If the device is not a failover primary device, call
vfio_migration_probe() and vfio_migration_finalize() to enable
migration support for those devices that support it respectively to
tear it down again.
Removed migration blocker from VFIO PCI device specific structure and use
migration blocker from generic structure of VFIO device.
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Added functions to save and restore PCI device specific data,
specifically config space of PCI device.
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Make the type checking macro name consistent with the TYPE_*
constant.
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Message-Id: <20200902224311.1321159-56-ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
This will make future conversion to OBJECT_DECLARE* easier.
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Tested-By: Roman Bolshakov <r.bolshakov@yadro.com>
Message-Id: <20200825192110.3528606-43-ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
When all we do with an Error we receive into a local variable is
propagating to somewhere else, we can just as well receive it there
right away. The previous commit did that with a Coccinelle script I
consider fairly trustworthy. This commit uses the same script with
the matching of return taken out, i.e. we convert
if (!foo(..., &err)) {
...
error_propagate(errp, err);
...
}
to
if (!foo(..., errp)) {
...
...
}
This is unsound: @err could still be read between afterwards. I don't
know how to express "no read of @err without an intervening write" in
Coccinelle. Instead, I manually double-checked for uses of @err.
Suboptimal line breaks tweaked manually. qdev_realize() simplified
further to placate scripts/checkpatch.pl.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200707160613.848843-36-armbru@redhat.com>
When all we do with an Error we receive into a local variable is
propagating to somewhere else, we can just as well receive it there
right away. Convert
if (!foo(..., &err)) {
...
error_propagate(errp, err);
...
return ...
}
to
if (!foo(..., errp)) {
...
...
return ...
}
where nothing else needs @err. Coccinelle script:
@rule1 forall@
identifier fun, err, errp, lbl;
expression list args, args2;
binary operator op;
constant c1, c2;
symbol false;
@@
if (
(
- fun(args, &err, args2)
+ fun(args, errp, args2)
|
- !fun(args, &err, args2)
+ !fun(args, errp, args2)
|
- fun(args, &err, args2) op c1
+ fun(args, errp, args2) op c1
)
)
{
... when != err
when != lbl:
when strict
- error_propagate(errp, err);
... when != err
(
return;
|
return c2;
|
return false;
)
}
@rule2 forall@
identifier fun, err, errp, lbl;
expression list args, args2;
expression var;
binary operator op;
constant c1, c2;
symbol false;
@@
- var = fun(args, &err, args2);
+ var = fun(args, errp, args2);
... when != err
if (
(
var
|
!var
|
var op c1
)
)
{
... when != err
when != lbl:
when strict
- error_propagate(errp, err);
... when != err
(
return;
|
return c2;
|
return false;
|
return var;
)
}
@depends on rule1 || rule2@
identifier err;
@@
- Error *err = NULL;
... when != err
Not exactly elegant, I'm afraid.
The "when != lbl:" is necessary to avoid transforming
if (fun(args, &err)) {
goto out
}
...
out:
error_propagate(errp, err);
even though other paths to label out still need the error_propagate().
For an actual example, see sclp_realize().
Without the "when strict", Coccinelle transforms vfio_msix_setup(),
incorrectly. I don't know what exactly "when strict" does, only that
it helps here.
The match of return is narrower than what I want, but I can't figure
out how to express "return where the operand doesn't use @err". For
an example where it's too narrow, see vfio_intx_enable().
Silently fails to convert hw/arm/armsse.c, because Coccinelle gets
confused by ARMSSE being used both as typedef and function-like macro
there. Converted manually.
Line breaks tidied up manually. One nested declaration of @local_err
deleted manually. Preexisting unwanted blank line dropped in
hw/riscv/sifive_e.c.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200707160613.848843-35-armbru@redhat.com>
VFIO is (except devices without a physical IOMMU or some mediated devices)
incompatible with discarding of RAM. The kernel will pin basically all VM
memory. Let's convert to ram_block_discard_disable(), which can now
fail, in contrast to qemu_balloon_inhibit().
Leave "x-balloon-allowed" named as it is for now.
Reviewed-by: Tony Krowiak <akrowiak@linux.ibm.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Tony Krowiak <akrowiak@linux.ibm.com>
Cc: Halil Pasic <pasic@linux.ibm.com>
Cc: Pierre Morel <pmorel@linux.ibm.com>
Cc: Eric Farman <farman@linux.ibm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20200626072248.78761-4-david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
VFIO is currently the only one left that is not using the generic
function (kvm_irqchip_add_irqfd_notifier_gsi()) to register irqfds.
Let VFIO use the common framework too.
Follow up patches will introduce extra features for kvm irqfd, so that
VFIO can easily leverage that after the switch.
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20200318145204.74483-3-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Several functions can't fail anymore: ich9_pm_add_properties(),
device_add_bootindex_property(), ppc_compat_add_property(),
spapr_caps_add_properties(), PropertyInfo.create(). Drop their @errp
parameter.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20200505152926.18877-16-armbru@redhat.com>
The kvm irqchip notifier is only registered if the device supports
INTx, however it's unconditionally removed. If the assigned device
does not support INTx, this will cause QEMU to crash when unplugging
the device from the system. Change it to conditionally remove the
notifier only if the notify hook is setup.
CC: Eduardo Habkost <ehabkost@redhat.com>
CC: David Gibson <david@gibson.dropbear.id.au>
CC: Alex Williamson <alex.williamson@redhat.com>
Cc: qemu-stable@nongnu.org # v4.2
Reported-by: yanghliu@redhat.com
Debugged-by: Eduardo Habkost <ehabkost@redhat.com>
Fixes: c5478fea27 ("vfio/pci: Respond to KVM irqchip change notifier")
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1782678
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Greg Kurz <groug@kaod.org>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
VFIO PCI devices already respond to the pci intx routing notifier, in order
to update kernel irqchip mappings when routing is updated. However this
won't handle the case where the irqchip itself is replaced by a different
model while retaining the same routing. This case can happen on
the pseries machine type due to PAPR feature negotiation.
To handle that case, add a handler for the irqchip change notifier, which
does much the same thing as the routing notifier, but is unconditional,
rather than being a no-op when the routing hasn't changed.
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Greg Kurz <groug@kaod.org>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
This splits the vfio_intx_update() function into one part doing the actual
reconnection with the KVM irqchip (vfio_intx_update(), now taking an
argument with the new routing) and vfio_intx_routing_notifier() which
handles calls to the pci device intx routing notifier and calling
vfio_intx_update() when necessary. This will make adding support for the
irqchip change notifier easier.
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Greg Kurz <groug@kaod.org>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
When an error occurs in migrate_add_blocker() it sets a
negative return value and uses error pointer we pass in.
Instead of just looking at the error pointer check for a negative return
value and avoid a coverity error because the return value is
set but never used. This fixes CID 1407219.
Reported-by: Coverity (CID 1407219)
Fixes: f045a0104c ("vfio: unplug failover primary device before migration")
Signed-off-by: Jens Freimann <jfreimann@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
When user tries to hotplug a VFIO device, but the operation fails
somewhere in the middle (in my testing it failed because of
RLIMIT_MEMLOCK forbidding more memory allocation), then a double
free occurs. In vfio_realize() the vdev->migration_blocker is
allocated, then something goes wrong which causes control to jump
onto 'error' label where the error is freed. But the pointer is
left pointing to invalid memory. Later, when
vfio_instance_finalize() is called, the memory is freed again.
In my testing the second hunk was sufficient to fix the bug, but
I figured the first hunk doesn't hurt either.
==169952== Invalid read of size 8
==169952== at 0xA47DCD: error_free (error.c:266)
==169952== by 0x4E0A18: vfio_instance_finalize (pci.c:3040)
==169952== by 0x8DF74C: object_deinit (object.c:606)
==169952== by 0x8DF7BE: object_finalize (object.c:620)
==169952== by 0x8E0757: object_unref (object.c:1074)
==169952== by 0x45079C: memory_region_unref (memory.c:1779)
==169952== by 0x45376B: do_address_space_destroy (memory.c:2793)
==169952== by 0xA5C600: call_rcu_thread (rcu.c:283)
==169952== by 0xA427CB: qemu_thread_start (qemu-thread-posix.c:519)
==169952== by 0x80A8457: start_thread (in /lib64/libpthread-2.29.so)
==169952== by 0x81C96EE: clone (in /lib64/libc-2.29.so)
==169952== Address 0x143137e0 is 0 bytes inside a block of size 48 free'd
==169952== at 0x4A342BB: free (vg_replace_malloc.c:530)
==169952== by 0xA47E05: error_free (error.c:270)
==169952== by 0x4E0945: vfio_realize (pci.c:3025)
==169952== by 0x76A4FF: pci_qdev_realize (pci.c:2099)
==169952== by 0x689B9A: device_set_realized (qdev.c:876)
==169952== by 0x8E2C80: property_set_bool (object.c:2080)
==169952== by 0x8E0EF6: object_property_set (object.c:1272)
==169952== by 0x8E3FC8: object_property_set_qobject (qom-qobject.c:26)
==169952== by 0x8E11DB: object_property_set_bool (object.c:1338)
==169952== by 0x5E7BDD: qdev_device_add (qdev-monitor.c:673)
==169952== by 0x5E81E5: qmp_device_add (qdev-monitor.c:798)
==169952== by 0x9E18A8: do_qmp_dispatch (qmp-dispatch.c:132)
==169952== Block was alloc'd at
==169952== at 0x4A35476: calloc (vg_replace_malloc.c:752)
==169952== by 0x51B1158: g_malloc0 (in /usr/lib64/libglib-2.0.so.0.6000.6)
==169952== by 0xA47357: error_setv (error.c:61)
==169952== by 0xA475D9: error_setg_internal (error.c:97)
==169952== by 0x4DF8C2: vfio_realize (pci.c:2737)
==169952== by 0x76A4FF: pci_qdev_realize (pci.c:2099)
==169952== by 0x689B9A: device_set_realized (qdev.c:876)
==169952== by 0x8E2C80: property_set_bool (object.c:2080)
==169952== by 0x8E0EF6: object_property_set (object.c:1272)
==169952== by 0x8E3FC8: object_property_set_qobject (qom-qobject.c:26)
==169952== by 0x8E11DB: object_property_set_bool (object.c:1338)
==169952== by 0x5E7BDD: qdev_device_add (qdev-monitor.c:673)
Fixes: f045a0104c ("vfio: unplug failover primary device before migration")
Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
As usual block all vfio-pci devices from being migrated, but make an
exception for failover primary devices. This is achieved by setting
unmigratable to 0 but also add a migration blocker for all vfio-pci
devices except failover primary devices. These will be unplugged before
migration happens by the migration handler of the corresponding
virtio-net standby device.
Signed-off-by: Jens Freimann <jfreimann@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Message-Id: <20191029114905.6856-12-jfreimann@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The following guest behaviour patter leads to double free in VFIO PCI:
1. Guest enables MSI interrupts
vfio_msi_enable is called, but fails in vfio_enable_vectors.
In our case this was because VFIO GPU device was in D3 state.
Unhappy path in vfio_msi_enable will g_free(vdev->msi_vectors) but not
set this pointer to NULL
2. Guest still sees MSI an enabled after that because emulated config
write is done in vfio_pci_write_config unconditionally before calling
vfio_msi_enable
3. Guest disables MSI interrupts
vfio_msi_disable is called and tries to g_free(vdev->msi_vectors)
in vfio_msi_disable_common => double free
Signed-off-by: Evgeny Yakovlev <wrfsh@yandex-team.ru>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
sysemu/sysemu.h is a rather unfocused dumping ground for stuff related
to the system-emulator. Evidence:
* It's included widely: in my "build everything" tree, changing
sysemu/sysemu.h still triggers a recompile of some 1100 out of 6600
objects (not counting tests and objects that don't depend on
qemu/osdep.h, down from 5400 due to the previous two commits).
* It pulls in more than a dozen additional headers.
Split stuff related to run state management into its own header
sysemu/runstate.h.
Touching sysemu/sysemu.h now recompiles some 850 objects. qemu/uuid.h
also drops from 1100 to 850, and qapi/qapi-types-run-state.h from 4400
to 4200. Touching new sysemu/runstate.h recompiles some 500 objects.
Since I'm touching MAINTAINERS to add sysemu/runstate.h anyway, also
add qemu/main-loop.h.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20190812052359.30071-30-armbru@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
[Unbreak OS-X build]
In my "build everything" tree, changing hw/qdev-properties.h triggers
a recompile of some 2700 out of 6600 objects (not counting tests and
objects that don't depend on qemu/osdep.h).
Many places including hw/qdev-properties.h (directly or via hw/qdev.h)
actually need only hw/qdev-core.h. Include hw/qdev-core.h there
instead.
hw/qdev.h is actually pointless: all it does is include hw/qdev-core.h
and hw/qdev-properties.h, which in turn includes hw/qdev-core.h.
Replace the remaining uses of hw/qdev.h by hw/qdev-properties.h.
While there, delete a few superfluous inclusions of hw/qdev-core.h.
Touching hw/qdev-properties.h now recompiles some 1200 objects.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Daniel P. Berrangé" <berrange@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20190812052359.30071-22-armbru@redhat.com>
In my "build everything" tree, changing qemu/main-loop.h triggers a
recompile of some 5600 out of 6600 objects (not counting tests and
objects that don't depend on qemu/osdep.h). It includes block/aio.h,
which in turn includes qemu/event_notifier.h, qemu/notify.h,
qemu/processor.h, qemu/qsp.h, qemu/queue.h, qemu/thread-posix.h,
qemu/thread.h, qemu/timer.h, and a few more.
Include qemu/main-loop.h only where it's needed. Touching it now
recompiles only some 1700 objects. For block/aio.h and
qemu/event_notifier.h, these numbers drop from 5600 to 2800. For the
others, they shrink only slightly.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20190812052359.30071-21-armbru@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
In my "build everything" tree, changing hw/hw.h triggers a recompile
of some 2600 out of 6600 objects (not counting tests and objects that
don't depend on qemu/osdep.h).
The previous commits have left only the declaration of hw_error() in
hw/hw.h. This permits dropping most of its inclusions. Touching it
now recompiles less than 200 objects.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20190812052359.30071-19-armbru@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
In my "build everything" tree, changing migration/vmstate.h triggers a
recompile of some 2700 out of 6600 objects (not counting tests and
objects that don't depend on qemu/osdep.h).
hw/hw.h supposedly includes it for convenience. Several other headers
include it just to get VMStateDescription. The previous commit made
that unnecessary.
Include migration/vmstate.h only where it's still needed. Touching it
now recompiles only some 1600 objects.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20190812052359.30071-16-armbru@redhat.com>
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Report an error in case we fail to set a trigger action
on any VFIO_PCI_MSIX_IRQ_INDEX subindex. This might be
useful in debugging a device that is not working properly.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reported-by: Coverity (CID 1402196)
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
The code used to assign an interrupt index/subindex to an
eventfd is duplicated many times. Let's introduce an helper that
allows to set/unset the signaling for an ACTION_TRIGGER,
ACTION_MASK or ACTION_UNMASK action.
In the error message, we now use errno in case of any
VFIO_DEVICE_SET_IRQS ioctl failure.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Li Qiang <liq3ea@gmail.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
The MSI-X relocation code can sometimes be used to work around bogus
MSI-X capabilities, but this test for whether the PBA is outside of
the specified BAR causes the device to error before we can apply a
relocation. Let it proceed if we intend to relocate MSI-X anyway.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
The resizable BAR capability is currently exposed read-only from the
kernel and we don't yet implement a protocol for virtualizing it to
the VM. Exposing it to the guest read-only introduces poor behavior
as the guest has no reason to test that a control register write is
accepted by the hardware. This can lead to cases where the guest OS
assumes the BAR has been resized, but it hasn't. This has been
observed when assigning AMD Vega GPUs.
Note, this does not preclude future enablement of resizable BARs, but
it's currently incorrect to expose this capability as read-only, so
better to not expose it at all.
Reported-by: James Courtier-Dutton <james.dutton@gmail.com>
Tested-by: James Courtier-Dutton <james.dutton@gmail.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Rather than looking inside the definition of a DeviceState with
"s->qdev", use the QOM prefered style: "DEVICE(s)".
This patch was generated using the following Coccinelle script:
// Use DEVICE() macros to access DeviceState.qdev
@use_device_macro_to_access_qdev@
expression obj;
identifier dev;
@@
-&obj->dev.qdev
+DEVICE(obj)
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Message-Id: <20190528164020.32250-10-philmd@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
'MSIX_CAP_LENGTH' is defined in two .c file. Move it
to hw/pci/msix.h file to reduce duplicated code.
CC: qemu-trivial@nongnu.org
Signed-off-by: Li Qiang <liq3ea@163.com>
Message-Id: <20190521151543.92274-5-liq3ea@163.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
The QOMConventions recommends we should use TYPE_FOO
for a TypeInfo's name. Though "vfio-pci-nohotplug" is not
used in other parts, for consistency we should make this change.
CC: qemu-trivial@nongnu.org
Signed-off-by: Li Qiang <liq3ea@163.com>
Message-Id: <20190521151543.92274-2-liq3ea@163.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
NVIDIA V100 GPUs have on-board RAM which is mapped into the host memory
space and accessible as normal RAM via an NVLink bus. The VFIO-PCI driver
implements special regions for such GPUs and emulates an NVLink bridge.
NVLink2-enabled POWER9 CPUs also provide address translation services
which includes an ATS shootdown (ATSD) register exported via the NVLink
bridge device.
This adds a quirk to VFIO to map the GPU memory and create an MR;
the new MR is stored in a PCI device as a QOM link. The sPAPR PCI uses
this to get the MR and map it to the system address space.
Another quirk does the same for ATSD.
This adds additional steps to sPAPR PHB setup:
1. Search for specific GPUs and NPUs, collect findings in
sPAPRPHBState::nvgpus, manage system address space mappings;
2. Add device-specific properties such as "ibm,npu", "ibm,gpu",
"memory-block", "link-speed" to advertise the NVLink2 function to
the guest;
3. Add "mmio-atsd" to vPHB to advertise the ATSD capability;
4. Add new memory blocks (with extra "linux,memory-usable" to prevent
the guest OS from accessing the new memory until it is onlined) and
npuphb# nodes representing an NPU unit for every vPHB as the GPU driver
uses it for link discovery.
This allocates space for GPU RAM and ATSD like we do for MMIOs by
adding 2 new parameters to the phb_placement() hook. Older machine types
set these to zero.
This puts new memory nodes in a separate NUMA node to as the GPU RAM
needs to be configured equally distant from any other node in the system.
Unlike the host setup which assigns numa ids from 255 downwards, this
adds new NUMA nodes after the user configures nodes or from 1 if none
were configured.
This adds requirement similar to EEH - one IOMMU group per vPHB.
The reason for this is that ATSD registers belong to a physical NPU
so they cannot invalidate translations on GPUs attached to another NPU.
It is guaranteed by the host platform as it does not mix NVLink bridges
or GPUs from different NPU in the same IOMMU group. If more than one
IOMMU group is detected on a vPHB, this disables ATSD support for that
vPHB and prints a warning.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
[aw: for vfio portions]
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Message-Id: <20190312082103.130561-1-aik@ozlabs.ru>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20190417190641.26814-8-armbru@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
This allows configure the display resolution which the vgpu should use.
The information will be passed to the guest using EDID, so the mdev
driver must support the vfio edid region for this to work.
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
The '%m' format instructs glibc's printf()/syslog() implementation to
insert the contents of strerror(errno). Since this is a glibc extension
it should generally be avoided in QEMU due to need for portability to a
variety of platforms.
Even though vfio is Linux-only code that could otherwise use "%m", it
must still be avoided in trace-events files because several of the
backends do not use the format string and so this error information is
invisible to them.
The errno string value should be given as an explicit trace argument
instead, making it accessible to all backends. This also allows it to
work correctly with future patches that use the format string with
systemtap's simple printf code.
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 20190123120016.4538-4-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Now that the downstream port will virtually negotiate itself to the
link status of the downstream device, we can remove this emulation.
It's not clear that it was every terribly useful anyway.
Tested-by: Geoffrey McRae <geoff@hostfission.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In preparation for reporting higher virtual link speeds and widths,
create enums and macros to help us manage them.
Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Tested-by: Geoffrey McRae <geoff@hostfission.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The previous commit changed vfio's warning messages from
vfio warning: DEV-NAME: Could not frobnicate
to
warning: vfio DEV-NAME: Could not frobnicate
To match this change, change error messages from
vfio error: DEV-NAME: On fire
to
vfio DEV-NAME: On fire
Note the loss of "error". If we think marking error messages that way
is a good idea, we should mark *all* error messages, i.e. make
error_report() print it.
Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Message-Id: <20181017082702.5581-7-armbru@redhat.com>
The vfio code reports warnings like
error_report(WARN_PREFIX "Could not frobnicate", DEV-NAME);
where WARN_PREFIX is defined so the message comes out as
vfio warning: DEV-NAME: Could not frobnicate
This usage predates the introduction of warn_report() & friends in
commit 97f40301f1. It's time to convert to that interface. Since
these functions already prefix the message with "warning: ", replace
WARN_PREFIX by VFIO_MSG_PREFIX, so the messages come out like
warning: vfio DEV-NAME: Could not frobnicate
The next commit will replace ERR_PREFIX.
Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20181017082702.5581-6-armbru@redhat.com>
From include/qapi/error.h:
* Pass an existing error to the caller with the message modified:
* error_propagate(errp, err);
* error_prepend(errp, "Could not frobnicate '%s': ", name);
Fei Li pointed out that doing error_propagate() first doesn't work
well when @errp is &error_fatal or &error_abort: the error_prepend()
is never reached.
Since I doubt fixing the documentation will stop people from getting
it wrong, introduce error_propagate_prepend(), in the hope that it
lures people away from using its constituents in the wrong order.
Update the instructions in error.h accordingly.
Convert existing error_prepend() next to error_propagate to
error_propagate_prepend(). If any of these get reached with
&error_fatal or &error_abort, the error messages improve. I didn't
check whether that's the case anywhere.
Cc: Fei Li <fli@suse.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20181017082702.5581-2-armbru@redhat.com>
Define a TYPE_VFIO_PCI and drop DO_UPCAST.
Signed-off-by: Li Qiang <liq3ea@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
So we have a boot display when using a vgpu as primary display.
ramfb depends on a fw_cfg file. fw_cfg files can not be added and
removed at runtime, therefore a ramfb-enabled vfio device can't be
hotplugged.
Add a nohotplug variant of the vfio-pci device (as child class). Add
the ramfb property to the nohotplug variant only. So to enable the vgpu
display with boot support use this:
-device vfio-pci-nohotplug,display=on,ramfb=on,sysfsdev=...
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Fix error reported by Coverity where realpath can return NULL,
resulting in a segfault in strcmp(). This should never happen given
that we're working through regularly structured sysfs paths, but
trivial enough to easily avoid.
Fixes: 238e917285 ("vfio/ccw/pci: Allow devices to opt-in for ballooning")
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
If a vfio assigned device makes use of a physical IOMMU, then memory
ballooning is necessarily inhibited due to the page pinning, lack of
page level granularity at the IOMMU, and sufficient notifiers to both
remove the page on balloon inflation and add it back on deflation.
However, not all devices are backed by a physical IOMMU. In the case
of mediated devices, if a vendor driver is well synchronized with the
guest driver, such that only pages actively used by the guest driver
are pinned by the host mdev vendor driver, then there should be no
overlap between pages available for the balloon driver and pages
actively in use by the device. Under these conditions, ballooning
should be safe.
vfio-ccw devices are always mediated devices and always operate under
the constraints above. Therefore we can consider all vfio-ccw devices
as balloon compatible.
The situation is far from straightforward with vfio-pci. These
devices can be physical devices with physical IOMMU backing or
mediated devices where it is unknown whether a physical IOMMU is in
use or whether the vendor driver is well synchronized to the working
set of the guest driver. The safest approach is therefore to assume
all vfio-pci devices are incompatible with ballooning, but allow user
opt-in should they have further insight into mediated devices.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
PCI devices needing a ROM allocate an optional MemoryRegion with
pci_add_option_rom(). pci_del_option_rom() does the cleanup when the
device is destroyed. The only action taken by this routine is to call
vmstate_unregister_ram() which clears the id string of the optional
ROM RAMBlock and now, also flags the RAMBlock as non-migratable. This
was recently added by commit b895de5027 ("migration: discard
non-migratable RAMBlocks"), .
VFIO devices do their own loading of the PCI option ROM in
vfio_pci_size_rom(). The memory region is switched to an I/O region
and the PCI attribute 'has_rom' is set but the RAMBlock of the ROM
region is not allocated. When the associated PCI device is deleted,
pci_del_option_rom() calls vmstate_unregister_ram() which tries to
flag a NULL RAMBlock, leading to a SEGV.
It seems that 'has_rom' was set to have memory_region_destroy()
called, but since commit 469b046ead ("memory: remove
memory_region_destroy") this is not necessary anymore as the
MemoryRegion is freed automagically.
Remove the PCIDevice 'has_rom' attribute setting in vfio.
Fixes: b895de5027 ("migration: discard non-migratable RAMBlocks")
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
It eases code review, unit is explicit.
Patch generated using:
$ git grep -E '(1024|2048|4096|8192|(<<|>>).?(10|20|30))' hw/ include/hw/
and modified manually.
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20180625124238.25339-38-f4bug@amsat.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Commit a9994687cb ("vfio/display: core & wireup") added display
support to vfio-pci with the default being "auto", which breaks
existing VMs when the vGPU requires GL support but had no previous
requirement for a GL compatible configuration. "Off" is the safer
default as we impose no new requirements to VM configurations.
Fixes: a9994687cb ("vfio/display: core & wireup")
Cc: qemu-stable@nongnu.org
Cc: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
With vfio ioeventfd support, we can program vfio-pci to perform a
specified BAR write when an eventfd is triggered. This allows the
KVM ioeventfd to be wired directly to vfio-pci, entirely avoiding
userspace handling for these events. On the same micro-benchmark
where the ioeventfd got us to almost 90% of performance versus
disabling the GeForce quirks, this gets us to within 95%.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
The NVIDIA BAR0 quirks virtualize the PCI config space mirrors found
in device MMIO space. Normally PCI config space is considered a slow
path and further optimization is unnecessary, however NVIDIA uses a
register here to enable the MSI interrupt to re-trigger. Exiting to
QEMU for this MSI-ACK handling can therefore rate limit our interrupt
handling. Fortunately the MSI-ACK write is easily detected since the
quirk MemoryRegion otherwise has very few accesses, so simply looking
for consecutive writes with the same data is sufficient, in this case
10 consecutive writes with the same data and size is arbitrarily
chosen. We configure the KVM ioeventfd with data match, so there's
no risk of triggering for the wrong data or size, but we do risk that
pathological driver behavior might consume all of QEMU's file
descriptors, so we cap ourselves to 10 ioeventfds for this purpose.
In support of the above, generic ioeventfd infrastructure is added
for vfio quirks. This automatically initializes an ioeventfd list
per quirk, disables and frees ioeventfds on exit, and allows
ioeventfds marked as dynamic to be dropped on device reset. The
rationale for this latter feature is that useful ioeventfds may
depend on specific driver behavior and since we necessarily place a
cap on our use of ioeventfds, a machine reset is a reasonable point
at which to assume a new driver and re-profile.
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
