and pass down RAM_GUEST_MEMFD when backend->guest_memfd is true, to
allow shm memory backend serve as shared memory for coco-VMs.
cc: Stefano Garzarella
Signed-off-by: Xiaoyao Li
Acked-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 16.07.25 15:31, Michael Tokarev wrote:
On 03.06.2025 14:13, David Hildenbrand wrote:
When we unplug a vhost device, we end up calling vhost_dev_cleanup()
where we do a memory_listener_unregister().
This memory_listener_unregister() call will end up disconnecting the
listener from the
pull request.
For these 3:
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 18.06.25 23:58, Peter Xu wrote:
Hi, Chenyi,
On Thu, Jun 12, 2025 at 04:27:41PM +0800, Chenyi Qiang wrote:
Relationship with in-place conversion
-
In-place page conversion is the ongoing work to allow mmap() of
guest_memfd to userspace so that both private
On 09.06.25 16:47, Albert Esteve wrote:
Add missing members to the VhostUserMsg excerpt in
the vhost-user spec documentation.
Reviewed-by: Stefan Hajnoczi
Signed-off-by: Albert Esteve
---
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 09.06.25 16:47, Albert Esteve wrote:
Add SHMEM_MAP/UNMAP requests to vhost-user to
handle VIRTIO Shared Memory mappings.
This request allows backends to dynamically map
fds into a VIRTIO Shared Memory Region indentified
by its `shmid`. The map is performed by calling
`memory_region_init_ram_f
On 04.06.25 13:53, Zhenzhong Duan wrote:
VirtIOPMEMClass's parent is VirtioDeviceClass rather than VirtIODevice.
Fixes: 5f503cd9f388 ("virtio-pmem: add virtio device")
Suggested-by: David Hildenbrand
Reported-by: might be better, with
Closes:
linking to my mail
Signed-of
undo support if state_change()
failed.
- Didn't add Reviewed-by from Alexey due to the new changes in this
commit.
---
Acked-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 04.06.25 10:47, Zhenzhong Duan wrote:
Parent of VirtIOMEMClass is VirtioDeviceClass rather than VirtIODevice.
Fixes: 910b25766b33 ("virtio-mem: Paravirtualized memory hot(un)plug")
Signed-off-by: Zhenzhong Duan
---
include/hw/virtio/virtio-mem.h | 2 +-
1 file changed, 1 insertion(+), 1 d
/* private */
-VirtIODevice parent;
+VirtioDeviceClass parent;
Reviewed-by: David Hildenbrand
I assume it's not currently a real problem because VirtIODevice is
bigger than VirtioDeviceClass?
Or are you aware of any existing problems with that?
--
Cheers,
David / dhildenb
ghao
Link:
https://lore.kernel.org/qemu-devel/20241121060755.164310-1-yuanm...@chinatelecom.cn/
Fixes: 2ce68e4cf5be ("vhost: add vhost_has_free_slot() interface")
Cc: Igor Mammedov
Cc: Michael S. Tsirkin
Cc: Stefano Garzarella
Signed-off-by: David Hildenbrand
---
I assume the pro
On 30.05.25 13:36, Michael S. Tsirkin wrote:
On Fri, May 30, 2025 at 01:28:58PM +0200, David Hildenbrand wrote:
On 30.05.25 13:18, Michael S. Tsirkin wrote:
On Wed, May 14, 2025 at 11:26:05AM +0200, David Hildenbrand wrote:
On 14.05.25 11:12, Igor Mammedov wrote:
On Tue, 13 May 2025 15:12:11
On 03.06.25 09:17, Gupta, Pankaj wrote:
+CC Tony & Kishen
In this patch series we are only maintaining the bitmap for Ram discard/
populate state not for regular guest_memfd private/shared?
As mentioned in changelog, "In the context of RamDiscardManager, shared
state is analogous to populated
On 30.05.25 10:32, Chenyi Qiang wrote:
Commit 852f0048f3 ("RAMBlock: make guest_memfd require uncoordinated
discard") highlighted that subsystems like VFIO may disable RAM block
discard. However, guest_memfd relies on discard operations for page
conversion between private and shared memory, poten
On 30.05.25 13:18, Michael S. Tsirkin wrote:
On Wed, May 14, 2025 at 11:26:05AM +0200, David Hildenbrand wrote:
On 14.05.25 11:12, Igor Mammedov wrote:
On Tue, 13 May 2025 15:12:11 +0200
David Hildenbrand wrote:
On 13.05.25 14:13, Igor Mammedov wrote:
On Mon, 3 Mar 2025 13:02:17 -0500
If something went wrong... well, on my AMD machine this usually means
the fw is really unhappy and recovery is hardly possible and the machine
needs reboot. Probably stopping the VM would make more sense for now (or
stop the device so the user could save work from the VM, dunno).
My current
On 27.05.25 07:47, Chenyi Qiang wrote:
On 5/26/2025 5:08 PM, David Hildenbrand wrote:
On 20.05.25 12:28, Chenyi Qiang wrote:
As guest_memfd is now managed by RamBlockAttribute with
RamDiscardManager, only block uncoordinated discard.
Signed-off-by: Chenyi Qiang
---
Changes in v5
On 26.05.25 12:19, Chenyi Qiang wrote:
On 5/26/2025 5:17 PM, David Hildenbrand wrote:
On 20.05.25 12:28, Chenyi Qiang wrote:
The current error handling is simple with the following assumption:
- QEMU will quit instead of resuming the guest if kvm_convert_memory()
fails, thus no need to
On 20.05.25 12:28, Chenyi Qiang wrote:
The current error handling is simple with the following assumption:
- QEMU will quit instead of resuming the guest if kvm_convert_memory()
fails, thus no need to do rollback.
- The convert range is required to be in the desired state. It is not
allowed
On 20.05.25 12:28, Chenyi Qiang wrote:
With the introduction of the RamBlockAttribute object to manage
RAMBlocks with guest_memfd, it is more elegant to move KVM set attribute
into a RamDiscardListener.
The KVM attribute change RamDiscardListener is registered/unregistered
for each memory region
On 20.05.25 12:28, Chenyi Qiang wrote:
As guest_memfd is now managed by RamBlockAttribute with
RamDiscardManager, only block uncoordinated discard.
Signed-off-by: Chenyi Qiang
---
Changes in v5:
- Revert to use RamDiscardManager.
Changes in v4:
- Modify commit message (RamDiscardMana
On 20.05.25 12:28, Chenyi Qiang wrote:
A new field, ram_shared, was introduced in RAMBlock to link to a
RamBlockAttribute object, which centralizes all guest_memfd state
information (such as fd and shared_bitmap) within a RAMBlock.
Create and initialize the RamBlockAttribute object upon ram_bloc
On 20.05.25 12:28, Chenyi Qiang wrote:
A new state_change() helper is introduced for RamBlockAttribute
to efficiently notify all registered RamDiscardListeners, including
VFIO listeners, about memory conversion events in guest_memfd. The VFIO
listener can dynamically DMA map/unmap shared pages ba
On 20.05.25 12:28, Chenyi Qiang wrote:
Commit 852f0048f3 ("RAMBlock: make guest_memfd require uncoordinated
discard") highlighted that subsystems like VFIO may disable RAM block
discard. However, guest_memfd relies on discard operations for page
conversion between private and shared memory, poten
VirtIOMEMReplayData, which makes
it cleaner.
Signed-off-by: Chenyi Qiang
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
at present.
Suggested-by: David Hildenbrand
Signed-off-by: Chenyi Qiang
---
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 17.05.25 15:55, Steven Sistare wrote:
On 5/16/2025 4:50 PM, David Hildenbrand wrote:
On 16.05.25 21:26, Steven Sistare wrote:
On 5/16/2025 2:58 PM, David Hildenbrand wrote:
On 16.05.25 19:13, Steve Sistare wrote:
Modify memory_get_xlat_addr and vfio_get_xlat_addr to return the memory
On 16.05.25 21:26, Steven Sistare wrote:
On 5/16/2025 2:58 PM, David Hildenbrand wrote:
On 16.05.25 19:13, Steve Sistare wrote:
Modify memory_get_xlat_addr and vfio_get_xlat_addr to return the memory
region that the translated address is found in. This will be needed by
CPR in a subsequent
r, errp);
-if (ret && mr_has_discard_manager) {
+mr = memory_translate_iotlb(iotlb, xlat_p, errp);
+if (!mr && memory_region_has_ram_discard_manager(mr)) {
Pretty sue this should be if (mr && ...)
otherwise we'd be dereferencing NULL :)
Apart from tha
On 16.05.25 05:23, Zhao Liu wrote:
On Thu, May 15, 2025 at 05:11:56PM +0100, Daniel P. Berrangé wrote:
Date: Thu, 15 May 2025 17:11:56 +0100
From: "Daniel P. Berrangé"
Subject: Re: [PATCH 8/9] target/s390x/kvm/pv: Consolidate
OBJECT_DEFINE_SIMPLE_TYPE_WITH_INTERFACES
On Thu, May 15, 2025 at
On 14.05.25 19:03, Cédric Le Goater wrote:
+ Paolo
+ David
+ Peter
+ Phil
On 5/12/25 22:51, John Levon wrote:
On Mon, May 12, 2025 at 08:32:37AM -0700, Steve Sistare wrote:
Modify memory_get_xlat_addr and vfio_get_xlat_addr to return the memory
region that the translated address is found in.
On 13.05.25 22:11, Michael S. Tsirkin wrote:
On Tue, May 13, 2025 at 07:21:36PM +0200, David Hildenbrand wrote:
On 12.05.25 17:16, Chaney, Ben wrote:
Hello,
When live migrating to a destination host with pmem there is a very
long downtime where the guest is paused. In some cases
On 14.05.25 11:12, Igor Mammedov wrote:
On Tue, 13 May 2025 15:12:11 +0200
David Hildenbrand wrote:
On 13.05.25 14:13, Igor Mammedov wrote:
On Mon, 3 Mar 2025 13:02:17 -0500
yuanminghao wrote:
Global used_memslots or used_shared_memslots is updated to 0 unexpectly
it shouldn't
Pasic
Cc: Christian Borntraeger
Cc: Thomas Huth
Cc: Richard Henderson
Cc: David Hildenbrand
Cc: Ilya Leoshkevich
Cc: qemu-s3...@nongnu.org
Signed-off-by: Zhao Liu
---
target/s390x/kvm/pv.c | 18 ++
1 file changed, 6 insertions(+), 12 deletions(-)
diff --git a/target/s390x/
On 12.05.25 17:16, Chaney, Ben wrote:
Hello,
When live migrating to a destination host with pmem there is a very
long downtime where the guest is paused. In some cases, this can be as high as
5 minutes, compared to less than one second in the good case.
Profiling suggests v
On 13.05.25 14:13, Igor Mammedov wrote:
On Mon, 3 Mar 2025 13:02:17 -0500
yuanminghao wrote:
Global used_memslots or used_shared_memslots is updated to 0 unexpectly
it shouldn't be 0 in practice, as it comes from number of RAM regions VM has.
It's likely a bug somewhere else.
I haven't to
ugin_vcpu_interrupt_cb() just after an interrupt got delivered?
`qemu_plugin_vcpu_interrupt_cb` or `qemu_plugin_vcpu_exception_cb` need
to be called after the CPU was set up (that is, after PC and any other
relevant register was set) and before the next instruction is executed.
So, yes, more or less.
Okay, thanks for the clarification!
Acked-by: David Hildenbrand
--
Cheers,
David / dhildenb
65506.31315-6-epere...@redhat.com>
Reviewed-by: Michael S. Tsirkin
Signed-off-by: Michael S. Tsirkin
I think this change here is fine, but it would be good getting Pete Xu's
opinion.
Acked-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 09.05.25 12:04, Chenyi Qiang wrote:
On 5/9/2025 4:22 PM, Baolu Lu wrote:
On 4/27/2025 10:26 AM, Chenyi Qiang wrote:
Hi David,
Any thought on patch 10-12, which is to move the change attribute into a
priority listener. A problem is how to handle the error handling of
private_to_shared fail
On 11.05.25 15:14, Julian Ganz wrote:
We recently introduced API for registering callbacks for trap related
events as well as the corresponding hook functions. Due to differences
between architectures, the latter need to be called from target specific
code.
This change places hooks for IBM Syste
On 09.05.25 04:38, Chao Gao wrote:
On Sun, Apr 27, 2025 at 10:26:52AM +0800, Chenyi Qiang wrote:
Hi David,
Any thought on patch 10-12, which is to move the change attribute into a
priority listener. A problem is how to handle the error handling of
private_to_shared failure. Previously, we thoug
Signed-off-by: Chenyi Qiang
<...>
+
+int ram_block_attribute_realize(RamBlockAttribute *attr, MemoryRegion
*mr)
+{
+ uint64_t shared_bitmap_size;
+ const int block_size = qemu_real_host_page_size();
+ int ret;
+
+ shared_bitmap_size = ROUND_UP(mr->size, block_size) / block_size;
On 02.05.25 23:45, Philippe Mathieu-Daudé wrote:
Remove unused "system/ram_addr.h" header. This file doesn't
use any target specific definitions anymore, compile it once
by moving it to system_virtio_ss[].
Signed-off-by: Philippe Mathieu-Daudé
Reviewed-by: David Hildenbrand
runtime.
Signed-off-by: Philippe Mathieu-Daudé
---
Acked-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 02.05.25 23:45, Philippe Mathieu-Daudé wrote:
Use target_system_arch() to check at runtime which target
architecture is being run.
Note, since TARGET_ARM is defined for TARGET_AARCH64, we
check for both ARM & AARCH64 enum values.
Signed-off-by: Philippe Mathieu-Daudé
---
Acked-by: D
On 30.04.25 11:58, Philippe Mathieu-Daudé wrote:
Hi Chao,
On 30/4/25 11:02, Chao Liu wrote:
Make the hierarchical relationship between nodes clearer by adding characters
W.r.t. $Subject, it isn't really about "optimization" but making
output clearer, as you describe.
e.g.
qemu-system-risc
On 30.04.25 06:02, Chao Liu wrote:
Make the hierarchical relationship between nodes clearer by adding characters
You should probably move most of your cover letter, including the example, in
here.
Signed-off-by: Chao Liu
---
system/memory.c | 34 +++---
1 file
On 27.04.25 03:40, Chenyi Qiang wrote:
On 4/25/2025 8:57 PM, David Hildenbrand wrote:
On 07.04.25 09:49, Chenyi Qiang wrote:
To manage the private and shared RAM states in confidential VMs,
introduce a new class of PrivateShareManager as a child of
GenericStateManager, which inherits the six
On 29.04.25 07:20, Nicholas Miehlbradt wrote:
The reset performed by subcode 3 of the diag308 instruction specifies
that system memory should be reset. This patch implements that
behaviour.
Introduce S390_RESET_REIPL_CLEAR to differentiate between subcode 3 and
subcode 4 resets.
When doing a cl
On 07.04.25 09:49, Chenyi Qiang wrote:
To manage the private and shared RAM states in confidential VMs,
introduce a new class of PrivateShareManager as a child of
GenericStateManager, which inherits the six interface callbacks. With a
different interface type, it can be distinguished from the
Ram
On 16.04.25 05:32, Chenyi Qiang wrote:
On 4/10/2025 9:44 AM, Chenyi Qiang wrote:
On 4/10/2025 8:11 AM, Alexey Kardashevskiy wrote:
On 9/4/25 22:57, Chenyi Qiang wrote:
On 4/9/2025 5:56 PM, Alexey Kardashevskiy wrote:
On 7/4/25 17:49, Chenyi Qiang wrote:
RamDiscardManager is an inte
On 09.04.25 11:56, Alexey Kardashevskiy wrote:
On 7/4/25 17:49, Chenyi Qiang wrote:
RamDiscardManager is an interface used by virtio-mem to adjust VFIO
mappings in relation to VM page assignment. It manages the state of
populated and discard for the RAM. To accommodate future scnarios for
mana
On 09.04.25 07:43, Alexey Kardashevskiy wrote:
On 7/4/25 17:49, Chenyi Qiang wrote:
Update ReplayRamDiscard() function to return the result and unify the
ReplayRamPopulate() and ReplayRamDiscard() to ReplayStateChange() at
the same time due to their identical definitions. This unification
simp
On 07.04.25 09:49, Chenyi Qiang wrote:
Update ReplayRamDiscard() function to return the result and unify the
ReplayRamPopulate() and ReplayRamDiscard() to ReplayStateChange() at
the same time due to their identical definitions. This unification
simplifies related structures, such as VirtIOMEMRepl
RamDiscardManager *rdm);>>> /**
* memory_region_find: translate an address/size relative to a
diff --git a/system/memory.c b/system/memory.c
index b17b5538ff..62d6b410f0 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -2115,12 +2115,16 @@ RamDiscardMan
ned-off-by: Philippe Mathieu-Daudé
---
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 11.04.25 13:43, Markus Armbruster wrote:
Daniel P. Berrangé writes:
On Fri, Apr 11, 2025 at 12:40:46PM +0200, Markus Armbruster wrote:
Daniel P. Berrangé writes:
On Wed, Apr 09, 2025 at 09:58:13AM +0200, Peter Krempa via Devel wrote:
On Wed, Apr 09, 2025 at 09:39:02 +0200, Markus Armbr
On 17.03.25 17:13, Philippe Mathieu-Daudé wrote:
Only file units within the system/ directory need access to
"memory-internal.h". Move it to system/ to restrict its scope.
Based-on: <20250314173139.2122904-1-pierrick.bouv...@linaro.org>
Reviewed-by: David Hildenbrand
-
On 17.03.25 03:54, Chenyi Qiang wrote:
On 3/14/2025 8:11 PM, Gupta, Pankaj wrote:
On 3/10/2025 9:18 AM, Chenyi Qiang wrote:
As the commit 852f0048f3 ("RAMBlock: make guest_memfd require
uncoordinated discard") highlighted, some subsystems like VFIO may
disable ram block discard. However, gues
On 14.03.25 10:30, Chenyi Qiang wrote:
On 3/14/2025 5:00 PM, David Hildenbrand wrote:
On 14.03.25 09:21, Chenyi Qiang wrote:
Hi David & Alexey,
Hi,
To keep the bitmap aligned, I add the undo operation for
set_memory_attributes() and use the bitmap + replay callback t
ugger.
Nothing jumped at me, with Richard's suggestion of keeping the new
function limited in scope
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 14.03.25 09:21, Chenyi Qiang wrote:
Hi David & Alexey,
Hi,
To keep the bitmap aligned, I add the undo operation for
set_memory_attributes() and use the bitmap + replay callback to do
set_memory_attributes(). Does this change make sense?
I assume you mean this hunk:
+ret =
memory_a
prototype declaration to "system/hostmem.h".
Signed-off-by: Philippe Mathieu-Daudé
Reviewed-by: Pierrick Bouvier
Reviewed-by: Eric Auger
Message-Id: <20250308230917.18907-7-phi...@linaro.org>
---
Acked-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 07.03.25 17:49, Philippe Mathieu-Daudé wrote:
On 7/3/25 17:38, Alex Bennée wrote:
Philippe Mathieu-Daudé writes:
Use qemu_arch_available() to check at runtime if a target
architecture is built in.
Signed-off-by: Philippe Mathieu-Daudé
---
hw/virtio/virtio-mem.c | 20 --
On 07.03.25 16:15, Philippe Mathieu-Daudé wrote:
Remove unused "exec/ram_addr.h" header. This file doesn't
use any target specific definitions anymore, compile it
once by moving it to system_virtio_ss[].
Signed-off-by: Philippe Mathieu-Daudé
Reviewed-by: David Hildenbrand
--
-Daudé
---
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 07.03.25 16:15, Philippe Mathieu-Daudé wrote:
Rather than checking ACPI availability at compile time by
checking the CONFIG_ACPI definition from CONFIG_DEVICES,
check at runtime via acpi_builtin().
Signed-off-by: Philippe Mathieu-Daudé
Reviewed-by: David Hildenbrand
--
Cheers,
David
rnel) have already been
marked to work only with KVM in the past, so those other tests are
skipped on the shared gitlab CI runners. As long as the problem isn't
fully understood and fixed, let's do the same with the virtio_balloon
test to avoid that the CI is failing here.
Reviewed-b
;.
To fix the latter, retry the stats query until seeing fresh data.
Adding 'quiet' to the kernel command line reduces serial output
which otherwise slows boot, making it less likely to hit the former
race too.
Signed-off-by: Daniel P. Berrangé
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 27.02.25 14:44, Roy Hopkins wrote:
Adds an IGVM loader to QEMU which processes a given IGVM file and
applies the directives within the file to the current guest
configuration.
The IGVM loader can be used to configure both confidential and
non-confidential guests. For confidential guests, the
to be of the format
guest_phys+sdma, allowing them to be used as lookup into the host
iommu table.
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
On 27.02.25 04:26, Chenyi Qiang wrote:
On 2/26/2025 8:43 PM, Chenyi Qiang wrote:
On 2/25/2025 5:41 PM, David Hildenbrand wrote:
On 25.02.25 03:00, Chenyi Qiang wrote:
On 2/21/2025 6:04 PM, Chenyi Qiang wrote:
On 2/21/2025 4:09 PM, David Hildenbrand wrote:
On 21.02.25 03:25, Chenyi
As commented offline, maybe one would want the option to enable the
alternative mode, where such updates (in the SHM region) are not sent to
vhost-user devices. In such a configuration, the MEM_READ / MEM_WRITE
would be unavoidable.
At first, I remember we discussed two options, having update me
+/* Ram device is remapped in new QEMU */
+if (memory_region_is_ram_device(mr)) {
+return true;
+}
+
+/* Named files are remapped in new QEMU, same contents if shared (no COW)
*/
+if (qemu_ram_is_shared(rb) && qemu_ram_is_named_file(rb)) {
+return true;
+}
In general
Reviewed-by: David Hildenbrand
just one more question:
+
+/* A file descriptor is remapped in new QEMU */
+if (rb->fd >= 0) {
+return true;
This looks odd / wrong. Assume we have
!qemu_ram_is_shared(rb) || !qemu_ram_is_named_file(rb)
(negated condition a
On 25.02.25 03:00, Chenyi Qiang wrote:
On 2/21/2025 6:04 PM, Chenyi Qiang wrote:
On 2/21/2025 4:09 PM, David Hildenbrand wrote:
On 21.02.25 03:25, Chenyi Qiang wrote:
On 2/21/2025 3:39 AM, David Hildenbrand wrote:
On 20.02.25 17:13, Jean-Philippe Brucker wrote:
For Arm CCA we'd
On 24.02.25 14:41, Albert Esteve wrote:
On Mon, Feb 24, 2025 at 10:49 AM David Hildenbrand wrote:
On 24.02.25 10:35, Albert Esteve wrote:
On Mon, Feb 24, 2025 at 10:16 AM David Hildenbrand wrote:
On 24.02.25 09:54, Albert Esteve wrote:
On Mon, Feb 17, 2025 at 9:01 PM David Hildenbrand
On 24.02.25 10:35, Albert Esteve wrote:
On Mon, Feb 24, 2025 at 10:16 AM David Hildenbrand wrote:
On 24.02.25 09:54, Albert Esteve wrote:
On Mon, Feb 17, 2025 at 9:01 PM David Hildenbrand wrote:
On 17.02.25 17:40, Albert Esteve wrote:
Hi all,
Hi,
looks like our debugging session was
On 24.02.25 09:54, Albert Esteve wrote:
On Mon, Feb 17, 2025 at 9:01 PM David Hildenbrand wrote:
On 17.02.25 17:40, Albert Esteve wrote:
Hi all,
Hi,
looks like our debugging session was successfu :)
One question below.
v3->v4
- Change mmap strategy to use RAM blocks
and subregi
On 21.02.25 09:26, David Hildenbrand wrote:
On 21.02.25 00:24, Michael S. Tsirkin wrote:
On Tue, Jan 28, 2025 at 07:57:03PM +0100, David Hildenbrand wrote:
This is based-on [1], which adds MSI-X support to virtio-balloon-pci,
but can be applied independently.
Turns out it is fairly easy to
On 21.02.25 00:24, Michael S. Tsirkin wrote:
On Tue, Jan 28, 2025 at 07:57:03PM +0100, David Hildenbrand wrote:
This is based-on [1], which adds MSI-X support to virtio-balloon-pci,
but can be applied independently.
Turns out it is fairly easy to get virtio-mem-pci running on s390x. We
only
On 21.02.25 03:25, Chenyi Qiang wrote:
On 2/21/2025 3:39 AM, David Hildenbrand wrote:
On 20.02.25 17:13, Jean-Philippe Brucker wrote:
For Arm CCA we'd like the guest_memfd discard notifier to call the IOMMU
notifiers and create e.g. VFIO mappings. The default VFIO discard
notifier
On 20.02.25 17:13, Jean-Philippe Brucker wrote:
For Arm CCA we'd like the guest_memfd discard notifier to call the IOMMU
notifiers and create e.g. VFIO mappings. The default VFIO discard
notifier isn't sufficient for CCA because the DMA addresses need a
translation (even without vIOMMU).
At the
object_get_typename(OBJECT(current_machine->cgs)));
+goto out_free;
+}
assert(new_block->guest_memfd < 0);
ret = ram_block_discard_require(true);
Reviewed-by: David Hildenbrand
--
Cheers,
David / dhildenb
instance is allowed to be set for
a MemoryRegion at present.
Suggested-by: David Hildenbrand
Signed-off-by: Chenyi Qiang
---
Changes in v2:
- newly added.
---
hw/virtio/virtio-mem.c | 30 +-
include/exec/memory.h | 6 +++---
system/memory.c| 11
On 17.02.25 17:40, Albert Esteve wrote:
Hi all,
Hi,
looks like our debugging session was successfu :)
One question below.
v3->v4
- Change mmap strategy to use RAM blocks
and subregions.
- Add new bitfield to qmp feature map
- Followed most review comments from
last iteration.
- Merge
On 14.02.25 21:12, Steve Sistare wrote:
Unlike cpr-reboot mode, cpr-transfer mode cannot save volatile ram blocks
in the migration stream file and recreate them later, because the physical
memory for the blocks is pinned and registered for vfio. Add a blocker
for volatile ram blocks.
Also add a
On 13.02.25 17:17, Igor Mammedov wrote:
On Thu, 13 Feb 2025 12:48:30 +0100
Markus Armbruster wrote:
gaosong writes:
Cc: Markus
hi, Markus
What is the difference between CPU_MODEL_EXPANSION_TYPE_STATIC and
CPU_MODEL_EXPANSION_TYPE_FULL?
the only difference is that 'static' expansion will
On 13.02.25 00:26, Stefan Zabka wrote:
Sorry for the delayed engagement, I failed to apply the patch set from
the mailing list and had to remember that David had published this
change set on GitHub.
Tested-by: Stefan Zabka
This addresses my initial use case of being able to write to a single
M
On 12.02.25 16:21, Peter Xu wrote:
On Mon, Feb 10, 2025 at 09:46:46AM +0100, David Hildenbrand wrote:
We want to pass another flag that will be stored in MemTxAttrs. So pass
MemTxAttrs directly.
Reviewed-by: Peter Xu
Reviewed-by: Philippe Mathieu-Daudé
Signed-off-by: David Hildenbrand
On 07.02.25 21:56, Matthew Rosato wrote:
When receiving a guest mpcifc(4) or mpcifc(6) instruction without the T
bit set, treat this as a request to perform direct mapping instead of
address translation. In order to facilitate this, pin the entirety of
guest memory into the host iommu.
Pinning
zUr6AY3X=x...@mail.gmail.com/
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/213
Reviewed-by: Peter Xu
Signed-off-by: David Hildenbrand
---
hw/core/cpu-system.c| 13 +
include/exec/memattrs.h | 5 -
include/exec/memory.h | 3 ++-
system/physmem.c| 9 ++--
We don't need the MemTxAttrs, so let's simply use the simpler function
variant.
Reviewed-by: Peter Xu
Reviewed-by: Philippe Mathieu-Daudé
Signed-off-by: David Hildenbrand
---
monitor/hmp-cmds-target.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/monito
We want to pass another flag that will be stored in MemTxAttrs. So pass
MemTxAttrs directly.
Reviewed-by: Peter Xu
Reviewed-by: Philippe Mathieu-Daudé
Signed-off-by: David Hildenbrand
---
hw/core/loader.c | 2 +-
hw/remote/vfio-user-obj.c | 2 +-
include/exec/memory.h | 5
E.
Reviewed-by: Peter Xu
Signed-off-by: David Hildenbrand
---
include/exec/memory.h | 14 +++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/include/exec/memory.h b/include/exec/memory.h
index cb35c38402..4e2cf95ab6 100644
--- a/include/exec/memory.h
+++ b/include/exec/memo
EVICE regions are also RAM regions, so we can check for RAM+ROMD
first.
This is a preparation for further changes.
Reviewed-by: Peter Xu
Signed-off-by: David Hildenbrand
---
include/exec/memory.h | 10 ++
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/include/exec/
to write to
these (and IO) regions.
This is a preparation for further changes.
Cc: Alex Williamson
Reviewed-by: Peter Xu
Signed-off-by: David Hildenbrand
---
system/physmem.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/system/physmem.c b/system/physmem.c
index 67c9db9
Peter Xu
Signed-off-by: David Hildenbrand
---
include/exec/memory.h | 13 ++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 9f73b59867..5cd7574c60 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -2997
hieu-Daudé
Cc: Peter Maydell
Cc: Alex Bennée
Cc: Alex Williamson
Cc: Eduardo Habkost
Cc: Marcel Apfelbaum
Cc: Elena Ufimtseva
Cc: Jagannathan Raman
Cc: "Dr. David Alan Gilbert"
Cc: Stefan Zabka
David Hildenbrand (7):
physmem: factor out memory_region_is_ram_device() check
On 04.02.25 18:58, Peter Xu wrote:
On Tue, Feb 04, 2025 at 06:50:17PM +0100, David Hildenbrand wrote:
/*
@@ -595,6 +628,7 @@ static const TypeInfo host_memory_backend_info = {
.instance_size = sizeof(HostMemoryBackend),
.instance_init = host_memory_backend_init
1 - 100 of 1495 matches
Mail list logo
