Compared with V9, just fixed indentation issues in patch 12. I put it
the patchset in
git://git.kernel.org/pub/scm/linux/kernel/git/xiantao/kvm-ia64.git
kvm-ia64-mc10. Please help to review.
Specially, the first two patches (TR Management patch and
smp_call_function_mask patch) needs Tony's review
David Abrahams wrote:
> > What HAL do you see in device manager?
>
> In the guest? I don't see anything that obviously appears to be HAL in
> device manager. Could you be more specific?
Hi,
He's referring to the Windows computer type -- the entry under
"computer" in device manager. See
http
Ok lets forget about the single theaded thing to solve the registration
races. As Andrea pointed out this still has ssues with other subscribed
subsystems (and also try_to_unmap). We could do something like what
stop_machine_run does: First disable all running subsystems before
registering a ne
David Abrahams wrote:
> on Wed Apr 02 2008, Avi Kivity wrote:
>
>> David Abrahams wrote:
>>> With the title combination, the guest takes nearly 100% of my real
>>> CPU time and still only sees one CPU. Is this a known problem, and
>>> does it have a known solution?
>>>
>>>
>>
>> Can you send
Thinking about this adventurous locking some more: I think you are
misunderstanding what a seqlock is. It is *not* a spinlock.
The critical read section with the reading of a version before and after
allows you access to a certain version of memory how it is or was some
time ago (caching effect
On Wed, Apr 02, 2008 at 03:34:01PM -0700, Christoph Lameter wrote:
> Still two methods ...
Yes, the invalidate_page is called with the core VM holding a
reference on the page _after_ the tlb flush. The invalidate_end is
called after the page has been freed already and after the tlb
flush. They've
> > Have you looked at Jens Axboe's patches to make all this stuff a lot
> > more arch-common?
>
> Nope, do you have a pointer?
Check your favourite archive for this Subject line:
Generic smp_call_function(), improvements, and smp_call_function_single()
-Tony
SIGUSR1 has no handler, and the SIGUSR2 one does nothing useful anymore
(thats also true for SIGIO on tap fd, which runs host_alarm_handler
unnecessarily).
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Index: kvm-userspace.io/qemu/qemu-kvm.c
This fixes the slow vmdk issue found in the regression
tests.
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Index: kvm-userspace.io/qemu/qemu-kvm.c
===
--- kvm-userspace.io.orig/qemu/qemu-kvm.c
+++ kvm-userspace.io/qemu/qemu-kvm
Move IO processing from vcpu0 to a dedicated thread.
This removes load on vcpu0 by allowing better cache locality and also
improves latency.
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Index: kvm-userspace.io/qemu/qemu-kvm.c
This version fixes the vmdk problems found by the
regression testing.
Dor, regarding the option to disable the IO thread, it
would require duplicating most of the changed code. For now
I believe its better to get the patch into a state
where its considered stable enough for inclusion.
Please rer
On Thu, 3 Apr 2008, Andrea Arcangeli wrote:
> I said try_to_unmap_cluster, not get_user_pages.
>
> CPU0CPU1
> try_to_unmap_cluster:
> emm_invalidate_start in EMM (or mmu_notifier_invalidate_range_start in #v10)
> walking the list by hand in EMM (or
On Thu, 3 Apr 2008, Andrea Arcangeli wrote:
> Why can't it fire on the mm_struct where GRU just registered? That
> mm_struct existed way before GRU registered, and VM is free to unmap
> it w/o mmap_sem if there was any memory pressure.
Right. Hmmm... Bad situation. We would have invalidate_start
On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
> + void (*invalidate_page)(struct mmu_notifier *mn,
> + struct mm_struct *mm,
> + unsigned long address);
> +
> + void (*invalidate_range_start)(struct mmu_notifier *mn,
> +
On Wed, Apr 02, 2008 at 03:06:19PM -0700, Christoph Lameter wrote:
> On Thu, 3 Apr 2008, Andrea Arcangeli wrote:
>
> > That would work for #v10 if I remove the invalidate_range_start from
> > try_to_unmap_cluster, it can't work for EMM because you've
> > emm_invalidate_start firing anywhere outsid
On Wed, Apr 02, 2008 at 02:56:25PM -0700, Christoph Lameter wrote:
> I am a bit surprised that brk performance is that important. There may be
I think it's not brk but fork that is being slowed down, did you
oprofile? AIM forks a lot... The write side fast path generating the
overscheduling I gue
On Wed, Apr 02, 2008 at 02:54:52PM -0700, Christoph Lameter wrote:
> On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
>
> > > Hmmm... Okay that is one solution that would just require a BUG_ON in the
> > > registration methods.
> >
> > Perhaps you didn't notice that this solution can't work if you ca
On Thu, 3 Apr 2008, Andrea Arcangeli wrote:
> That would work for #v10 if I remove the invalidate_range_start from
> try_to_unmap_cluster, it can't work for EMM because you've
> emm_invalidate_start firing anywhere outside the context of the
> current task (even regular rmap code, not just nonline
On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
> diff --git a/mm/memory.c b/mm/memory.c
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -1626,9 +1626,10 @@
>*/
> page_table = pte_offset_map_lock(mm, pmd, address,
>
On Wed, Apr 02, 2008 at 02:05:28PM -0700, Christoph Lameter wrote:
> Here is a patch to require single threaded execution during emm_register.
> This also allows an easy implementation of an unregister function and gets
> rid of the races that Andrea worried about.
That would work for #v10 if I r
On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
> paging), hence the slowdown. What you benchmarked is the write side,
> which is also the fast path when the system is heavily CPU bound. I've
> to say aim is a great benchmark to test this regression.
I am a bit surprised that brk performance is that
On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
> > Hmmm... Okay that is one solution that would just require a BUG_ON in the
> > registration methods.
>
> Perhaps you didn't notice that this solution can't work if you call
> range_begin/end not in the "current" context and try_to_unmap_cluster
> do
On Wed, Apr 02, 2008 at 11:15:26AM -0700, Christoph Lameter wrote:
> On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
>
> > On Tue, Apr 01, 2008 at 01:55:36PM -0700, Christoph Lameter wrote:
> > > This results in f.e. the Aim9 brk performance test to got down by
> > > 10-15%.
> >
> > I guess it's m
On Wed, Apr 02, 2008 at 10:59:50AM -0700, Christoph Lameter wrote:
> Did I see #v10? Could you start a new subject when you post please? Do
> not respond to some old message otherwise the threading will be wrong.
I wasn't clear enough, #v10 was in the works... I was thinking about
the last two is
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207159059 -7200
# Node ID f3f119118b0abd9c4624263ef388dc7230d937fe
# Parent 31fc23193bd039cc595fba1ca149a9715f7d0fb2
This patch adds a lock ordering rule to avoid a potential deadlock when
multiple mmap_sems need to be locked
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207159055 -7200
# Node ID 316e5b1e4bf388ef0198c91b3067ed1e4171d7f6
# Parent 3c3787c496cab1fc590ba3f97e7904bdfaab5375
We no longer abort unmapping in unmap vmas because we can reschedule while
unmapping since we are holding a
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207159059 -7200
# Node ID 31fc23193bd039cc595fba1ca149a9715f7d0fb2
# Parent dd918e267ce1d054e8364a53adcecf3c7439cff4
XPMEM would have used sys_madvise() except that madvise_dontneed()
returns an -EINVAL if VM_PFNMAP is set, w
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207159058 -7200
# Node ID dd918e267ce1d054e8364a53adcecf3c7439cff4
# Parent 316e5b1e4bf388ef0198c91b3067ed1e4171d7f6
Convert the anon_vma spinlock to a rw semaphore. This allows concurrent
traversal of reverse maps for try_to
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207158873 -7200
# Node ID a406c0cc686d0ca94a4d890d661cdfa48cfba09f
# Parent 249e077dc932a5322e04ac1d69326622ea4023b8
Core of mmu notifiers.
Signed-off-by: Andrea Arcangeli <[EMAIL PROTECTED]>
Signed-off-by: Nick Piggin <[EMA
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207159011 -7200
# Node ID 3c3787c496cab1fc590ba3f97e7904bdfaab5375
# Parent d880c227ddf345f5d577839d36d150c37b653bfd
The conversion to a rwsem allows callbacks during rmap traversal
for files in a non atomic context. A rw sty
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207159010 -7200
# Node ID d880c227ddf345f5d577839d36d150c37b653bfd
# Parent fe00cb9deeb31467396370c835cb808f4b85209a
Move the tlb flushing into free_pgtables. The conversion of the locks
taken for reverse map scanning would r
# HG changeset patch
# User Andrea Arcangeli <[EMAIL PROTECTED]>
# Date 1207159010 -7200
# Node ID fe00cb9deeb31467396370c835cb808f4b85209a
# Parent a406c0cc686d0ca94a4d890d661cdfa48cfba09f
Moves all mmu notifier methods outside the PT lock (first and not last
step to make them sleep capable).
Si
Hello,
this is the mmu notifier #v10. Patches 1 and 2 are the only difference between
this and EMM V2. The rest is the same as with Christoph's patches.
I think maximum priority should be given in merging patch 1 and 2 into -mm and
ASAP in mainline.
Patches from 3 to 8 can go in -mm for testing
On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
> but anyway it's silly to be hardwired to such an interface that worst
> of all requires switch statements instead of proper pointer to
> functions and a fixed set of parameters and retval semantics for all
> methods.
The EMM API with a single callback
On Wed, Apr 02, 2008 at 12:03:50PM -0700, Christoph Lameter wrote:
> + /*
> + * Callback may return a positive value to indicate a
> count
> + * or a negative error code. We keep the first error
> code
> + * but co
Here is a patch to require single threaded execution during emm_register.
This also allows an easy implementation of an unregister function and gets
rid of the races that Andrea worried about.
The approach here is similar to what was used in selinux for security
context changes (see selinux_setpr
This patch introduces a gfn_to_pfn() function and corresponding functions like
kvm_release_pfn_dirty(). Using these new functions, we can modify the x86
MMU to no longer assume that it can always get a struct page for any given gfn.
We don't want to eliminate gfn_to_page() entirely because a numb
On Wed, 2 Apr 2008, Christoph Lameter wrote:
> Here f.e. We can add a special emm_age() function that iterates
> differently and does the | for you.
Well maybe not really necessary. How about this fix? Its likely a problem
to stop callbacks if one callback returned an error.
Subject: EMM: Fix
On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
> On Tue, Apr 01, 2008 at 01:55:36PM -0700, Christoph Lameter wrote:
> > This results in f.e. the Aim9 brk performance test to got down by 10-15%.
>
> I guess it's more likely because of overscheduling for small crtitical
> sections, did you counted t
On Wed, 2 Apr 2008, Andrea Arcangeli wrote:
> There are much bigger issues besides the rcu safety in this patch,
> proper aging of the secondary mmu through access bits set by hardware
> is unfixable with this model (you would need to do age |=
> e->callback), which is the proof of why this isn't
On Tue, Apr 01, 2008 at 01:55:36PM -0700, Christoph Lameter wrote:
> This results in f.e. the Aim9 brk performance test to got down by 10-15%.
I guess it's more likely because of overscheduling for small crtitical
sections, did you counted the total number of context switches? I
guess there will
on Wed Apr 02 2008, Avi Kivity wrote:
> David Abrahams wrote:
>> With the title combination, the guest takes nearly 100% of my real CPU
>> time and still only sees one CPU. Is this a known problem, and does it
>> have a known solution?
>>
>>
>
> Can you send the output of 'kvm_stat -1'?
I
Guillaume Thouvenin wrote:
> Hello,
>
> I have a question about how guest page table and shadow page table
> work together and more precisely, about how host is involved when guest
> access a page that it's already in the page table.
>
> The guest maintains its page table to translate guest virtu
Avi Kivity wrote:
> Andrea Arcangeli wrote:
>> On Wed, Apr 02, 2008 at 12:50:50PM +0300, Avi Kivity wrote:
>>
>>> Isn't it faster though? We don't need to pull in the cacheline
>>> containing the struct page anymore.
>>>
>>
>> Exactly, not only that, get_user_pages is likely a bit slower t
I must have missed v10. Could you repost so I can build xpmem
against it to see how it operates? To help reduce confusion, you should
probably comandeer the patches from Christoph's set which you think are
needed to make it sleep.
Thanks,
Robin
On Wed, Apr 02, 2008 at 01:16:51PM +0200, Andrea
Hello,
I have a question about how guest page table and shadow page table
work together and more precisely, about how host is involved when guest
access a page that it's already in the page table.
The guest maintains its page table to translate guest virtual address
to guest physical address. I
On Wed, Apr 02, 2008 at 01:50:19PM +0200, Andrea Arcangeli wrote:
> if (pfn_valid(pfn)) {
> page = pfn_to_page(pfn);
> if (!PageReserved(page)) {
> BUG_ON(page_count(page) != 1);
> if (is_writeable_pte(*spte))
>
On Wed, Apr 02, 2008 at 02:16:41PM +0300, Avi Kivity wrote:
> Ugh, there's still mark_page_accessed() and SetPageDirty().
btw, like PG_dirty is only set if the spte is writeable,
mark_page_accessed should only run if the accessed bit is set in the
spte. It doesn't matter now as nobody could possib
On 02/04/2008, Jonathan Underwood <[EMAIL PROTECTED]> wrote:
> On 01/04/2008, Avi Kivity <[EMAIL PROTECTED]> wrote:
>
> > Please run 'kvm_stat -1' (found in the tarball) while the guest is hanging
> > and report the output.
>
> # /home/jgu/Desktop/kvm_stat -1
> efer_reload 8757563
Izik Eidus wrote:
> From ebb9fe4765f1572314d2249e29a7ef4d0de07273 Mon Sep 17 00:00:00 2001
> From: Izik Eidus <[EMAIL PROTECTED]>
> Date: Sun, 30 Mar 2008 15:48:35 +0300
> Subject: [PATCH] KVM: add kvm_get_kvm and kvm_put_kvm functions,
>
> the main purpose of adding this functions is the abilaty t
On 01/04/2008, Avi Kivity <[EMAIL PROTECTED]> wrote:
> Please run 'kvm_stat -1' (found in the tarball) while the guest is hanging
> and report the output.
# /home/jgu/Desktop/kvm_stat -1
efer_reload 8757563 129
exits 17039786 362
halt_exits
On Wed, Apr 02, 2008 at 05:59:25AM -0500, Robin Holt wrote:
> On Wed, Apr 02, 2008 at 08:49:52AM +0200, Andrea Arcangeli wrote:
> > Most other patches will apply cleanly on top of my coming mmu
> > notifiers #v10 that I hope will go in -mm.
> >
> > For #v10 the only two left open issues to discuss
Avi Kivity wrote:
> Andrea Arcangeli wrote:
>> On Wed, Apr 02, 2008 at 12:50:50PM +0300, Avi Kivity wrote:
>>
>>> Isn't it faster though? We don't need to pull in the cacheline
>>> containing the struct page anymore.
>>>
>>
>> Exactly, not only that, get_user_pages is likely a bit slower t
Andrea Arcangeli wrote:
> On Wed, Apr 02, 2008 at 12:50:50PM +0300, Avi Kivity wrote:
>
>> Isn't it faster though? We don't need to pull in the cacheline containing
>> the struct page anymore.
>>
>
> Exactly, not only that, get_user_pages is likely a bit slower that we
> need for just kvm
On Wed, Apr 02, 2008 at 08:49:52AM +0200, Andrea Arcangeli wrote:
> Most other patches will apply cleanly on top of my coming mmu
> notifiers #v10 that I hope will go in -mm.
>
> For #v10 the only two left open issues to discuss are:
Does your v10 allow sleeping inside the callbacks?
Thanks,
Rob
Anthony Liguori wrote:
> This patch is mostly code motion to move the newly refactored
> in-kernel PIT device to a separate file.
>
>
Applied both, thanks.
--
error compiling committee.c: too many arguments to function
---
On Wed, Apr 02, 2008 at 12:50:50PM +0300, Avi Kivity wrote:
> Isn't it faster though? We don't need to pull in the cacheline containing
> the struct page anymore.
Exactly, not only that, get_user_pages is likely a bit slower that we
need for just kvm pte lookup. GRU uses follow_page directly bec
Am Montag, 31. März 2008 schrieb Arnd Bergmann:
Hello Arnd,
thanks for the review.
> On Tuesday 25 March 2008, Carsten Otte wrote:
>
> > +
> > +static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
> > + u64 guestaddr)
> > +{
> > + u64
Fantastic offer on luxuries
The clock was invented to be re-invented to have a spot on your wrist.
http://www.poretiage.com/
-
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
ju
Andrea Arcangeli wrote:
> On Wed, Apr 02, 2008 at 07:32:35AM +0300, Avi Kivity wrote:
>
>> It ought to work. gfn_to_hfn() (old gfn_to_page) will still need to take a
>> refcount if possible.
>>
>
> This reminds me, that mmu notifiers we could implement gfn_to_hfn only
> with follow_page a
Jeremy Fitzhardinge wrote:
>> I wasn't suggesting we shouldn't have both interfaces, merely
>> questioning why adding what to me seems like an unnecessary performance
>> hit for the classic case of the call.
>
> I don't mind how many interfaces there are, so long as there only needs
> to be one p
On Wed, Apr 02, 2008 at 07:32:35AM +0300, Avi Kivity wrote:
> It ought to work. gfn_to_hfn() (old gfn_to_page) will still need to take a
> refcount if possible.
This reminds me, that mmu notifiers we could implement gfn_to_hfn only
with follow_page and skip the refcounting on the struct page.
I
62 matches
Mail list logo
