ng if the two pages to merge
belong to the same hugepage when attempting to merge them. If so, the
hugepage is split safely. This means that the hugepage is not split if
not necessary.
Signed-off-by: Gerald Schaefer
Signed-off-by: Claudio Imbrenda
---
mm/ksm.c | 9 -
1 file changed,
ng if the two pages to merge
belong to the same hugepage when attempting to merge them. If so, the
hugepage is split safely. This means that the hugepage is not split if
not necessary.
Co-authored-by: Gerald Schaefer
Signed-off-by: Claudio Imbrenda
---
mm/ksm.c | 28
On Mon, 12 Mar 2018 14:22:10 -0700
Andrew Morton wrote:
> On Mon, 12 Mar 2018 17:42:17 +0100 Claudio Imbrenda
> wrote:
>
> > This patch fixes a corner case for KSM. When two pages belong or
> > belonged to the same transparent hugepage, and they should be
> > mer
I don't have objections to this patch, but I wonder how much impact it
would have. Have you performed any tests? does it really have such a big
impact on the availability of order-1 page blocks?
Claudio
On Mon, 15 Oct 2018 12:33:36 +0300
Kirill Tkhai wrote:
> v2: Style improvements
>
> try_t
: e86c59b1b1 ("mm/ksm: improve deduplication of zero pages with colouring")
Signed-off-by: Claudio Imbrenda
---
mm/ksm.c | 7 +++
1 file changed, 7 insertions(+)
diff --git a/mm/ksm.c b/mm/ksm.c
index 293721f..2d6b352 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1131,6 +1131,13 @@
ded small comment to explain what they are about
v2->v3
* improved some comments
* improved some variable and parameter names for increased readability
* fixed missing handling of page faults in the MVPG handler
* small readability improvements
v1->v2
* complete rewrite
Claudio Imbrenda (2
, region) tables.
PEI_NOT_PTE: indicates that the address of the DAT table entry returned
does not refer to a PTE, but to a segment or region table.
Signed-off-by: Claudio Imbrenda
Cc: sta...@vger.kernel.org
Reviewed-by: Janosch Frank
Reviewed-by: David Hildenbrand
---
arch/s390/kvm
Correctly handle the MVPG instruction when issued by a VSIE guest.
Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested
virtualization")
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
Acked-by: Janosch Frank
---
arch/s390/kvm/v
On Thu, 11 Feb 2021 10:18:56 +0100
David Hildenbrand wrote:
> On 09.02.21 16:43, Claudio Imbrenda wrote:
> > Extend kvm_s390_shadow_fault to return the pointer to the valid leaf
> > DAT table entry, or to the invalid entry.
> >
> > Also return some flags in th
) tables
NOT_PTE: indicates that the address of the DAT table entry returned
does not refer to a PTE, but to a segment or region table.
Signed-off-by: Claudio Imbrenda
Cc: sta...@vger.kernel.org
---
arch/s390/kvm/gaccess.c | 26 ++
arch/s390/kvm/gaccess.h | 5
Correctly handle the MVPG instruction when issued by a VSIE guest.
Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested
virtualization")
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
---
arch/s390/kvm/vsie.c | 94 +-
The current handling of the MVPG instruction when executed in a nested
guest is wrong, and can lead to the nested guest hanging.
This patchset fixes the behaviour to be more architecturally correct,
and fixes the hangs observed.
v1->v2
* complete rewrite
Claudio Imbrenda (2):
s390/kvm: ext
On Tue, 2 Feb 2021 19:00:28 +0100
Claudio Imbrenda wrote:
> Correctly handle the MVPG instruction when issued by a VSIE guest.
>
> Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested
> virtualization") Cc: sta...@vger.kernel.org
> Signed-off-by: Claudi
On Thu, 4 Feb 2021 17:34:00 +0100
Janosch Frank wrote:
> On 2/2/21 7:00 PM, Claudio Imbrenda wrote:
> > Extend kvm_s390_shadow_fault to return the pointer to the valid leaf
> > DAT table entry, or to the invalid entry.
> >
> > Also return some flags in th
On Thu, 4 Feb 2021 18:05:15 +0100
Janosch Frank wrote:
> On 2/4/21 5:34 PM, Janosch Frank wrote:
> > On 2/2/21 7:00 PM, Claudio Imbrenda wrote:
> >> Extend kvm_s390_shadow_fault to return the pointer to the valid
> >> leaf DAT table entry, or to the invalid entry.
On Fri, 5 Feb 2021 13:56:53 +0100
Janosch Frank wrote:
> On 2/5/21 1:15 PM, Claudio Imbrenda wrote:
> > On Thu, 4 Feb 2021 17:34:00 +0100
> > Janosch Frank wrote:
> >
> >> On 2/2/21 7:00 PM, Claudio Imbrenda wrote:
> >>> Extend kvm_s390_shado
Correctly handle the MVPG instruction when issued by a VSIE guest.
Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested
virtualization")
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
---
arch/s390/kvm/vsie.c | 93 +-
and parameter names for increased readability
* fixed missing handling of page faults in the MVPG handler
* small readability improvements
v1->v2
* complete rewrite
Claudio Imbrenda (2):
s390/kvm: extend kvm_s390_shadow_fault to return entry pointer
s390/kvm: VSIE: correctly handle MVPG when i
) tables
NOT_PTE: indicates that the address of the DAT table entry returned
does not refer to a PTE, but to a segment or region table.
Signed-off-by: Claudio Imbrenda
Cc: sta...@vger.kernel.org
---
arch/s390/kvm/gaccess.c | 30 +-
arch/s390/kvm/gaccess.h | 5
On Tue, 19 Jan 2021 05:04:02 -0500
Janosch Frank wrote:
> Turns out that the bit 61 in the TEID is not always 1 and if that's
> the case the address space ID and the address are
> unpredictable. Without an address and it's address space ID we can't
*its
Reviewed-by: Cla
; limit.
>
> The naming of the field is a bit misleading. Number in this context is
> used like ID and starts at 0. The query field denotes the maximum
> number that can be put into the VCPU number field in the "create
> secure CPU" UV call.
once you address Christian'
;)
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
---
arch/s390/kvm/vsie.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 48aab6290a77..92864f9b3d84 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
The guest real address needs to pass through prefixing in order to yield
the absolute address.
The absolute address needs to be offset by the MSO in order to get the
host virtual address.
Claudio Imbrenda (2):
s390/kvm: split kvm_s390_real_to_abs
s390/kvm: VSIE: fix MVPG handling for
A new function _kvm_s390_real_to_abs will apply prefixing to a real address
with a given prefix value.
The old kvm_s390_real_to_abs becomes now a wrapper around the new function.
This is needed to avoid code duplication in vSIE.
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
On Tue, 23 Mar 2021 16:16:18 +0100
Christian Borntraeger wrote:
> On 23.03.21 16:11, David Hildenbrand wrote:
> > On 23.03.21 16:07, Christian Borntraeger wrote:
> >>
> >>
> >> On 22.03.21 15:05, Claudio Imbrenda wrote:
> >>> Prefixing
A new function _kvm_s390_real_to_abs will apply prefixing to a real address
with a given prefix value.
The old kvm_s390_real_to_abs becomes now a wrapper around the new function.
This is needed to avoid code duplication in vSIE.
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
to improve readability
Claudio Imbrenda (2):
s390/kvm: split kvm_s390_real_to_abs
s390/kvm: VSIE: fix MVPG handling for prefixing and MSO
arch/s390/kvm/gaccess.h | 23 +--
arch/s390/kvm/vsie.c| 6 +-
2 files changed, 22 insertions(+), 7 deletions(-)
--
2.26.2
;)
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
Reported-by: Janosch Frank
---
arch/s390/kvm/vsie.c | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 48aab6290a77..ac86f11e46dc 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arc
The current handling of the MVPG instruction when executed in a nested
guest is wrong, and can lead to the nested guest hanging.
This patchset fixes the behaviour to be more architecturally correct,
and fixes the hangs observed.
Claudio Imbrenda (4):
s390/kvm: VSIE: stop leaking host addresses
s390: vsie: initial support for nested
virtualization")
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
---
arch/s390/kvm/vsie.c | 5 -
1 file changed, 5 deletions(-)
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 4f3cbf6003a9..ada49583e530 100644
--- a/arc
Extend guest_translate to optionally return the address of the guest
DAT table which caused the exception, and change the return value to int.
Also return the appropriate values in the low order bits of the address
indicating protection or EDAT.
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio
Add kvm_s390_vsie_mvpg_check to perform the necessary checks in case an
MVPG instruction intercepts in a VSIE guest.
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
---
arch/s390/kvm/gaccess.c | 55 +
arch/s390/kvm/gaccess.h | 3 +++
2 files
Correctly handle the MVPG instruction when issued by a VSIE guest.
Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested
virtualization")
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
---
arch/s390/kvm/vsie.c | 73 ++
, region) tables.
PEI_NOT_PTE: indicates that the address of the DAT table entry returned
does not refer to a PTE, but to a segment or region table.
Signed-off-by: Claudio Imbrenda
Cc: sta...@vger.kernel.org
Reviewed-by: Janosch Frank
Reviewed-by: David Hildenbrand
---
arch/s390/kvm
Correctly handle the MVPG instruction when issued by a VSIE guest.
Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested
virtualization")
Cc: sta...@vger.kernel.org
Signed-off-by: Claudio Imbrenda
Acked-by: Janosch Frank
Reviewed-by: David Hildenbrand
---
arch/s390/
needed to avoid code duplication for vSIE.
Signed-off-by: Claudio Imbrenda
---
arch/s390/kvm/gaccess.h | 29 -
1 file changed, 24 insertions(+), 5 deletions(-)
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index f4c51756c462..107fdfd2eadd 100644
--- a
variable and parameter names for increased readability
* fixed missing handling of page faults in the MVPG handler
* small readability improvements
v1->v2
* complete rewrite
Claudio Imbrenda (3):
s390/kvm: split kvm_s390_logical_to_effective
s390/kvm: extend kvm_s390_shadow_fault to return e
On Mon, 8 Mar 2021 16:26:58 +0100
Janosch Frank wrote:
> On 3/8/21 4:19 PM, Christian Borntraeger wrote:
> > On 02.03.21 18:44, Claudio Imbrenda wrote:
> >> The current handling of the MVPG instruction when executed in a
> >> nested guest is wrong, and can lead
} else
> + panic("Unexpected PGM 0x3d with TEID bit
> 61=0");
> + }
> +
> switch (get_fault_type(regs)) {
> case USER_FAULT:
> mm = current->mm;
Reviewed-by: Claudio Imbrenda
On Thu, 4 Feb 2021 18:10:01 +0100
Janosch Frank wrote:
> On 2/2/21 7:00 PM, Claudio Imbrenda wrote:
> > Correctly handle the MVPG instruction when issued by a VSIE guest.
> >
> > Fixes: a3508fbe9dc6d ("KVM: s390: vsie: initial support for nested
> > virtualizat
On Sun, 20 Dec 2020 11:13:57 +0100
David Hildenbrand wrote:
> On 18.12.20 15:18, Claudio Imbrenda wrote:
> > Correctly handle the MVPG instruction when issued by a VSIE guest.
> >
>
> I remember that MVPG SIE documentation was completely crazy and full
> of corner
On Sun, 20 Dec 2020 10:40:27 +0100
David Hildenbrand wrote:
> On 18.12.20 15:18, Claudio Imbrenda wrote:
> > The current handling of the MVPG instruction when executed in a
> > nested guest is wrong, and can lead to the nested guest hanging.
>
> Hi,
>
> thanks for
On Sun, 20 Dec 2020 10:44:56 +0100
David Hildenbrand wrote:
> On 18.12.20 15:18, Claudio Imbrenda wrote:
> > The addresses in the SIE control block of the host should not be
> > forwarded to the guest. They are only meaningful to the host, and
> > moreover it would be a
On Mon, 4 Jan 2021 17:08:15 +0100
David Hildenbrand wrote:
> On 04.01.21 16:22, Claudio Imbrenda wrote:
> > On Sun, 20 Dec 2020 11:13:57 +0100
> > David Hildenbrand wrote:
> >
> >> On 18.12.20 15:18, Claudio Imbrenda wrote:
> >>> Correctly handle
gt; + }
> > /*
> > * The second half of the bitmap is only used on
> > x86,
> > * and would be wasted otherwise, so we put it to
> > good
Otherwise it looks good.
Claudio Imbrenda
>memslots + slotnr;
> + if (!ms->dirty_bitmap)
> + return -EINVAL;
> /*
>* The second half of the bitmap is only used on x86,
>* and would be wasted otherwise, so we put it to
> good
Reviewed-by: Claudio Imbrenda
that do not need to deal
with inaccessible pages.
Fixes: f28d43636d6f ("mm/gup/writeback: add callbacks for inaccessible pages")
Signed-off-by: Claudio Imbrenda
---
fs/splice.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/splice.c b/fs/splice.c
index 4735defc46ee..f026e0ce9
On Wed, 29 Apr 2020 16:52:46 -0700
Dave Hansen wrote:
> On 4/29/20 3:53 PM, Claudio Imbrenda wrote:
> >> Actually, that's the problem. You've gone through all these
> >> careful checks and made the page inaccessible. *After* that
> >> process, how do yo
issue.
Fixes: f28d43636d6f ("mm/gup/writeback: add callbacks for inaccessible pages")
Signed-off-by: Claudio Imbrenda
---
fs/splice.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/splice.c b/fs/splice.c
index 4735defc46ee..f026e0ce9acd 100644
--- a/fs/splice.c
+++ b/fs/splice.c
On Tue, 28 Apr 2020 12:43:45 -0700
Dave Hansen wrote:
> On 4/21/20 2:31 PM, Dave Hansen wrote:
> > On 4/16/20 12:02 PM, Dave Hansen wrote:
> >> On 4/16/20 9:34 AM, Claudio Imbrenda wrote:
> >>>> Ahh, so this is *just* intended to precede I/O done on the page,
On Wed, 29 Apr 2020 10:55:52 -0700
Dave Hansen wrote:
> On 4/29/20 10:31 AM, Christian Borntraeger wrote:
> > On 29.04.20 18:07, Dave Hansen wrote:
> >> On 4/28/20 3:50 PM, Claudio Imbrenda wrote:
> >>> If a page is inaccesible and it is used for things like se
) continue;
>
> - if (!rwc->rmap_one(page, vma,
> - rmap_item->address,
> rwc->arg)) {
> + if (addr & STABLE_FLAG)
> + addr &= ~KSM_FLAG_MASK;
then you would not need the IF above, and it would be more readable.
> +
> + if (!rwc->rmap_one(page, vma, addr,
> rwc->arg)) { anon_vma_unlock_read(anon_vma);
> return;
> }
best regards,
Claudio Imbrenda
ng if the two pages to merge
belong to the same hugepage when attempting to merge them. If so, the
hugepage is split safely. This means that the hugepage is not split if
not necessary.
Co-authored-by: Gerald Schaefer
Signed-off-by: Claudio Imbrenda
---
mm/ksm.c | 28
Hi Andrea,
On 12/01/17 18:21, Andrea Arcangeli wrote:
> Hello Claudio,
>
> On Thu, Jan 12, 2017 at 05:17:14PM +0100, Claudio Imbrenda wrote:
>> +#ifdef __HAVE_COLOR_ZERO_PAGE
>> +/*
>> + * Same checksum as an empty page. We attempt to merge it with the
>&
On 18/01/17 17:29, Andrea Arcangeli wrote:
> It's still good to be able to exercise this code on all archs (if
> nothing else for debugging purposes). There's nothing arch dependent
> in it after all.
If it's fine for you, I'm definitely not going to complain :)
>> ZERO_PAGE() would save exactly
coloured zero pages. The default value is
disabled, for backwards compatibility.
With this patch, the performance with KSM is the same as with non
COW-broken actual zero pages, which is also the same as without KSM.
Signed-off-by: Claudio Imbrenda
---
mm/ksm.c | 68
This patch adds the needed documentation for the use_zero_pages property.
Signed-off-by: Claudio Imbrenda
---
Documentation/vm/ksm.txt | 14 ++
1 file changed, 14 insertions(+)
diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt
index f34a8ee..0c64a81d 100644
--- a
: Claudio Imbrenda
---
mm/ksm.c | 29 +
1 file changed, 29 insertions(+)
diff --git a/mm/ksm.c b/mm/ksm.c
index 9ae6011..b0cfc30 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -223,6 +223,11 @@ struct rmap_item {
/* Milliseconds ksmd should sleep between batches */
static unsigned
ons.
This patch shrinks the influence of prepare_to_wait to the area where it
is strictly needed, therefore relaxing the no-sleep restriction there.
Signed-off-by: Claudio Imbrenda
---
net/vmw_vsock/af_vsock.c | 158 +--
1 file changed, 85 insertions(+
checked but before
the sleep happens, and we miss it. ( A description of the problem can be
found here: http://www.makelinux.net/ldd3/chp-6-sect-2 ).
The first patch reverts the previous broken patch, while the second patch
properly fixes the sleep-while-waiting issue.
Claudio Imbrenda (2):
Revert
nd the schedule) but at least
it will not miss wakeups.
The next patch in the series actually fixes the behaviour.
Signed-off-by: Claudio Imbrenda
---
net/vmw_vsock/af_vsock.c | 19 +--
1 file changed, 13 insertions(+), 6 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c
influence of prepare_to_wait to the area where it
is strictly needed, therefore relaxing the no-sleep restriction there.
Signed-off-by: Claudio Imbrenda
---
net/vmw_vsock/af_vsock.c | 158 +--
1 file changed, 85 insertions(+), 73 deletions(-)
diff --git a
influence of prepare_to_wait to the area where it
is strictly needed, therefore relaxing the no-sleep restriction there.
Signed-off-by: Claudio Imbrenda
---
net/vmw_vsock/af_vsock.c | 158 +--
1 file changed, 85 insertions(+), 73 deletions(-)
diff --git a
This reverts commit 5988818008257ca42010d6b43a3e0e48afec9898 ("vsock: Fix
blocking ops call in prepare_to_wait")
Signed-off-by: Claudio Imbrenda
---
net/vmw_vsock/af_vsock.c | 19 +--
1 file changed, 13 insertions(+), 6 deletions(-)
diff --git a/net/vmw_vsock/af_vso
I'm resending as requested.
This patchset applies on net-next.
And sorry for the mis-formatting of the previous message.
Claudio Imbrenda (2):
Revert "vsock: Fix blocking ops call in prepare_to_wait"
AF_VSOCK: Shrink the area influenced by prepare_to_wait
net/vmw_vsock/a
s")
This patch simply restores the call to kvm_put_kvm, so that the kvm
object is destroyed before returning an error.
Signed-off-by: Claudio Imbrenda
Fixes: 506cfba9e726 ("KVM: don't use anon_inode_getfd() before possible
failures")
---
virt/kvm/kvm_main.c | 1 +
1 file ch
v3:
* added EVENT
* shortened the names of the other variables
v1 -> v2:
* added KVM_VM_PID and KVM_VM_STATS_PATH
* some cleanup, the patch should look nicer now
* rebased on 4.12
Claudio Imbrenda (1):
KVM: trigger uevents when creating or destroying
erspace to deal with the
creation or destruction of VMs as needed.
Signed-off-by: Claudio Imbrenda
---
virt/kvm/kvm_main.c | 69 +
1 file changed, 69 insertions(+)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f0fe9d0..24ad3f5 1
erspace to deal with the
creation or destruction of VMs as needed.
Signed-off-by: Claudio Imbrenda
---
virt/kvm/kvm_main.c | 59 +
1 file changed, 59 insertions(+)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f0fe9d0..7c39783 1
erspace to deal with the
creation or destruction of VMs as needed.
v2 -> v3:
* added EVENT
* shortened the names of the other variables
v1 -> v2:
* added KVM_VM_PID and KVM_VM_STATS_PATH
* some cleanup, the patch should look nicer now
* rebased on 4.12
*** BLURB HERE ***
Claudio Imbrenda (
On Mon, 10 Jul 2017 11:40:55 +0200
David Hildenbrand wrote:
> On 10.07.2017 11:20, Claudio Imbrenda wrote:
>
> Minor minor nit:
>
> The subject should state "creating or destroying a VM"
I'll fix it
[...]
> > +static void kvm_uevent_notify_change(un
t; v2:
* added KVM_VM_PID and KVM_VM_STATS_PATH
* some cleanup, the patch should look nicer now
* rebased on 4.12
Claudio Imbrenda (1):
KVM: trigger uevents when creating or destroying a VM
virt/kvm/kvm_main.c | 74 +
1 file changed, 74 insertions(+)
--
2.7.4
erspace to deal with the
creation or destruction of VMs as needed.
Signed-off-by: Claudio Imbrenda
---
virt/kvm/kvm_main.c | 74 +
1 file changed, 74 insertions(+)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f0fe9d0..4a7a632 1
creation or destruction of VMs as needed.
v1 -> v2:
* added KVM_VM_PID and KVM_VM_STATS_PATH
* some cleanup, the patch should look nicer now
* rebased on 4.12
Claudio Imbrenda (1):
KVM: trigger uevents when starting or stopping a VM
virt/kvm/kvm_main.c |
creation or destruction of VMs as needed.
Signed-off-by: Claudio Imbrenda
---
virt/kvm/kvm_main.c | 50 ++
1 file changed, 50 insertions(+)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 6e3b12c..f4cf7d2 100644
--- a/virt/kvm/kvm_main.c
On Mon, 17 Jul 2017 17:53:51 +0200
David Hildenbrand wrote:
> > + add_uevent_var(env, "CREATED=%llu", created);
> > + add_uevent_var(env, "COUNT=%llu", active);
>
> I like that much better.
>
> > +
> > + if (type == KVM_EVENT_CREATE_VM)
> > + add_uevent_var(env, "EVENT=create"
This is just a refactoring of the existing code:
* Split the page checksum and page comparison functions from ksm.c into
a new asm-generic header (page_memops.h)
* Add a line in every Kbuild of every arch, to use the generic version
of page_memops.h
Signed-off-by: Claudio Imbrenda
Introduce s390 specific page comparison and checksumming functions:
The s390-specific functions use the CKSM instruction to quickly
calculate the checksum of a page.
This provides a measurable reduction on CPU load when KSM is active.
Signed-off-by: Claudio Imbrenda
---
arch/s390/include/asm
gh I did not see any performance regressions in my tests).
While there is a crypto API to choose between different hash functions,
there is nothing like that for page comparison.
I think at this point we need to coordinate a little, to avoid
reinventing the wheel three times and in differe
("KVM: trigger uevents when creating or destroying a VM")
Signed-off-by: Claudio Imbrenda
---
include/linux/kvm_host.h | 1 +
virt/kvm/kvm_main.c | 35 ---
2 files changed, 13 insertions(+), 23 deletions(-)
diff --git a/include/linux/kvm_host.h
active.
Specific udev rules can be then set up in userspace to deal with the
creation or destruction of VMs as needed.
Signed-off-by: Claudio Imbrenda
---
virt/kvm/kvm_main.c | 25 +
1 file changed, 25 insertions(+)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
On Tue, 4 Jul 2017 11:23:36 +0200
Paolo Bonzini wrote:
> On 04/07/2017 11:03, Claudio Imbrenda wrote:
> > This patch adds a few lines to the KVM common code to fire a
> > KOBJ_CHANGE uevent whenever a KVM VM is created or destroyed. The
> > event carries two
On Tue, 4 Jul 2017 11:27:44 +0200
Paolo Bonzini wrote:
> On 04/07/2017 11:25, Christian Borntraeger wrote:
> > On 07/04/2017 11:23 AM, Paolo Bonzini wrote:
> >>
> >>
> >> On 04/07/2017 11:03, Claudio Imbrenda wrote:
> >>> This patch a
83 matches
Mail list logo
