The 'es1370_transfer_audio' method has a 4k byte array used for
copying data between the audio backend and device. Skip the automatic
zero-init of this array to eliminate the performance overhead in
the I/O hot path.
The 'tmpbuf' array will be fully initialized when reading data from
the audio backend and/or device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-10-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The 'cs_write_audio' method has a pair of byte arrays, one 4k in size
and one 8k, which are used in converting audio samples. Skip the
automatic zero-init of these arrays to eliminate the performance
overhead in the I/O hot path.
The 'tmpbuf' array will be fully initialized when reading a block of
data from the guest. The 'linbuf' array will be fully initialized
when converting the audio samples.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-9-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The 'read_audio' & 'write_audio' methods have a 4k byte array used
for copying data between the audio backend and device. Skip the
automatic zero-init of these arrays to eliminate the performance
overhead in the I/O hot path.
The 'tmpbuf' array will be fully initialized when reading data from
the audio backend and/or device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-8-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Since commit 7ff9ff0393 ("meson: mitigate against use of uninitialize
stack for exploits") the -ftrivial-auto-var-init=zero compiler option is
used to zero local variables. While this reduces security risks
associated with uninitialized stack data, it introduced a measurable
bottleneck in the virtqueue_split_pop() and virtqueue_packed_pop()
functions.
These virtqueue functions are in the hot path. They are called for each
element (request) that is popped from a VIRTIO device's virtqueue. Using
__attribute__((uninitialized)) on large stack variables in these
functions improves fio randread bs=4k iodepth=64 performance from 304k
to 332k IOPS (+9%).
This issue was found using perf-top(1). virtqueue_split_pop() was one of
the top CPU consumers and the "annotate" feature showed that the memory
zeroing instructions at the beginning of the functions were hot.
Fixes: 7ff9ff0393 ("meson: mitigate against use of uninitialize stack for exploits")
Cc: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-3-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
default_bus_bypass_iommu tells us whether the bypass_iommu is set
for the default PCIe root bus. Make sure we check that before adding
the "iommu-map" DT property.
Cc: qemu-stable@nongnu.org
Fixes: 6d7a85483a ("hw/arm/virt: Add default_bus_bypass_iommu machine option")
Suggested-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Message-id: 20250602114655.42920-1-shameerali.kolothum.thodi@huawei.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Move event_notifier_cleanup calls to a helper vfio_notifier_cleanup.
This version is trivial, and does not yet use the vdev and nr parameters.
No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-17-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Pass the vector number to vfio_connect_kvm_msi_virq and
vfio_remove_kvm_msi_virq, so it can be passed to their subroutines in
a subsequent patch. No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-15-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Move event_notifier_init calls to a helper vfio_notifier_init.
This version is trivial, but it will be expanded to support CPR
in subsequent patches. No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-14-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Do not reset a vfio-pci device during CPR, and do not complain if the
kernel's PCI config space changes for non-emulated bits between the
vmstate save and load, which can happen due to ongoing interrupt activity.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-12-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
If there are multiple containers and unmap-all fails for some container, we
need to remap vaddr for the other containers for which unmap-all succeeded.
Recover by walking all address ranges of all containers to restore the vaddr
for each. Do so by invoking the vfio listener callback, and passing a new
"remap" flag that tells it to restore a mapping without re-allocating new
userland data structures.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-9-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
During CPR, after VFIO_DMA_UNMAP_FLAG_VADDR, the vaddr is temporarily
invalid, so mediated devices cannot be supported. Add a blocker for them.
This restriction will not apply to iommufd containers when CPR is added
for them in a future patch.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-8-git-send-email-steven.sistare@oracle.com
[ clg: Fixed context change in VFIODevice ]
Signed-off-by: Cédric Le Goater <clg@redhat.com>
In new QEMU, do not register the memory listener at device creation time.
Register it later, in the container post_load handler, after all vmstate
that may affect regions and mapping boundaries has been loaded. The
post_load registration will cause the listener to invoke its callback on
each flat section, and the calls will match the mappings remembered by the
kernel.
The listener calls a special dma_map handler that passes the new VA of each
section to the kernel using VFIO_DMA_MAP_FLAG_VADDR. Restore the normal
handler at the end.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-7-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
In the container pre_save handler, discard the virtual addresses in DMA
mappings with VFIO_DMA_UNMAP_FLAG_VADDR, because guest RAM will be
remapped at a different VA after in new QEMU. DMA to already-mapped
pages continues.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-6-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
At vfio creation time, save the value of vfio container, group, and device
descriptors in CPR state. On qemu restart, vfio_realize() finds and uses
the saved descriptors.
During reuse, device and iommu state is already configured, so operations
in vfio_realize that would modify the configuration, such as vfio ioctl's,
are skipped. The result is that vfio_realize constructs qemu data
structures that reflect the current state of the device.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-5-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Register a legacy container for cpr-transfer, replacing the generic CPR
register call with a more specific legacy container register call. Add a
blocker if the kernel does not support VFIO_UPDATE_VADDR or VFIO_UNMAP_ALL.
This is mostly boiler plate. The fields to to saved and restored are added
in subsequent patches.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-4-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
For vfio-user, the region write implementation needs to know if the
write is posted; add the necessary plumbing to support this.
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250607001056.335310-5-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
For vfio-user, each region has its own fd rather than sharing
vbasedev's. Add the necessary plumbing to support this, and use the
correct fd in vfio_region_mmap().
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250607001056.335310-4-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
The vfio-user code will need to re-use various parts of the vfio PCI
code. Export them in hw/vfio/pci.h, and rename them to the vfio_pci_*
namespace.
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Mark Cave-Ayland <mark.caveayland@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250607001056.335310-2-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Handle interception of the CHSC SEI instruction for requests
indicating the guest's AP configuration has changed.
If configuring --without-default-devices, hw/s390x/ap-stub.c
was created to handle such circumstance. Also added the
following to hw/s390x/meson.build if CONFIG_VFIO_AP is
false, it will use the stub file.
Signed-off-by: Rorie Reyes <rreyes@linux.ibm.com>
Reviewed-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250609164418.17585-5-rreyes@linux.ibm.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
These functions can be invoked by the function that handles interception
of the CHSC SEI instruction for requests indicating the accessibility of
one or more adjunct processors has changed.
Signed-off-by: Rorie Reyes <rreyes@linux.ibm.com>
Reviewed-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Link: https://lore.kernel.org/qemu-devel/20250609164418.17585-4-rreyes@linux.ibm.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Creates an object indicating that an AP configuration change event
has been received and stores it in a queue. These objects will later
be used to store event information for an AP configuration change
when the CHSC instruction is intercepted.
Signed-off-by: Rorie Reyes <rreyes@linux.ibm.com>
Reviewed-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Link: https://lore.kernel.org/qemu-devel/20250609164418.17585-3-rreyes@linux.ibm.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Register an event notifier handler to process AP configuration
change events by queuing the event and generating a CRW to let
the guest know its AP configuration has changed
Signed-off-by: Rorie Reyes <rreyes@linux.ibm.com>
Reviewed-by: Anthony Krowiak <akrowiak@linux.ibm.com>
Link: https://lore.kernel.org/qemu-devel/20250609164418.17585-2-rreyes@linux.ibm.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Currently the final instance_size of VFIO_PCI_BASE is sizeof(PCIDevice).
It should be sizeof(VFIOPCIDevice), VFIO_PCI uses same structure as
base class VFIO_PCI_BASE, so no need to set its instance_size explicitly.
This isn't catastrophic only because VFIO_PCI_BASE is an abstract class.
Fixes: d4e392d0a9 ("vfio: add vfio-pci-base class")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/qemu-devel/20250611024228.423666-1-zhenzhong.duan@intel.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
It's wrong to call into listener_begin callback in vfio_listener_commit().
Currently this impacts vfio-user.
Fixes: d9b7d8b699 ("vfio/container: pass listener_begin/commit callbacks")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: John Levon <john.levon@nutanix.com>
Link: https://lore.kernel.org/qemu-devel/20250609115433.401775-1-zhenzhong.duan@intel.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
With the upcoming release of QEMU 10.1, the s390-ccw-virtio-4.1 machine
will be older than 6 years, so according to our machine support policy,
it can be removed now. The V4_1 CPU feature group gets merged into the
minimum CPU feature group now.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-ID: <20250519054744.36715-1-thuth@redhat.com>
Change the asset link to one which is working from the PARISC website.
Signed-off-by: Soumyajyotii Ssarkar <soumyajyotisarkar23@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <20250607152711.108914-2-soumyajyotisarkar23@gmail.com>
[PMD: Split patch in 2]
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
The tracing function for the write case incorrectly has
parameters switched around. So order them in the correct way.
Signed-off-by: Philippe Michaud-Boudreault <philmb3487@proton.me>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <HnyjTNqwrfGusE44bnM7kuLuj13Di1VgXN-dXVHMOSnfgCUhoipOVIoVS1WQaKrJxmEDy9XJGdlQj6zVTIdJE0QVlfBhfbcckFFWRRP56uY=@proton.me>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
RISCVIOMMUPciClass and RISCVIOMMUSysClass are defined with missed
parent class, class_init on them may corrupt their parent class
fields.
It's lucky that parent_realize and parent_phases are not initialized
or used until now, so just remove the definitions. They can be added
back when really necessary.
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-ID: <20250606092406.229833-6-zhenzhong.duan@intel.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
We have pin_count <= PCA955X_PIN_COUNT_MAX. Having
PCA955X_PIN_COUNT_MAX = 16, it is safe to explicitly
allocate the char buffer on the stack, without g_newa().
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Reviewed-by: Glenn Miles <milesg@linux.ibm.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20250605193540.59874-2-philmd@linaro.org>
Rather than accessing the attributes of TYPE_CCSR directly, use the SysBusDevice
API which exists exactly for that purpose. Furthermore, registering the memory
region with the SysBusDevice API makes it show up in QMP's `info qom-tree`
command.
Signed-off-by: Bernhard Beschow <shentey@gmail.com>
Reviewed-by: BALATON Zoltan <balaton@eik.bme.hu>
[balaton: rebased]
Signed-off-by: BALATON Zoltan <balaton@eik.bme.hu>
Acked-by: Bernhard Beschow <shentey@gmail.com>
Message-ID: <619a58d1f83d2aad5b4feec930d46c64abff0977.1748012109.git.balaton@eik.bme.hu>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Use default MAC address if none is specified by property as done by
most other network interface models.
Signed-off-by: BALATON Zoltan <balaton@eik.bme.hu>
Reviewed-by: Bernhard Beschow <shentey@gmail.com>
Acked-by: Bernhard Beschow <shentey@gmail.com>
Message-ID: <8bd7ca691bd502b5fd761615d9af805e783fba36.1748012109.git.balaton@eik.bme.hu>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Different machines have different frequencies so make this
configurable in machine class instead of using a hard coded constant.
Signed-off-by: BALATON Zoltan <balaton@eik.bme.hu>
Acked-by: Bernhard Beschow <shentey@gmail.com>
Message-ID: <431166f96ff12ff3dbc670d40544974415f11305.1748012109.git.balaton@eik.bme.hu>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
The QOM type of HvBalloon is declared by OBJECT_DECLARE_SIMPLE_TYPE,
which means it doesn't need the class!
Therefore, use OBJECT_DEFINE_SIMPLE_TYPE_WITH_INTERFACES to implement
the type, then there's no need for class definition.
Cc: "Maciej S. Szmigiero" <maciej.szmigiero@oracle.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
Acked-by: Maciej S. Szmigiero <maciej.szmigiero@oracle.com>
Message-ID: <20250514084957.2221975-6-zhao1.liu@intel.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
This reverts commit d0b2542574.
Loading firmware from the PCI host is unusual and raven is only used
by one board so this does not simplify anything but rather complicates
it. Revert to loading firmware from board code as that is the usual
way and also because raven has nothing to do with ROM so it is not a
good place for this.
Signed-off-by: BALATON Zoltan <balaton@eik.bme.hu>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <4ca4f71bf661923d9a91b7e6776a0e40726e2337.1746374076.git.balaton@eik.bme.hu>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
This was a workaround for the prep machine that was removed 5 years
ago so this is no longer needed.
Fixes: b2ce76a073 (hw/ppc/prep: Remove the deprecated "prep" machine and the OpenHackware BIOS)
Signed-off-by: BALATON Zoltan <balaton@eik.bme.hu>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-ID: <0d41c18a8831bd4c8b0948eda3ef8f60f5a311f3.1746374076.git.balaton@eik.bme.hu>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
QOM types are now registered using as TypeInfo via DEFINE_TYPES()
or type_init(). Update TYPE_SH_SERIAL, removing the empty QOM
instance_init/finalize handlers.
This was definitely wrong, because OBJECT_DEFINE_TYPE() is only
for cases where the class needs its own virtual methods or some
other per-class state in its own class struct.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-Id: <20250124175053.74461-3-philmd@linaro.org>
fifo_timeout_timer is created in the DeviceRealize handler,
not in the instance_init one. For parity, delete it in
DeviceUnrealize, rather than instance_finalize.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-Id: <20250124175053.74461-2-philmd@linaro.org>
Global variables memmap_table and memmap_entries stores UEFI memory
map table informations. It can be moved into structure
LoongArchVirtMachineState.
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Reviewed-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20250430094738.1556670-3-maobibo@loongson.cn>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Global variables initrd_offset and initrd_size records loading information
about initrd, it can be moved to structure loongarch_boot_info.
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20250430094738.1556670-2-maobibo@loongson.cn>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Commit bab27ea2e3 ("hw/arm/virt: smbios:
inform guest of kvm") fixes the same issue
on arm.
without this patch:
[root@localhost ~]# virt-what
qemu
with this patch:
[root@localhost ~]# virt-what
kvm
Signed-off-by: Qiang Ma <maqianga@uniontech.com>
Reviewed-by: Bibo Mao <maobibo@loongson.cn>
Reviewed-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20250603031813.31794-1-maqianga@uniontech.com>
Signed-off-by: Song Gao <gaosong@loongson.cn>
With PCH ID register, it is defined as union type as follows:
union LoongArchPIC_ID {
struct {
uint8_t _reserved_0[3];
uint8_t id;
uint8_t version;
uint8_t _reserved_1;
uint8_t irq_num;
uint8_t _reserved_2;
} QEMU_PACKED desc;
uint64_t data;
}
And with pch driver in virt machine irq_number is parsed with little
endian method:
vec_count = ((readq(priv->base) >> 48) & 0xff) + 1
So the value of ID register should be converted to little endian.
With this patch, linux kernel passes to run on S390 big endian host
machine with TCG method.
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Reviewed-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20250604065502.1114098-3-maobibo@loongson.cn>
Signed-off-by: Song Gao <gaosong@loongson.cn>
