Some old Linux kernels (upstream before v4.0), or any released RHEL
kernels has problem in sending APIC EOI when IR is enabled. Meanwhile,
many of them only support explicit EOI for IOAPIC, which is only
introduced in IOAPIC version 0x20. This patch provide a way to boost
QEMU IOAPIC to version 0x20, in order for QEMU to correctly receive EOI
messages.
Without boosting IOAPIC version to 0x20, kernels before commit d32932d
("x86/irq: Convert IOAPIC to use hierarchical irqdomain interfaces")
will have trouble enabling both IR and level-triggered interrupt devices
(like e1000).
To upgrade IOAPIC to version 0x20, we need to specify:
-global ioapic.version=0x20
To be compatible with old systems, 0x11 will still be the default IOAPIC
version. Here 0x11 and 0x20 are the only versions to be supported.
One thing to mention: this patch only applies to emulated IOAPIC. It
does not affect kernel IOAPIC behavior.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1470059959-372-1-git-send-email-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
For level triggered interrupts, we will get Remote IRR bit cleared after
guest kernel finished processing specific request. Before that, we
should ignore the same interrupt from triggering again.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1469974685-4144-1-git-send-email-peterx@redhat.com>
[Push new "if" up so that it covers KVM split irqchip as well. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reported from Alexey Kardashevskiy:
3f1fea0fb5 "kvm-irqchip: do explicit commit when update irq" produces
a crash on pseries guest running with VFIO on POWER8 machine as it does
not support KVM_CAP_IRQCHIP (KVM_CAP_IRQ_XICS is there instead). At the
result, KVMState::irq_routes is NULL when VFIO calls
kvm_irqchip_commit_routes.
This makes the routing update conditional.
Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
When user specify "intremap=on" with "-M kernel-irqchip=on", throw error
and then quit.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
These will help us monitoring irqchip route activities more easily.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In the past, we are doing gsi route commit for each irqchip route
update. This is not efficient if we are updating lots of routes in the
same time. This patch removes the committing phase in
kvm_irqchip_update_msi_route(). Instead, we do explicit commit after all
routes updated.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
One more IEC notifier is added to let msi routes know about the IEC
changes. When interrupt invalidation happens, all registered msi routes
will be updated for all PCI devices.
Since both vfio and vhost are possible gsi route consumers, this patch
will go one step further to keep them safe in split irqchip mode and
when irqfd is enabled.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
[move trace-events lines into target-i386/trace-events]
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Adding two hooks to be notified when adding/removing msi routes. There
are two kinds of MSI routes:
- in kvm_irqchip_add_irq_route(): before assigning IRQFD. Used by
vhost, vfio, etc.
- in kvm_irqchip_send_msi(): when sending direct MSI message, if
direct MSI not allowed, we will first create one MSI route entry
in the kernel, then trigger it.
This patch only hooks the first one (irqfd case). We do not need to
take care for the 2nd one, since it's only used by QEMU userspace
(kvm-apic) and the messages will always do in-time translation when
triggered. While we need to note them down for the 1st one, so that we
can notify the kernel when cache invalidation happens.
Also, we do not hook IOAPIC msi routes (we have explicit notifier for
IOAPIC to keep its cache updated). We only need to care about irqfd
users.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Changing the original MSIMessage parameter in kvm_irqchip_add_msi_route
into the vector number. Vector index provides more information than the
MSIMessage, we can retrieve the MSIMessage using the vector easily. This
will avoid fetching MSIMessage every time before adding MSI routes.
Meanwhile, the vector info will be used in the coming patches to further
enable gsi route update notifications.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This patch enables SID validation. Invalid interrupts will be dropped.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Let IOAPIC the first consumer of x86 IOMMU IEC invalidation
notifiers. This is only used for split irqchip case, when vIOMMU
receives IR invalidation requests, IOAPIC will be notified to update
kernel irq routes. For simplicity, we just update all IOAPIC routes,
even if the invalidated entries are not IOAPIC ones.
Since now we are creating IOMMUs using "-device" parameter, IOMMU
device will be created after IOAPIC. We need to do the registration
after machine done by leveraging machine_done notifier.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This patch introduces x86 IOMMU IEC (Interrupt Entry Cache)
invalidation notifier list. When vIOMMU receives IEC invalidate
request, all the registered units will be notified with specific
invalidation requests.
Intel IOMMU is the first provider that generates such a event.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In split irqchip mode, IOAPIC is working in user space, only update
kernel irq routes when entry changed. When IR is enabled, we directly
update the kernel with translated messages. It works just like a kernel
cache for the remapping entries.
Since KVM irqfd is using kernel gsi routes to deliver interrupts, as
long as we can support split irqchip, we will support irqfd as
well. Also, since kernel gsi routes will cache translated interrupts,
irqfd delivery will not suffer from any performance impact due to IR.
And, since we supported irqfd, vhost devices will be able to work
seamlessly with IR now. Logically this should contain both vhost-net and
vhost-user case.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
[move trace-events lines into target-i386/trace-events]
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Abstract IOAPIC entry parsing logic into a helper function.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This patch translates all IOAPIC interrupts into MSI ones. One pseudo
ioapic address space is added to transfer the MSI message. By default,
it will be system memory address space. When IR is enabled, it will be
IOMMU address space.
Currently, only emulated IOAPIC is supported.
Idea suggested by Jan Kiszka and Rita Sinha in the following patch:
https://lists.gnu.org/archive/html/qemu-devel/2016-03/msg01933.html
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This patch enables interrupt remapping for PCI devices.
To play the trick, one memory region "iommu_ir" is added as child region
of the original iommu memory region, covering range 0xfeeXXXXX (which is
the address range for APIC). All the writes to this range will be taken
as MSI, and translation is carried out only when IR is enabled.
Idea suggested by Paolo Bonzini.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Adding translation fault definitions for interrupt remapping. Please
refer to VT-d spec section 7.1.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Several data structs are defined to better support the rest of the
patches: IRTE to parse remapping table entries, and IOAPIC/MSI related
structure bits to parse interrupt entries to be filled in by guest
kernel.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Handle writting to IRE bit in global command register.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Defined Interrupt Remap Table Address register to store IR table
pointer. Also, do proper handling on global command register writes to
store table pointer and its size.
One more debug flag "DEBUG_IR" is added for interrupt remapping.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
To enable interrupt remapping for intel IOMMU device, each IOAPIC device
in the system reported via ACPI MADT must be explicitly enumerated under
one specific remapping hardware unit. This patch adds the root-complex
IOAPIC into the default DMAR device.
Please refer to VT-d spec 8.3.1.1 for more information.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Enable IR in IOMMU Extended Capability register.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Queued invalidation is required for IR. This patch add basic support for
interrupt cache invalidate requests. Since we currently have no IR cache
implemented yet, we can just skip all interrupt cache invalidation
requests for now.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In ACPI DMA remapping report structure, enable INTR flag when specified.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Adding one property for intel-iommu devices to specify whether we should
support interrupt remapping. By default, IR is disabled. To enable it,
we should use (take Intel IOMMU as example):
-device intel_iommu,intremap=on
This property can be shared by Intel and future AMD IOMMUs.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Instead of searching the device tree every time, one static variable is
declared for the default system x86 IOMMU device.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Introducing parent class for intel-iommu devices named "x86-iommu". This
is preparation work to abstract shared functionalities out from Intel
and AMD IOMMUs. Currently, only the parent class is introduced. It does
nothing yet.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This fix SID verification failure when IOMMU IR is enabled with PCI
bridges. Existing pci_requester_id() is more like getting BDF info
only. Renaming it to pci_get_bdf(). Meanwhile, we provide the correct
implementation to get requester ID. VT-d spec 5.1.1 is a good reference
to go, though it talks only about interrupt delivery, the rule works
exactly the same for non-interrupt cases.
Currently, there are three use cases for pci_requester_id():
- PCIX status bits: here we need BDF only, not requester ID. Replacing
with pci_get_bdf().
- PCIe Error injection and MSI delivery: for both these cases, we are
looking for requester IDs. Here we should use the new impl.
To avoid a PCI walk every time we send MSI message, one requester_id
cache field is added to PCIDevice to cache the result when initialize
PCI device.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This is to better emulate IOAPIC version 0x1X hardware. Linux kernel
leveraged this "feature" to do explicit EOI since EOI register is still
not introduced at that time. This will also fix the issue that level
triggered interrupts failed to work when IR enabled (tested with Linux
kernel version 4.5).
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1462875682-1349-3-git-send-email-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Here we use one g_strdup_printf() to replace the two stack allocated
array, considering it's more convenient, safe, and as long as it's
called rarely only when quorum device opens. This will remove the
unbound stack warning when compiling with "-Wstack-usage=1000000".
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
This patch add "query-gic-capabilities" but does not implement it. The
command is ARM-only. The command will return a list of GICCapability
structs that describes all GIC versions that current QEMU and system
support.
Libvirt is possibly the first consumer of this new command.
Before this patch, a libvirt user can successfully configure all kinds
of GIC devices for ARM guests, no matter whether current QEMU/kernel
supports them. If the specified GIC version/type is not supported, the
user will get an ambiguous "QEMU boot failure" error when trying to start
the VM. This is not user-friendly.
With this patch, libvirt should be able to query which type (and which
version) of GIC device is supported. Using this information, libvirt
can warn the user during configuration of guests when specified GIC
device type is not supported. Or better, we can just list those versions
that we support, and filter out the unsupported ones.
For example, if we got the query result:
{"return": [{"emulated": false, "version": 3, "kernel": true},
{"emulated": true, "version": 2, "kernel": false}]}
then it means that we support emulated GIC version 2 using:
qemu-system-aarch64 -M virt,accel=tcg,gic-version=2 ...
or KVM-accelerated GIC version 3 using:
qemu-system-aarch64 -M virt,accel=kvm,gic-version=3 ...
If we specify other explicit GIC versions rather than the above, QEMU
will not be able to boot.
The community is working on a more generic way to query these kinds of
information about valid values of machine properties. However, due to
the importance of supporting this specific use case, weecided to first
implement this ad-hoc one; then when the generic method is ready, we
can move on to that one smoothly.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 1458788142-17509-2-git-send-email-peterx@redhat.com
[PMM: tweaked commit message a bit; monitor.o is CONFIG_SOFTMMU only]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
All the callers for xhci_dma_write_u32s() are using mostly 5 * uint32_t
in len. To avoid unbound stack warning for the function, make it
statically allocated, and assert when it's not big enough in the
future.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-id: 1457661106-9569-1-git-send-email-peterx@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
When dump-guest-memory is requested with detach flag, after its
return, user could query its status using "query-dump" command (with
no argument). The result contains:
- status: current dump status
- completed: bytes written in the latest dump
- total: bytes to write in the latest dump
From completed and total, we could know how much work
finished by calculating:
100.0 * completed / total (%)
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1455772616-8668-10-git-send-email-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If "detach" is provided, one thread is created to do the dump work,
while main thread will return immediately. For each GuestPhysBlock,
adding one more field "mr" to points to MemoryRegion that it
belongs, also ref the mr before use.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Message-Id: <1455772616-8668-8-git-send-email-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Peter Xu