Hi, all
I am testing the performance of xen netfront-netback driver that with
multi-queues support. The throughput from domU to remote dom0 is 9.2Gb/s, but
the throughput from domU to remote domU is only 3.6Gb/s, I think the bottleneck
is the throughput from dom0 to local domU. However, we h
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> This should be based on a new parameter globally, 'pci_rdmforce'.
>
> pci_rdmforce = 1 => Of course this should be 0 by default.
>
> '1' means we should force check to reserve all ranges. If failed
> VM wouldn't be created succes
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> We will introduce that hypercall xc_reserved_device_memory_map
> approach to libxc.
>
> Signed-off-by: Tiejun Chen
Reviewed-by: Kevin Tian
> ---
> tools/libxc/include/xenctrl.h | 5 +
> tools/libxc/xc_domain.c | 30
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> After we intend to expost that hypercall explicitly based on
> XEN_DOMCTL_set_rdm, we need this rebase. I hope we can squash
> this into that previous patch once Jan Ack this.
better to merge together, since it's the right thing t
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> In case of reserved device memory overlapping with ram, it also probably
> overlap with modules space so we need to check these reserved device
> memory as well.
>
> Signed-off-by: Tiejun Chen
Reviewed-by: Kevin Tian , with one
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> We need to use reserved device memory maps with multiple times, so
> provide just one common function should be friend.
>
> Signed-off-by: Tiejun Chen
> ---
> tools/firmware/hvmloader/util.c | 59
> ++
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> We need to make sure all mmio allocation don't overlap
> any rdm, reserved device memory. Here we just skip
> all reserved device memory range in mmio space.
>
> Signed-off-by: Tiejun Chen
> ---
> tools/firmware/hvmloader/pci.c
On Mon, 2014-12-01 at 23:41 +, Mark Pryor wrote:
> list,
Thanks. If you've identified a buggy changeset then it is fine to post
to the devel lists. I've added a CC. I've also CCd everyone listed in
the commit which you've fingered.
Olaf, does this suggested change look correct? If so then can
flight 31980 linux-linus real [real]
http://www.chiark.greenend.org.uk/~xensrcts/logs/31980/
Regressions :-(
Tests which did not succeed and are blocking,
including tests which could not be run:
test-amd64-i386-rumpuserxen-i386 3 host-install(3) broken REGR. vs. 31241
test-amd64-i386-libvi
>>> On 02.12.14 at 08:48, wrote:
>
> On 12/1/2014 8:31 PM, Jan Beulich wrote:
> On 01.12.14 at 13:13, wrote:
>>> At 11:17 + on 01 Dec (1417429027), Jan Beulich wrote:
>>> On 01.12.14 at 11:30, wrote:
> At 09:32 + on 01 Dec (1417422746), Jan Beulich wrote:
> On 01.12
Hi,
looking into the upstream linux sources I realized that the PVHVM
drivers of XEN are only available with the pvops kernel. Is this on
purpose? Shouldn't the frontend drivers, xen/platform-pci.c etc. be
configurable without having to enable CONFIG_PARAVIRT?
Juergen
__
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> We need to check to reserve all reserved device memory maps in e820
> to avoid any potential guest memory conflict.
>
> Currently, if we can't insert RDM entries directly, we may need to handle
> several ranges as follows:
> a. Fi
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> In some cases like igd_opregion_pgbase, guest will use mem_hole_alloc
> to allocate some memory to use in runtime cycle, so we alsoe need to
> make sure all reserved device memory don't overlap such a region.
OK, seems you meant t
>>> On 01.12.14 at 20:22, wrote:
> xc_physdev_unmap_pirq might revoke the permission to map the irq from
> the domain causing the following xc_domain_irq_permission call to fail
> and return error (domain_pirq_to_irq returns 0).
Apart from the patch title being rather confusing, isn't the root
pr
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:24 PM
>
> We need to reject to populate reserved device memory mapping, and
> then make sure all reserved device memory can't be accessed by any
> !iommu approach.
>
> Signed-off-by: Tiejun Chen
> ---
> xen/arch/x86/mm/p2m.c | 59
> ++
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:25 PM
>
> We always reserve these ranges since we never allow any stuff to
> poke them.
>
> But in theory some untrusted VM can maliciously access them. So we
> need to intercept this approach. But we just don't want to leak
> anything or i
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:25 PM
>
> We will create RMRR mapping as follows:
>
> If gfn space unoccupied, we just set that. If
> space already occupy by 1:1 RMRR mapping do thing. Others
> should be failed.
>
> Signed-off-by: Tiejun Chen
Reviewed-by: Kevin Tian
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:25 PM
>
> intel_iommu_map_page() does nothing if VT-d shares EPT page table.
> So rmrr_identity_mapping() never create RMRR mapping but in some
> cases like some GFX drivers it still need to access RMRR.
>
> Here we will create those RMRR m
Rename lock to maptrack_lock and use it to protect maptrack state.
The new rwlock is used to prevent readers from accessing
inconsistent grant table state such as current
version, partially initialized active table pages,
etc.
Signed-off-by: Matt Wilson
[chegger: ported to xen-staging, split int
This patch series changes the grant table locking to
a more fain grained locking protocol. The result is
a performance boost measured with blkfront/blkback.
Document the locking protocol.
[PATCH 1/2] gnttab: Introduce rwlock to protect updates to grant
[PATCH 2/2] gnttab: refactor locking for scal
From: Matt Wilson
This patch refactors grant table locking. It splits the previous
single spinlock per grant table into multiple locks. The heavily
modified components of the grant table (the maptrack state and the
active entries) are now protected by their own spinlocks. The
remaining elements o
>>> On 21.11.14 at 23:17, wrote:
> Konrad Rzeszutek Wilk (7):
> xen/pciback: Don't deadlock when unbinding.
> driver core: Provide an wrapper around the mutex to do lockdep warnings
> xen/pciback: Include the domain id if removing the device whilst still
> in use
> xen/pci
> From: Chen, Tiejun
> Sent: Monday, December 01, 2014 5:25 PM
>
> Sometimes different devices may share RMRR range so in this
> case we shouldn't assign these devices into different VMs
> since they may have potential leakage even damage between VMs.
>
> So we need to group all devices as RMRR r
At 12:31 + on 01 Dec (1417433464), Jan Beulich wrote:
> >>> On 01.12.14 at 13:13, wrote:
> > At 11:17 + on 01 Dec (1417429027), Jan Beulich wrote:
> >> >>> On 01.12.14 at 11:30, wrote:
> >> > At 09:32 + on 01 Dec (1417422746), Jan Beulich wrote:
> >> >> >>> On 01.12.14 at 09:49, wrot
On 02/12/14 09:39, Juergen Gross wrote:
> Hi,
>
> looking into the upstream linux sources I realized that the PVHVM
> drivers of XEN are only available with the pvops kernel. Is this on
> purpose? Shouldn't the frontend drivers, xen/platform-pci.c etc. be
> configurable without having to enable CO
On Tue, 2 Dec 2014, Jan Beulich wrote:
> >>> On 01.12.14 at 20:22, wrote:
> > xc_physdev_unmap_pirq might revoke the permission to map the irq from
> > the domain causing the following xc_domain_irq_permission call to fail
> > and return error (domain_pirq_to_irq returns 0).
>
> Apart from the pa
On 02/12/14 08:30, zhangleiqiang wrote:
> Hi, all
> I am testing the performance of xen netfront-netback driver that
> with multi-queues support. The throughput from domU to remote dom0 is
> 9.2Gb/s, but the throughput from domU to remote domU is only 3.6Gb/s, I
> think the bottleneck is the th
On 02/12/14 10:06, Christoph Egger wrote:
> This patch series changes the grant table locking to
> a more fain grained locking protocol. The result is
> a performance boost measured with blkfront/blkback.
> Document the locking protocol.
>
> [PATCH 1/2] gnttab: Introduce rwlock to protect updates t
On Tue, Dec 02, 2014 at 04:30:49PM +0800, zhangleiqiang wrote:
> Hi, all
> I am testing the performance of xen netfront-netback driver that with
> multi-queues support. The throughput from domU to remote dom0 is 9.2Gb/s, but
> the throughput from domU to remote domU is only 3.6Gb/s, I think t
On 12/02/2014 11:54 AM, David Vrabel wrote:
On 02/12/14 09:39, Juergen Gross wrote:
Hi,
looking into the upstream linux sources I realized that the PVHVM
drivers of XEN are only available with the pvops kernel. Is this on
purpose? Shouldn't the frontend drivers, xen/platform-pci.c etc. be
confi
>>> On 02.12.14 at 11:37, wrote:
> At 12:31 + on 01 Dec (1417433464), Jan Beulich wrote:
>> >>> On 01.12.14 at 13:13, wrote:
>> > At 11:17 + on 01 Dec (1417429027), Jan Beulich wrote:
>> >> >>> On 01.12.14 at 11:30, wrote:
>> >> > At 09:32 + on 01 Dec (1417422746), Jan Beulich wrote:
On Tue, 2014-12-02 at 10:54 +, David Vrabel wrote:
> On 02/12/14 09:39, Juergen Gross wrote:
> > Hi,
> >
> > looking into the upstream linux sources I realized that the PVHVM
> > drivers of XEN are only available with the pvops kernel. Is this on
> > purpose? Shouldn't the frontend drivers, xe
On 2014/12/02 12:00, Andrew Cooper wrote:
> On 02/12/14 10:06, Christoph Egger wrote:
>> This patch series changes the grant table locking to
>> a more fain grained locking protocol. The result is
>> a performance boost measured with blkfront/blkback.
>> Document the locking protocol.
>>
>> [PATCH
On 01/12/14 22:36, Luis R. Rodriguez wrote:
>
> Then I do agree its a fair analogy (and find this obviously odd that how
> widespread cond_resched() is), we just don't have an equivalent for IRQ
> context, why not avoid the special check then and use this all the time in the
> middle of a hypercal
>>> On 02.12.14 at 11:55, wrote:
> On Tue, 2 Dec 2014, Jan Beulich wrote:
>> >>> On 01.12.14 at 20:22, wrote:
>> > xc_physdev_unmap_pirq might revoke the permission to map the irq from
>> > the domain causing the following xc_domain_irq_permission call to fail
>> > and return error (domain_pirq_t
On 02/12/14 10:06, Christoph Egger wrote:
> Rename lock to maptrack_lock and use it to protect maptrack state.
>
> The new rwlock is used to prevent readers from accessing
> inconsistent grant table state such as current
> version, partially initialized active table pages,
> etc.
I would suggest p
On 12/02/2014 12:05 PM, Ian Campbell wrote:
On Tue, 2014-12-02 at 10:54 +, David Vrabel wrote:
On 02/12/14 09:39, Juergen Gross wrote:
Hi,
looking into the upstream linux sources I realized that the PVHVM
drivers of XEN are only available with the pvops kernel. Is this on
purpose? Shouldn'
On Tue, 2014-12-02 at 12:33 +0100, Juergen Gross wrote:
> On 12/02/2014 12:05 PM, Ian Campbell wrote:
> > On Tue, 2014-12-02 at 10:54 +, David Vrabel wrote:
> >> On 02/12/14 09:39, Juergen Gross wrote:
> >>> Hi,
> >>>
> >>> looking into the upstream linux sources I realized that the PVHVM
> >>>
On 12/02/2014 12:36 PM, Ian Campbell wrote:
On Tue, 2014-12-02 at 12:33 +0100, Juergen Gross wrote:
On 12/02/2014 12:05 PM, Ian Campbell wrote:
On Tue, 2014-12-02 at 10:54 +, David Vrabel wrote:
On 02/12/14 09:39, Juergen Gross wrote:
Hi,
looking into the upstream linux sources I realize
At 15:38 +0800 on 02 Dec (1417531126), Yu, Zhang wrote:
> On 12/1/2014 8:13 PM, Tim Deegan wrote:
> > At 11:17 + on 01 Dec (1417429027), Jan Beulich wrote:
> > On 01.12.14 at 11:30, wrote:
> >>> During this bit of archaeology I realised that either this new type
> >>> should _not_ be made
On Mon, 1 Dec 2014, Don Slutz wrote:
> On 11/25/14 12:54, Stefano Stabellini wrote:
> > In libxl_set_memory_target when setting the new maxmem, retain the same
> > offset on top of the current target. The offset includes memory
> > allocated by QEMU for rom files.
> >
> > Signed-off-by: Stefano St
>>> On 02.12.14 at 12:40, wrote:
> At 15:38 +0800 on 02 Dec (1417531126), Yu, Zhang wrote:
>> 2> p2m_grant_map_ro is also supposed to be discarded? Will handling of
>> this type of pages goes into __hvm_copy()/__hvm_clear(), or should?
>
> I think so, yes. At the moment we inject #GP when the g
> -Original Message-
> From: xen-devel-boun...@lists.xen.org
> [mailto:xen-devel-boun...@lists.xen.org] On Behalf Of Wei Liu
> Sent: Tuesday, December 02, 2014 7:02 PM
> To: zhangleiqiang
> Cc: wei.l...@citrix.com; xen-devel@lists.xen.org
> Subject: Re: [Xen-devel] Poor network performance
> -Original Message-
> From: xen-devel-boun...@lists.xen.org
> [mailto:xen-devel-boun...@lists.xen.org] On Behalf Of David Vrabel
> Sent: Tuesday, December 02, 2014 6:57 PM
> To: zhangleiqiang; xen-devel@lists.xen.org
> Subject: Re: [Xen-devel] Poor network performance between DomU with
> m
In libxl_set_memory_target when setting the new maxmem, retain the same
offset on top of the current target. The offset includes memory
allocated by QEMU for rom files.
Signed-off-by: Stefano Stabellini
---
Changes in v2:
- call libxl_domain_info instead of libxl_dominfo_init;
- call libxl_doma
On 02/12/14 11:33, Juergen Gross wrote:
>
> I think we have customers wanting to run a default kernel as domU. So it
> isn't always the distro refusing paravirt, it might be the user...
I don't think this is a sensible use case but I'm not adverse to
improving the set of Xen config options.
> To
On Tue, Dec 02, 2014 at 11:50:59AM +, Zhangleiqiang (Trump) wrote:
> > -Original Message-
> > From: xen-devel-boun...@lists.xen.org
> > [mailto:xen-devel-boun...@lists.xen.org] On Behalf Of Wei Liu
> > Sent: Tuesday, December 02, 2014 7:02 PM
> > To: zhangleiqiang
> > Cc: wei.l...@citri
flight 31983 qemu-mainline real [real]
http://www.chiark.greenend.org.uk/~xensrcts/logs/31983/
Regressions :-(
Tests which did not succeed and are blocking,
including tests which could not be run:
test-amd64-i386-xl-qemut-debianhvm-amd64 5 xen-boot fail REGR. vs. 31947
Regressions which a
On Mon, 1 Dec 2014, Don Slutz wrote:
> On 12/01/14 10:37, Stefano Stabellini wrote:
> > On Mon, 1 Dec 2014, Don Slutz wrote:
> > > On 11/27/14 05:48, Stefano Stabellini wrote:
>
> [...]
>
> > >
> > > Works fine in both claim modes and with PoD used (maxmem > memory). Do
> > > not know how to te
Hi Christoph,
On 02/12/14 10:06, Christoph Egger wrote:
> diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
> index 522c43d..37c13b1 100644
> --- a/xen/arch/x86/mm.c
> +++ b/xen/arch/x86/mm.c
> @@ -4565,7 +4565,7 @@ int xenmem_add_to_physmap_one(
> mfn = virt_to_mfn(d->shared_inf
On 12/02/2014 12:59 PM, David Vrabel wrote:
On 02/12/14 11:33, Juergen Gross wrote:
I think we have customers wanting to run a default kernel as domU. So it
isn't always the distro refusing paravirt, it might be the user...
I don't think this is a sensible use case but I'm not adverse to
impr
On 2014/12/02 13:35, Julien Grall wrote:
> Hi Christoph,
>
> On 02/12/14 10:06, Christoph Egger wrote:
>> diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
>> index 522c43d..37c13b1 100644
>> --- a/xen/arch/x86/mm.c
>> +++ b/xen/arch/x86/mm.c
>> @@ -4565,7 +4565,7 @@ int xenmem_add_to_physmap_one
Hi,
On 02/12/14 13:03, Egger, Christoph wrote:
> On 2014/12/02 13:35, Julien Grall wrote:
>> Hi Christoph,
>>
>> On 02/12/14 10:06, Christoph Egger wrote:
>>> diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
>>> index 522c43d..37c13b1 100644
>>> --- a/xen/arch/x86/mm.c
>>> +++ b/xen/arch/x86/mm.
On 12/02/14 06:53, Stefano Stabellini wrote:
In libxl_set_memory_target when setting the new maxmem, retain the same
offset on top of the current target. The offset includes memory
allocated by QEMU for rom files.
Signed-off-by: Stefano Stabellini
---
Changes in v2:
- call libxl_domain_info in
On 2014/12/02 14:08, Julien Grall wrote:
> Hi,
>
> On 02/12/14 13:03, Egger, Christoph wrote:
>> On 2014/12/02 13:35, Julien Grall wrote:
>>> Hi Christoph,
>>>
>>> On 02/12/14 10:06, Christoph Egger wrote:
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 522c43d..37c13b1 100644
>
On Fri, 2014-11-28 at 16:53 +, Stefano Stabellini wrote:
CCing Boris because he was fixing a similar sounding issue in the same
area. Not sure if this is related to those patches or not.
> On do_pci_remove when QEMU returns error, we just bail out early without
> resetting the device. On doma
On Mon, 2014-12-01 at 12:19 +, Wei Liu wrote:
> On Mon, Dec 01, 2014 at 09:42:13AM +, Ian Campbell wrote:
> > On Sat, 2014-11-29 at 21:23 -0800, Ed Swierk wrote:
> > > - Use %lex-param instead of obsolete YYLEX_PARAM to override lex scanner
> > > parameter
> > > - Change deprecated %name-
On Mon, 2014-12-01 at 16:14 -0500, Konrad Rzeszutek Wilk wrote:
> On Fri, Nov 28, 2014 at 11:38:52AM +, Ian Campbell wrote:
> > On Thu, 2014-11-27 at 12:34 +, Andrew Cooper wrote:
> > > Don't leak a 16k allocation if PyArg_ParseTupleAndKeywords() or the first
> > > xc_readconsolering() fail
On Fri, 2014-11-28 at 15:17 +, Julien Grall wrote:
> Some platforms (such as Xgene and ARMv8 models) use an edge-triggered
> interrupt
> for the virtual timer. Even if the timer output signal is masked in the
> context switch, the GIC will keep track that of any interrupts raised
> while IRQs
On 02/12/14 13:47, Ian Campbell wrote:
> On Mon, 2014-12-01 at 12:19 +, Wei Liu wrote:
>> On Mon, Dec 01, 2014 at 09:42:13AM +, Ian Campbell wrote:
>>> On Sat, 2014-11-29 at 21:23 -0800, Ed Swierk wrote:
- Use %lex-param instead of obsolete YYLEX_PARAM to override lex scanner
pa
On Tue, 2014-12-02 at 02:43 +, Andrew Cooper wrote:
> On 01/12/2014 20:30, Konrad Rzeszutek Wilk wrote:
> > On Fri, Nov 28, 2014 at 11:31:24AM +, Ian Campbell wrote:
> >> On Tue, 2014-11-25 at 11:11 -0500, Boris Ostrovsky wrote:
> >>> c/s d1b93ea causes substantial functional regressions in
Hi Ian,
On 02/12/14 13:54, Ian Campbell wrote:
> On Fri, 2014-11-28 at 15:17 +, Julien Grall wrote:
>> Some platforms (such as Xgene and ARMv8 models) use an edge-triggered
>> interrupt
>> for the virtual timer. Even if the timer output signal is masked in the
>> context switch, the GIC will
On 02/12/14 13:00, Juergen Gross wrote:
>
> I'd see:
> - XEN_PV (selects PARAVIRT, XEN_FRONTEND): be able to run as pv-domain
> (x86 only)
Depends on PARAVIRT perhaps?
> - XEN_PVHVM (selects XEN_FRONTEND): be able to run as hvm-domain with
> pv-drivers
> - XEN_BACKEND (selects PARAVIRT if x8
On Mon, 2014-12-01 at 11:31 +, Wei Liu wrote:
> Free strings returned by libxl_basename after used.
>
> Signed-off-by: Wei Liu
> Cc: Ian Campbell
> Cc: Ian Jackson
> ---
> tools/libxl/xl_cmdimpl.c |8 ++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/tools/li
On Tue, 2014-12-02 at 14:08 +, Julien Grall wrote:
> Hi Ian,
>
> On 02/12/14 13:54, Ian Campbell wrote:
> > On Fri, 2014-11-28 at 15:17 +, Julien Grall wrote:
> >> Some platforms (such as Xgene and ARMv8 models) use an edge-triggered
> >> interrupt
> >> for the virtual timer. Even if the
On Tue, Dec 02, 2014 at 02:19:49PM +, Ian Campbell wrote:
> On Mon, 2014-12-01 at 11:31 +, Wei Liu wrote:
> > Free strings returned by libxl_basename after used.
> >
> > Signed-off-by: Wei Liu
> > Cc: Ian Campbell
> > Cc: Ian Jackson
> > ---
> > tools/libxl/xl_cmdimpl.c |8 ++--
On Tue, 2 Dec 2014, Don Slutz wrote:
> On 12/02/14 06:53, Stefano Stabellini wrote:
> > In libxl_set_memory_target when setting the new maxmem, retain the same
> > offset on top of the current target. The offset includes memory
> > allocated by QEMU for rom files.
> >
> > Signed-off-by: Stefano St
On 02/12/14 14:21, Ian Campbell wrote:
> On Tue, 2014-12-02 at 14:08 +, Julien Grall wrote:
>> Hi Ian,
>>
>> On 02/12/14 13:54, Ian Campbell wrote:
>>> On Fri, 2014-11-28 at 15:17 +, Julien Grall wrote:
Some platforms (such as Xgene and ARMv8 models) use an edge-triggered
interru
On 12/02/2014 03:09 PM, David Vrabel wrote:
On 02/12/14 13:00, Juergen Gross wrote:
I'd see:
- XEN_PV (selects PARAVIRT, XEN_FRONTEND): be able to run as pv-domain
(x86 only)
Depends on PARAVIRT perhaps?
Chicken and egg problem? :-)
I'd say select, as PARAVIRT isn't a primary function t
On Tue, 2014-12-02 at 14:32 +, Julien Grall wrote:
> On 02/12/14 14:21, Ian Campbell wrote:
> > On Tue, 2014-12-02 at 14:08 +, Julien Grall wrote:
> >> Hi Ian,
> >>
> >> On 02/12/14 13:54, Ian Campbell wrote:
> >>> On Fri, 2014-11-28 at 15:17 +, Julien Grall wrote:
> Some platforms
Thanks for your reply, Wei.
I do the following testing just now and found the results as follows:
There are three DomUs (4U4G) are running on Host A (6U6G) and one DomU (4U4G)
is running on Host B (6U6G), I send packets from three DomUs to the DomU on
Host B simultaneously.
1. The "top" outpu
Hi,
CC Tamas as he did some work on memaccess for ARM.
On 01/12/14 09:24, Tiejun Chen wrote:
> We can't expost those reserved device memory in case of mem_access
s/expost/expose/
> since any access may corrupt device usage.
>
> Signed-off-by: Tiejun Chen
> ---
> xen/common/mem_access.c | 41
From: Matt Wilson
This patch refactors grant table locking. It splits the previous
single spinlock per grant table into multiple locks. The heavily
modified components of the grant table (the maptrack state and the
active entries) are now protected by their own spinlocks. The
remaining elements o
Split grant table lock into two separate locks. One to protect
maptrack state and change the other into a rwlock.
The rwlock is used to prevent readers from accessing
inconsistent grant table state such as current
version, partially initialized active table pages,
etc.
Signed-off-by: Matt Wilson
This patch series changes the grant table locking to
a more fain grained locking protocol. The result is
a performance boost measured with blkfront/blkback.
Document the locking protocol.
Christoph Egger (1):
gnttab: Introduce rwlock to protect updates to grant table state
Matt Wilson (1):
gn
In general initial conring size is sufficient. However, if log
level is increased on platforms which have e.g. huge number
of memory regions (I have an IBM System x3550 M2 with 8 GiB RAM
which has more than 200 entries in EFI memory map) then some
of earlier messages in console ring are overwritten
On 12/02/14 09:26, Stefano Stabellini wrote:
On Tue, 2 Dec 2014, Don Slutz wrote:
On 12/02/14 06:53, Stefano Stabellini wrote:
In libxl_set_memory_target when setting the new maxmem, retain the same
offset on top of the current target. The offset includes memory
allocated by QEMU for rom files.
On 02/12/14 14:57, Daniel Kiper wrote:
> In general initial conring size is sufficient. However, if log
> level is increased on platforms which have e.g. huge number
> of memory regions (I have an IBM System x3550 M2 with 8 GiB RAM
> which has more than 200 entries in EFI memory map) then some
> of
On Tue, Dec 02, 2014 at 10:10:11AM +, Jan Beulich wrote:
> >>> On 21.11.14 at 23:17, wrote:
> > Konrad Rzeszutek Wilk (7):
> > xen/pciback: Don't deadlock when unbinding.
> > driver core: Provide an wrapper around the mutex to do lockdep
> > warnings
> > xen/pciback: Include
On Tue, 2 Dec 2014, Don Slutz wrote:
> On 12/02/14 09:26, Stefano Stabellini wrote:
> > On Tue, 2 Dec 2014, Don Slutz wrote:
> > > On 12/02/14 06:53, Stefano Stabellini wrote:
> > > > In libxl_set_memory_target when setting the new maxmem, retain the same
> > > > offset on top of the current target
On 12/02/2014 08:43 AM, Ian Campbell wrote:
On Fri, 2014-11-28 at 16:53 +, Stefano Stabellini wrote:
CCing Boris because he was fixing a similar sounding issue in the same
area. Not sure if this is related to those patches or not.
Not really. I was trying to fix something that another Stef
On Tue, Dec 02, 2014 at 02:02:58PM +, Ian Campbell wrote:
> On Tue, 2014-12-02 at 02:43 +, Andrew Cooper wrote:
> > On 01/12/2014 20:30, Konrad Rzeszutek Wilk wrote:
> > > On Fri, Nov 28, 2014 at 11:31:24AM +, Ian Campbell wrote:
> > >> On Tue, 2014-11-25 at 11:11 -0500, Boris Ostrovsky
>>> Konrad Rzeszutek Wilk 12/02/14 4:05 PM >>>
>On Tue, Dec 02, 2014 at 10:10:11AM +, Jan Beulich wrote:
>> >>> On 21.11.14 at 23:17, wrote:
>> > Konrad Rzeszutek Wilk (7):
>> > xen/pciback: Don't deadlock when unbinding.
>> > driver core: Provide an wrapper around the mutex to do
On Tue, Dec 02, 2014 at 10:39:59AM +0100, Juergen Gross wrote:
> Hi,
>
> looking into the upstream linux sources I realized that the PVHVM
> drivers of XEN are only available with the pvops kernel. Is this on
> purpose? Shouldn't the frontend drivers, xen/platform-pci.c etc. be
> configurable with
On Thu, Nov 27, 2014 at 3:11 PM, Konrad Rzeszutek Wilk
wrote:
>
> On Nov 27, 2014 6:59 AM, Tim Deegan wrote:
>>
>> At 11:39 + on 27 Nov (1417084797), George Dunlap wrote:
>> > -BEGIN PGP SIGNED MESSAGE-
>> > Hash: SHA512
>> >
>> > I agree to the conditions in the XenProject Coverity c
On Tue, Dec 02, 2014 at 11:05:14AM +, Ian Campbell wrote:
> On Tue, 2014-12-02 at 10:54 +, David Vrabel wrote:
> > On 02/12/14 09:39, Juergen Gross wrote:
> > > Hi,
> > >
> > > looking into the upstream linux sources I realized that the PVHVM
> > > drivers of XEN are only available with th
On Tue, Dec 02, Daniel Kiper wrote:
> Hence, this patch increases initial conring size to 64 KiB.
Instead of increasing the default it was suggested to dynamically
allocate the buffer very early.
http://lists.xenproject.org/archives/html/xen-devel/2011-07/msg00689.html
Olaf
___
On Tue, Dec 02, Ian Campbell wrote:
> On Mon, 2014-12-01 at 23:41 +, Mark Pryor wrote:
> > list,
>
> Thanks. If you've identified a buggy changeset then it is fine to post
> to the devel lists. I've added a CC. I've also CCd everyone listed in
> the commit which you've fingered.
>
> Olaf, do
Signed-off-by: Daniel Kiper
---
.gitignore |3 +++
1 file changed, 3 insertions(+)
diff --git a/.gitignore b/.gitignore
index b24e905..2b51d5f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -141,12 +141,15 @@ tools/flask/utils/flask-set-bool
tools/flask/utils/flask-label-pci
tools/hotplug/com
Signed-off-by: Daniel Kiper
---
tools/Makefile |3 +++
tools/hotplug/Makefile |5 -
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/tools/Makefile b/tools/Makefile
index af9798a..19b24f3 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -261,6 +261,9 @@ subdir-
XEN_DOMCTL_getdomaininfo, which is being used by xc_domain_getinfo(), has
strange interface: it reports first domain which has domid >= requested domid
so all callers are supposed to check that the proper domain(s) was queried
by checking domid. xc_get_tot_pages() doesn't do that. In case the reque
Signed-off-by: Daniel Kiper
---
.gitignore |9 -
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/.gitignore b/.gitignore
index 2b51d5f..8c8c06f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -145,6 +145,10 @@ tools/hotplug/Linux/init.d/sysconfig.xencommons
tools/hotplug/Li
Hi,
Here are three tools build system patches:
- tools/hotplug: distclean target should remove files generated by configure,
- gitignore: ignore some files generated by configure,
- gitignore: group tools/hotplug files in one place.
First two are real fixes. Last one is a cleanup which is n
On 12/02/14 09:59, Don Slutz wrote:
On 12/02/14 09:26, Stefano Stabellini wrote:
On Tue, 2 Dec 2014, Don Slutz wrote:
On 12/02/14 06:53, Stefano Stabellini wrote:
In libxl_set_memory_target when setting the new maxmem, retain the
same
offset on top of the current target. The offset includes m
AC_CHECK_LIB fails on Debian Jessie since the ld flag it generates is
incorrect, even in the event systemd library is available. Use
PKG_CHECK_MODULES instead.
Tested on Debian Jessie and Arch Linux.
Please rerun autogen.sh after applying this patch.
Reported-by: Mark Pryor
Signed-off-by: Wei
Hello Andrew,
On 28/11/2014 13:57, Andrew Turner wrote:
On Sun, 23 Nov 2014 22:35:36 +
Julien Grall wrote:
Major changes in this new version:
* Add Device Tree support via Linux Boot ABI
* Add zImage support
* Netfront support
* Blkfront fixes
* DOM0
On 12/02/14 10:18, Vitaly Kuznetsov wrote:
XEN_DOMCTL_getdomaininfo, which is being used by xc_domain_getinfo(), has
strange interface: it reports first domain which has domid >= requested domid
so all callers are supposed to check that the proper domain(s) was queried
by checking domid. xc_get_t
On Tue, 2014-12-02 at 15:10 +, George Dunlap wrote:
> On Thu, Nov 27, 2014 at 3:11 PM, Konrad Rzeszutek Wilk
> wrote:
> >
> > On Nov 27, 2014 6:59 AM, Tim Deegan wrote:
> >>
> >> At 11:39 + on 27 Nov (1417084797), George Dunlap wrote:
> >> > -BEGIN PGP SIGNED MESSAGE-
> >> > Hash:
On Tue, 2014-12-02 at 10:11 -0500, Konrad Rzeszutek Wilk wrote:
> > [0] The default i386 Debian installer falls into this camp, but you can
> > use the special PV Xen variant to install as PVHVM too so it's not so
> > critical.
>
> And the Fedora 21 LiveISO (32-bit) does too.
Interesting, I thoug
On Tue, 2014-12-02 at 15:11 +, Wei Liu wrote:
> AC_CHECK_LIB fails on Debian Jessie since the ld flag it generates is
> incorrect, even in the event systemd library is available. Use
> PKG_CHECK_MODULES instead.
>
> Tested on Debian Jessie and Arch Linux.
>
> Please rerun autogen.sh after ap
1 - 100 of 196 matches
Mail list logo