kernel/pvclock.c
===
--- vsyscall.orig/arch/x86/kernel/pvclo
TSC initialization will soon make use of online_vcpus.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/ia64/kvm/kvm-ia64.c
===
--- vsyscall.orig/arch/ia64/kvm/kvm-ia64.c
+++ vsyscall/arch/ia64/kvm/kvm-ia64.c
@@ -1330,6 +1330,11
Originally from Jeremy Fitzhardinge.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/include/linux/sched.h
===
--- vsyscall.orig/include/linux/sched.h
+++ vsyscall/include/linux/sched.h
@@ -107,6 +107,14 @@ extern unsigned long this_
As noted by Gleb, not advertising SSE2 support implies
no RDTSC barriers.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/include/asm/pvclock.h
===
--- vsyscall.orig/arch/x86/include/asm/pvclock.h
+++ vsyscall/arch/x86/inclu
Originally from Jeremy Fitzhardinge.
So code can be reused.
Acked-by: Glauber Costa
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kernel/pvclock.c
===
--- vsyscall.orig/arch/x86/kernel/pvclock.c
+++ vsyscall/arch/x86/ker
With master clock, a pvclock clock read calculates:
ret = system_timestamp + [ (rdtsc + tsc_offset) - tsc_timestamp ]
Where 'rdtsc' is the host TSC.
system_timestamp and tsc_timestamp are unique, one tuple
per VM: the "master clock".
Given a host with synchronized TSCs, its obvious that
guest
Otherwise its possible for an unrelated KVM_REQ_UPDATE_CLOCK (such as due to CPU
migration) to clear the bit.
Noticed by Paolo Bonzini.
Reviewed-by: Gleb Natapov
Reviewed-by: Glauber Costa
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kvm/x86.c
==
Allow the caller to pass host tsc value to kvm_x86_ops->read_l1_tsc().
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/include/asm/kvm_host.h
===
--- vsyscall.orig/arch/x86/include/asm/kvm_host.h
+++ vsyscall/arch/x86/includ
Acked-by: Glauber Costa
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kernel/pvclock.c
===
--- vsyscall.orig/arch/x86/kernel/pvclock.c
+++ vsyscall/arch/x86/kernel/pvclock.c
@@ -45,6 +45,19 @@ void pvclock_resume(void)
Improve performance of time system calls when using Linux pvclock,
by reading time info from fixmap visible copy of pvclock data.
Originally from Jeremy Fitzhardinge.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/vdso/vclock_gettime.c
=
Originally from Jeremy Fitzhardinge.
pvclock_get_time_values, which contains the memory barriers
will be removed by next patch.
Signed-off-by: Marcelo Tosatti
Index: vsyscall/arch/x86/kernel/pvclock.c
===
--- vsyscall.orig/arch/x86
On Mon, Nov 19, 2012 at 04:53:42PM +0800, Asias He wrote:
> vhost-blk is an in-kernel virito-blk device accelerator.
>
> Due to lack of proper in-kernel AIO interface, this version converts
> guest's I/O request to bio and use submit_bio() to submit I/O directly.
> So this version any supports raw
From: "Michael S. Tsirkin"
Date: Mon, 19 Nov 2012 21:49:55 +0200
> On Mon, Nov 19, 2012 at 02:18:13PM -0500, David Miller wrote:
>> From: Sachin Kamat
>> Date: Mon, 19 Nov 2012 16:58:28 +0530
>>
>> > linux/vhost.h was included twice.
>> >
>> > Signed-off-by: Sachin Kamat
>>
>> Michael, are y
On Mon, Nov 19, 2012 at 02:18:13PM -0500, David Miller wrote:
> From: Sachin Kamat
> Date: Mon, 19 Nov 2012 16:58:28 +0530
>
> > linux/vhost.h was included twice.
> >
> > Signed-off-by: Sachin Kamat
>
> Michael, are you gonna take this?
>
> Thanks.
Pls pick it up.
Acked-by: Michael S. Tsirk
From: Sachin Kamat
Date: Mon, 19 Nov 2012 16:58:28 +0530
> linux/vhost.h was included twice.
>
> Signed-off-by: Sachin Kamat
Michael, are you gonna take this?
Thanks.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More m
On Sun, 2012-11-18 at 11:13 +0200, Michael S. Tsirkin wrote:
> On Sat, Nov 17, 2012 at 12:35:29AM +, Ben Hutchings wrote:
> > On Tue, 2012-11-13 at 08:40 +0200, Michael S. Tsirkin wrote:
> > > On Mon, Nov 05, 2012 at 11:38:39AM +1030, Rusty Russell wrote:
> > > > > @@ -924,11 +1032,10 @@ static
CONFIG_HOTPLUG is going away as an option so __devinit is no longer
needed.
Signed-off-by: Bill Pemberton
Cc: "Hans J. Koch" )
Cc: kvm@vger.kernel.org
---
drivers/uio/uio_aec.c | 2 +-
drivers/uio/uio_cif.c | 2 +-
drivers/uio/uio_netx.c| 2 +-
drivers/uio/uio_pci_gener
On 19.11.2012, at 18:20, Scott Wood wrote:
> On 11/19/2012 06:36:42 AM, Alexander Graf wrote:
>> On 14.11.2012, at 05:32, Paul Mackerras wrote:
>> > +/*
>> > + * Note modification of an HPTE; set the HPTE modified bit
>> > + * if it wasn't modified before and anyone is interested.
>> > + */
>> >
On 11/19/2012 06:36:42 AM, Alexander Graf wrote:
On 14.11.2012, at 05:32, Paul Mackerras wrote:
> +/*
> + * Note modification of an HPTE; set the HPTE modified bit
> + * if it wasn't modified before and anyone is interested.
> + */
> +static inline void note_hpte_modification(struct kvm *kvm,
>
On Thu, Nov 8, 2012 at 4:26 PM, Peter Lieven wrote:
> Has anyone any other idea what the cause could be or where to start?
Hi Peter,
I suggested posting the source tree you are building. Since you have
applied patches yourself no one else is able to follow along with the
gdb output or reproduce
On Mon, Nov 19, 2012 at 04:09:06PM +, Christoffer Dall wrote:
> On Mon, Nov 19, 2012 at 10:26 AM, Will Deacon wrote:
> > On Mon, Nov 19, 2012 at 03:04:38PM +, Christoffer Dall wrote:
> In all seriousness, I will unite myself with an alcoholic beverage one
> of these evenings and try to see
On Mon, Nov 19, 2012 at 10:26 AM, Will Deacon wrote:
> On Mon, Nov 19, 2012 at 03:04:38PM +, Christoffer Dall wrote:
>> On Mon, Nov 19, 2012 at 9:55 AM, Will Deacon wrote:
>> > On Sat, Nov 10, 2012 at 03:42:59PM +, Christoffer Dall wrote:
>> >> +int kvm_vm_ioctl_irq_line(struct kvm *kvm,
On 19 November 2012 15:01, Will Deacon wrote:
> On Sat, Nov 10, 2012 at 03:43:13PM +, Christoffer Dall wrote:
>> +/*
>> + * A15-specific CP15 registers.
>> + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
>> + */
>> +static const struct coproc_reg a15_regs[] = {
>> + /* MPID
On 11/19/2012 09:51 AM, Will Deacon wrote:
Typo in subject, use one of initiali[sz]ation instead.
On Sat, Nov 10, 2012 at 03:42:45PM +, Christoffer Dall wrote:
Sets up KVM code to handle all exceptions taken to Hyp mode.
When the kernel is booted in Hyp mode, calling "hvc #0xff" with r0 p
On Mon, Nov 19, 2012 at 03:04:38PM +, Christoffer Dall wrote:
> On Mon, Nov 19, 2012 at 9:55 AM, Will Deacon wrote:
> > On Sat, Nov 10, 2012 at 03:42:59PM +, Christoffer Dall wrote:
> >> +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level
> >> *irq_level)
> >> +{
> >> +
Greetings all,
I am running Ubuntu-Precise 3.2.0-29-generic #46, with stock KVM ("QEMU
emulator version 1.0 (qemu-kvm-1.0)") on a Dell R510 server. I have one
dual-port Intel's NIC 82599, of which I spawn 32 VFs from each port. I spawn
virtual machines with KVM, each VM has 4 VFs attached (two
On Sat, Nov 10, 2012 at 03:43:49PM +, Christoffer Dall wrote:
> When the guest accesses I/O memory this will create data abort
> exceptions and they are handled by decoding the HSR information
> (physical address, read/write, length, register) and forwarding reads
> and writes to QEMU which per
On Sat, Nov 10, 2012 at 03:43:42PM +, Christoffer Dall wrote:
> Handles the guest faults in KVM by mapping in corresponding user pages
> in the 2nd stage page tables.
>
> We invalidate the instruction cache by MVA whenever we map a page to the
> guest (no, we cannot only do it when we have an
On Mon, Nov 19, 2012 at 9:53 AM, Will Deacon wrote:
> On Sat, Nov 10, 2012 at 03:42:52PM +, Christoffer Dall wrote:
>> This commit introduces the framework for guest memory management
>> through the use of 2nd stage translation. Each VM has a pointer
>> to a level-1 table (the pgd field in str
On Mon, Nov 19, 2012 at 9:55 AM, Will Deacon wrote:
> On Sat, Nov 10, 2012 at 03:42:59PM +, Christoffer Dall wrote:
>> From: Christoffer Dall
>>
>> All interrupt injection is now based on the VM ioctl KVM_IRQ_LINE. This
>> works semantically well for the GIC as we in fact raise/lower a line
On Sat, Nov 10, 2012 at 03:43:28PM +, Christoffer Dall wrote:
> The Cache Size Selection Register (CSSELR) selects the current Cache
> Size ID Register (CCSIDR). You write which cache you are interested
> in to CSSELR, and read the information out of CCSIDR.
>
> Which cache numbers are valid
On Sat, Nov 10, 2012 at 03:43:21PM +, Christoffer Dall wrote:
> The following three ioctls are implemented:
> - KVM_GET_REG_LIST
> - KVM_GET_ONE_REG
> - KVM_SET_ONE_REG
[...]
> diff --git a/Documentation/virtual/kvm/api.txt
> b/Documentation/virtual/kvm/api.txt
> index 845ceda..9671cd2
On Sat, Nov 10, 2012 at 03:43:13PM +, Christoffer Dall wrote:
> Adds a new important function in the main KVM/ARM code called
> handle_exit() which is called from kvm_arch_vcpu_ioctl_run() on returns
> from guest execution. This function examines the Hyp-Syndrome-Register
> (HSR), which contain
On Sat, Nov 10, 2012 at 03:43:06PM +, Christoffer Dall wrote:
> Provides complete world-switch implementation to switch to other guests
> running in non-secure modes. Includes Hyp exception handlers that
> capture necessary exception information and stores the information on
> the VCPU and KVM
On Sat, Nov 10, 2012 at 03:42:59PM +, Christoffer Dall wrote:
> From: Christoffer Dall
>
> All interrupt injection is now based on the VM ioctl KVM_IRQ_LINE. This
> works semantically well for the GIC as we in fact raise/lower a line on
> a machine component (the gic). The IOCTL uses the fo
On Sat, Nov 10, 2012 at 03:42:52PM +, Christoffer Dall wrote:
> This commit introduces the framework for guest memory management
> through the use of 2nd stage translation. Each VM has a pointer
> to a level-1 table (the pgd field in struct kvm_arch) which is
> used for the 2nd stage translatio
Typo in subject, use one of initiali[sz]ation instead.
On Sat, Nov 10, 2012 at 03:42:45PM +, Christoffer Dall wrote:
> Sets up KVM code to handle all exceptions taken to Hyp mode.
>
> When the kernel is booted in Hyp mode, calling "hvc #0xff" with r0 pointing to
> the new vectors, the HVBAR
On Mon, Nov 19, 2012 at 6:29 AM, Sundaram, Senthilkumar
wrote:
> What is the use of MMU Notifiers in the absence of Shadow Page Table?
>
> Thanks
> Senthil
MMU notifiers are used to manage the stage-2 page tables in the event
of swapping or KSM. Please don't top-top post to this list.
-Christoff
On Sat, Nov 10, 2012 at 03:42:38PM +, Christoffer Dall wrote:
> Targets KVM support for Cortex A-15 processors.
>
> Contains all the framework components, make files, header files, some
> tracing functionality, and basic user space API.
>
> Only supported core is Cortex-A15 for now.
>
> Most
On 11/10/2012 09:42 AM, Christoffer Dall wrote:
> Add a method (hyp_idmap_setup) to populate a hyp pgd with an
> identity mapping of the code contained in the .hyp.idmap.text
> section.
>
> Offer a method to drop this identity mapping through
> hyp_idmap_teardown.
>
> Make all the above depend on
On Sat, Nov 10, 2012 at 03:42:31PM +, Christoffer Dall wrote:
> Decoding the implementor and part number of the CPU id in the CPU ID
> register is needed by KVM, so we factor it out to share the code.
>
> Reviewed-by: Marcelo Tosatti
> Signed-off-by: Christoffer Dall
[...]
> diff --git a/a
On Sat, Nov 10, 2012 at 03:42:24PM +, Christoffer Dall wrote:
> Add a method (hyp_idmap_setup) to populate a hyp pgd with an
> identity mapping of the code contained in the .hyp.idmap.text
> section.
>
> Offer a method to drop this identity mapping through
> hyp_idmap_teardown.
>
> Make all t
On Sat, Nov 10, 2012 at 03:42:17PM +, Christoffer Dall wrote:
> KVM uses the stage-2 page tables and the Hyp page table format,
> so we define the fields and page protection flags needed by KVM.
>
> The nomenclature is this:
> - page_hyp:PL2 code/data mappings
> - page_hyp_device: PL
On 31.10.2012, at 17:24, Cornelia Huck wrote:
> Provide a mechanism for qemu to provide fully virtual subchannels to
> the guest. In the KVM case, this relies on the kernel's css support
> for I/O and machine check interrupt handling. The !KVM case handles
> interrupts on its own.
>
> Signed-off
On 14.11.2012, at 05:31, Paul Mackerras wrote:
> This restructures the code that creates HPT (hashed page table)
> entries so that it can be called in situations where we don't have a
> struct vcpu pointer, only a struct kvm pointer. It also fixes a bug
> where kvmppc_map_vrma() would corrupt th
On 14.11.2012, at 05:33, Paul Mackerras wrote:
> A new ioctl, KVM_PPC_GET_HTAB_FD, returns a file descriptor. Reads on
> this fd return the contents of the HPT (hashed page table), writes
> create and/or remove entries in the HPT. There is a new capability,
> KVM_CAP_PPC_HTAB_FD, to indicate th
On 14.11.2012, at 05:32, Paul Mackerras wrote:
> This uses a bit in our record of the guest view of the HPTE to record
> when the HPTE gets modified. We use a reserved bit for this, and ensure
> that this bit is always cleared in HPTE values returned to the guest.
> The recording of modified HPT
Hi
Please send in any agenda topics you are interested in.
Later, Juan.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Hi Will,
On Mon, 19 Nov 2012, Will Deacon wrote:
> > > I'm struggling to reproduce this with my tree. Can you confirm whether or
> > > not you have commit 29fc7c5a4f51 ("rbtree: include linux/compiler.h for
> > > definition of __always_inline") in your *kernel* sources please?
> >
> > No, I don't
linux/vhost.h was included twice.
Signed-off-by: Sachin Kamat
---
drivers/vhost/tcm_vhost.c |1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c
index 73bbc46..798792b 100644
--- a/drivers/vhost/tcm_vhost.c
+++ b/drivers/v
What is the use of MMU Notifiers in the absence of Shadow Page Table?
Thanks
Senthil
> -Original Message-
> From: kvmarm-boun...@lists.cs.columbia.edu [mailto:kvmarm-
> boun...@lists.cs.columbia.edu] On Behalf Of Christoffer Dall
> Sent: Monday, October 22, 2012 12:20 PM
> To: kvm@vger.ker
On Fri, Nov 16, 2012 at 10:01:01PM +, Pekka Enberg wrote:
> On Fri, 16 Nov 2012, Will Deacon wrote:
> > > I'm seeing the following breakage with this patch applied:
> > >
> > > [penberg@tux kvm]$ make
> > > CC hw/rtc.o
> > > CC ioport.o
> > > CC kvm-cpu.o
> > > CC
On Thu, Nov 15, 2012 at 12:25:45PM -0800, Will Auld wrote:
> In order to track who initiated the call (host or guest) to modify an msr
> value I have changed function call parameters along the call path. The
> specific change is to add a struct pointer parameter that points to (index,
> data, calle
vhost-blk is an in-kernel virito-blk device accelerator.
Due to lack of proper in-kernel AIO interface, this version converts
guest's I/O request to bio and use submit_bio() to submit I/O directly.
So this version any supports raw block device as guest's disk image,
e.g. /dev/sda, /dev/ram0. We ca
Hi,
on one of our servers, windows 2008 KVM suddenly crashed. I see following
in libvirt log:
*** glibc detected *** /usr/bin/qemu-kvm: double free or corruption (!prev):
0x7fc634008cd0 ***
=== Backtrace: =
/lib64/libc.so.6(+0x75916)[0x7fc9026f4916]
/lib64/libc.so.6(+0x78443)[0x7f
77 matches
Mail list logo
