When a guest has a PCI pass-through device with an interrupt, it
will direct the interrupt to a particular guest VCPU. In fact the
physical interrupt might arrive on any CPU, and then get
delivered to the target VCPU in the emulated XICS (guest interrupt
controller), and eventually delivered to the target VCPU.
Now that we have code to handle device interrupts in real mode
without exiting to the host kernel, there is an advantage to having
the device interrupt arrive on the same sub(core) as the target
VCPU is running on. In this situation, the interrupt can be
delivered to the target VCPU without any exit to the host kernel
(using a hypervisor doorbell interrupt between threads if
necessary).
This patch aims to get passed-through device interrupts arriving
on the correct core by setting the interrupt server in the real
hardware XICS for the interrupt to the first thread in the (sub)core
where its target VCPU is running. We do this in the real-mode H_EOI
code because the H_EOI handler already needs to look at the
emulated ICS state for the interrupt (whereas the H_XIRR handler
doesn't), and we know we are running in the target VCPU context
at that point.
We set the server CPU in hardware using an OPAL call, regardless of
what the IRQ affinity mask for the interrupt says, and without
updating the affinity mask. This amounts to saying that when an
interrupt is passed through to a guest, as a matter of policy we
allow the guest's affinity for the interrupt to override the host's.
This is inspired by an earlier patch from Suresh Warrier, although
none of this code came from that earlier patch.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Dump the passthrough irqmap structure associated with a
guest as part of /sys/kernel/debug/powerpc/kvm-xics-*.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
In existing real mode ICP code, when updating the virtual ICP
state, if there is a required action that cannot be completely
handled in real mode, as for instance, a VCPU needs to be woken
up, flags are set in the ICP to indicate the required action.
This is checked when returning from hypercalls to decide whether
the call needs switch back to the host where the action can be
performed in virtual mode. Note that if h_ipi_redirect is enabled,
real mode code will first try to message a free host CPU to
complete this job instead of returning the host to do it ourselves.
Currently, the real mode PCI passthrough interrupt handling code
checks if any of these flags are set and simply returns to the host.
This is not good enough as the trap value (0x500) is treated as an
external interrupt by the host code. It is only when the trap value
is a hypercall that the host code searches for and acts on unfinished
work by calling kvmppc_xics_rm_complete.
This patch introduces a special trap BOOK3S_INTERRUPT_HV_RM_HARD
which is returned by KVM if there is unfinished business to be
completed in host virtual mode after handling a PCI passthrough
interrupt. The host checks for this special interrupt condition
and calls into the kvmppc_xics_rm_complete, which is made an
exported function for this reason.
[paulus@ozlabs.org - moved logic to set r12 to BOOK3S_INTERRUPT_HV_RM_HARD
in book3s_hv_rmhandlers.S into the end of kvmppc_check_wake_reason.]
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
It turns out that if userspace creates a pseries-type VM without
in-kernel XICS (interrupt controller) emulation, and then connects
an eventfd to the VM as an irqfd, and the eventfd gets signalled,
that the code will try to deliver an interrupt via the non-existent
XICS object and crash the host kernel with a NULL pointer dereference.
To fix this, we check for the presence of the XICS object before
trying to deliver the interrupt, and return with an error if not.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
KVM devices were manipulating list data structures without any form of
synchronization, and some implementations of the create operations also
suffered from a lack of synchronization.
Now when we've split the xics create operation into create and init, we
can hold the kvm->lock mutex while calling the create operation and when
manipulating the devices list.
The error path in the generic code gets slightly ugly because we have to
take the mutex again and delete the device from the list, but holding
the mutex during anon_inode_getfd or releasing/locking the mutex in the
common non-error path seemed wrong.
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
As we are about to hold the kvm->lock during the create operation on KVM
devices, we should move the call to xics_debugfs_init into its own
function, since holding a mutex over extended amounts of time might not
be a good idea.
Introduce an init operation on the kvm_device_ops struct which cannot
fail and call this, if configured, after the device has been created.
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Commit c9a5eccac1 ("kvm/eventfd: add arch-specific set_irq",
2015-10-16) added the possibility for architecture-specific code
to handle the generation of virtual interrupts in atomic context
where possible, without having to schedule a work function.
Since we can easily generate virtual interrupts on XICS without
having to do anything worse than take a spinlock, we define a
kvm_arch_set_irq_inatomic() for XICS. We also remove kvm_set_msi()
since it is not used any more.
The one slightly tricky thing is that with the new interface, we
don't get told whether the interrupt is an MSI (or other edge
sensitive interrupt) vs. level-sensitive. The difference as far
as interrupt generation is concerned is that for LSIs we have to
set the asserted flag so it will continue to fire until it is
explicitly cleared.
In fact the XICS code gets told which interrupts are LSIs by userspace
when it configures the interrupt via the KVM_DEV_XICS_GRP_SOURCES
attribute group on the XICS device. To store this information, we add
a new "lsi" field to struct ics_irq_state. With that we can also do a
better job of returning accurate values when reading the attribute
group.
Signed-off-by: Paul Mackerras <paulus@samba.org>
When XICS_DBG is enabled, gcc produces format errors. This fixes
formats to match passed values types.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Commit 34cb7954c0 "Convert ICS mutex lock to spin lock" added an
include of asm/spinlock.h, which does not work in the SMP=n case.
It should instead include linux/spinlock.h
Fixes: 34cb7954c0 ("KVM: PPC: Book3S HV: Convert ICS mutex lock to spin lock")
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add two counters to count how often we generate real-mode ICS resend
and reject events. The counters provide some performance statistics
that could be used in the future to consider if the real mode functions
need further optimizing. The counters are displayed as part of IPC and
ICP state provided by /sys/debug/kernel/powerpc/kvm* for each VM.
Also added two counters that count (approximately) how many times we
don't find an ICP or ICS we're looking for. These are not currently
exposed through sysfs, but can be useful when debugging crashes.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Replaces the ICS mutex lock with a spin lock since we will be porting
these routines to real mode. Note that we need to disable interrupts
before we take the lock in anticipation of the fact that on the guest
side, we are running in the context of a hard irq and interrupts are
disabled (EE bit off) when the lock is acquired. Again, because we
will be acquiring the lock in hypervisor real mode, we need to use
an arch_spinlock_t instead of a normal spinlock here as we want to
avoid running any lockdep code (which may not be safe to execute in
real mode).
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Add counters to track number of times we switch from guest real mode
to host virtual mode during an interrupt-related hyper call because the
hypercall requires actions that cannot be completed in real mode. This
will help when making optimizations that reduce guest-host transitions.
It is safe to use an ordinary increment rather than an atomic operation
because there is one ICP per virtual CPU and kvmppc_xics_rm_complete()
only works on the ICP for the current VCPU.
The counters are displayed as part of IPC and ICP state provided by
/sys/debug/kernel/powerpc/kvm* for each VM.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
ACCESS_ONCE does not work reliably on non-scalar types. For
example gcc 4.6 and 4.7 might remove the volatile tag for such
accesses during the SRA (scalar replacement of aggregates) step
(https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145)
Change the ppc/kvm code to replace ACCESS_ONCE with READ_ONCE.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Alexander Graf <agraf@suse.de>
This fixes some inaccuracies in the state machine for the virtualized
ICP when implementing the H_IPI hcall (Set_MFFR and related states):
1. The old code wipes out any pending interrupts when the new MFRR is
more favored than the CPPR but less favored than a pending
interrupt (by always modifying xisr and the pending_pri). This can
cause us to lose a pending external interrupt.
The correct code here is to only modify the pending_pri and xisr in
the ICP if the MFRR is equal to or more favored than the current
pending pri (since in this case, it is guaranteed that that there
cannot be a pending external interrupt). The code changes are
required in both kvmppc_rm_h_ipi and kvmppc_h_ipi.
2. Again, in both kvmppc_rm_h_ipi and kvmppc_h_ipi, there is a check
for whether MFRR is being made less favored AND further if new MFFR
is also less favored than the current CPPR, we check for any
resends pending in the ICP. These checks look like they are
designed to cover the case where if the MFRR is being made less
favored, we opportunistically trigger a resend of any interrupts
that had been previously rejected. Although, this is not a state
described by PAPR, this is an action we actually need to do
especially if the CPPR is already at 0xFF. Because in this case,
the resend bit will stay on until another ICP state change which
may be a long time coming and the interrupt stays pending until
then. The current code which checks for MFRR < CPPR is broken when
CPPR is 0xFF since it will not get triggered in that case.
Ideally, we would want to do a resend only if
prio(pending_interrupt) < mfrr && prio(pending_interrupt) < cppr
where pending interrupt is the one that was rejected. But we don't
have the priority of the pending interrupt state saved, so we
simply trigger a resend whenever the MFRR is made less favored.
3. In kvmppc_rm_h_ipi, where we save state to pass resends to the
virtual mode, we also need to save the ICP whose need_resend we
reset since this does not need to be my ICP (vcpu->arch.icp) as is
incorrectly assumed by the current code. A new field rm_resend_icp
is added to the kvmppc_icp structure for this purpose.
Signed-off-by: Suresh Warrier <warrier@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This makes it possible to use IRQFDs on platforms that use the XICS
interrupt controller. To do this we implement kvm_irq_map_gsi() and
kvm_irq_map_chip_pin() in book3s_xics.c, so as to provide a 1-1 mapping
between global interrupt numbers and XICS interrupt source numbers.
For now, all interrupts are mapped as "IRQCHIP" interrupts, and no
MSI support is provided.
This means that kvm_set_irq can now get called with level == 0 or 1
as well as the powerpc-specific values KVM_INTERRUPT_SET,
KVM_INTERRUPT_UNSET and KVM_INTERRUPT_SET_LEVEL. We change
ics_deliver_irq() to accept all those values, and remove its
report_status argument, as it is always false, given that we don't
support KVM_IRQ_LINE_STATUS.
This also adds support for interrupt ack notifiers to the XICS code
so that the IRQFD resampler functionality can be supported.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Tested-by: Eric Auger <eric.auger@linaro.org>
Tested-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
drop is_hv_enabled, because that should not be a callback property
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
This moves the kvmppc_ops callbacks to be a per VM entity. This
enables us to select HV and PR mode when creating a VM. We also
allow both kvm-hv and kvm-pr kernel module to be loaded. To
achieve this we move /dev/kvm ownership to kvm.ko module. Depending on
which KVM mode we select during VM creation we take a reference
count on respective module
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[agraf: fix coding style]
Signed-off-by: Alexander Graf <agraf@suse.de>
This help us to identify whether we are running with hypervisor mode KVM
enabled. The change is needed so that we can have both HV and PR kvm
enabled in the same kernel.
If both HV and PR KVM are included, interrupts come in to the HV version
of the kvmppc_interrupt code, which then jumps to the PR handler,
renamed to kvmppc_interrupt_pr, if the guest is a PR guest.
Allowing both PR and HV in the same kernel required some changes to
kvm_dev_ioctl_check_extension(), since the values returned now can't
be selected with #ifdefs as much as previously. We look at is_hv_enabled
to return the right value when checking for capabilities.For capabilities that
are only provided by HV KVM, we return the HV value only if
is_hv_enabled is true. For capabilities provided by PR KVM but not HV,
we return the PR value only if is_hv_enabled is false.
NOTE: in later patch we replace is_hv_enabled with a static inline
function comparing kvm_ppc_ops
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
This patch add a new callback kvmppc_ops. This will help us in enabling
both HV and PR KVM together in the same kernel. The actual change to
enable them together is done in the later patch in the series.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[agraf: squash in booke changes]
Signed-off-by: Alexander Graf <agraf@suse.de>
Commit 8e44ddc3f3 ("powerpc/kvm/book3s: Add support for H_IPOLL and
H_XIRR_X in XICS emulation") added a call to get_tb() but didn't
include the header that defines it, and on some configs this means
book3s_xics.c fails to compile:
arch/powerpc/kvm/book3s_xics.c: In function ‘kvmppc_xics_hcall’:
arch/powerpc/kvm/book3s_xics.c:812:3: error: implicit declaration of function ‘get_tb’ [-Werror=implicit-function-declaration]
Cc: stable@vger.kernel.org [v3.10, v3.11]
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds the remaining two hypercalls defined by PAPR for manipulating
the XICS interrupt controller, H_IPOLL and H_XIRR_X. H_IPOLL returns
information about the priority and pending interrupts for a virtual
cpu, without changing any state. H_XIRR_X is like H_XIRR in that it
reads and acknowledges the highest-priority pending interrupt, but it
also returns the timestamp (timebase register value) from when the
interrupt was first received by the hypervisor. Currently we just
return the current time, since we don't do any software queueing of
virtual interrupts inside the XICS emulation code.
These hcalls are not currently used by Linux guests, but may be in
future.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This adds the API for userspace to instantiate an XICS device in a VM
and connect VCPUs to it. The API consists of a new device type for
the KVM_CREATE_DEVICE ioctl, a new capability KVM_CAP_IRQ_XICS, which
functions similarly to KVM_CAP_IRQ_MPIC, and the KVM_IRQ_LINE ioctl,
which is used to assert and deassert interrupt inputs of the XICS.
The XICS device has one attribute group, KVM_DEV_XICS_GRP_SOURCES.
Each attribute within this group corresponds to the state of one
interrupt source. The attribute number is the same as the interrupt
source number.
This does not support irq routing or irqfd yet.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds the ability for userspace to save and restore the state
of the XICS interrupt presentation controllers (ICPs) via the
KVM_GET/SET_ONE_REG interface. Since there is one ICP per vcpu, we
simply define a new 64-bit register in the ONE_REG space for the ICP
state. The state includes the CPU priority setting, the pending IPI
priority, and the priority and source number of any pending external
interrupt.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds support for the ibm,int-on and ibm,int-off RTAS calls to the
in-kernel XICS emulation and corrects the handling of the saved
priority by the ibm,set-xive RTAS call. With this, ibm,int-off sets
the specified interrupt's priority in its saved_priority field and
sets the priority to 0xff (the least favoured value). ibm,int-on
restores the saved_priority to the priority field, and ibm,set-xive
sets both the priority and the saved_priority to the specified
priority value.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds an implementation of the XICS hypercalls in real mode for HV
KVM, which allows us to avoid exiting the guest MMU context on all
threads for a variety of operations such as fetching a pending
interrupt, EOI of messages, IPIs, etc.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Currently, we wake up a CPU by sending a host IPI with
smp_send_reschedule() to thread 0 of that core, which will take all
threads out of the guest, and cause them to re-evaluate their
interrupt status on the way back in.
This adds a mechanism to differentiate real host IPIs from IPIs sent
by KVM for guest threads to poke each other, in order to target the
guest threads precisely when possible and avoid that global switch of
the core to host state.
We then use this new facility in the in-kernel XICS code.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
This adds in-kernel emulation of the XICS (eXternal Interrupt
Controller Specification) interrupt controller specified by PAPR, for
both HV and PR KVM guests.
The XICS emulation supports up to 1048560 interrupt sources.
Interrupt source numbers below 16 are reserved; 0 is used to mean no
interrupt and 2 is used for IPIs. Internally these are represented in
blocks of 1024, called ICS (interrupt controller source) entities, but
that is not visible to userspace.
Each vcpu gets one ICP (interrupt controller presentation) entity,
used to store the per-vcpu state such as vcpu priority, pending
interrupt state, IPI request, etc.
This does not include any API or any way to connect vcpus to their
ICP state; that will be added in later patches.
This is based on an initial implementation by Michael Ellerman
<michael@ellerman.id.au> reworked by Benjamin Herrenschmidt and
Paul Mackerras.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix typo, add dependency on !KVM_MPIC]
Signed-off-by: Alexander Graf <agraf@suse.de>
