The problem:
On -RT, an emulated LAPIC timer instances has the following path:
1) hard interrupt
2) ksoftirqd is scheduled
3) ksoftirqd wakes up vcpu thread
4) vcpu thread is scheduled
This extra context switch introduces unnecessary latency in the
LAPIC path for a KVM guest.
The solution:
Allow waking up vcpu thread from hardirq context,
thus avoiding the need for ksoftirqd to be scheduled.
Normal waitqueues make use of spinlocks, which on -RT
are sleepable locks. Therefore, waking up a waitqueue
waiter involves locking a sleeping lock, which
is not allowed from hard interrupt context.
cyclictest command line:
This patch reduces the average latency in my tests from 14us to 11us.
Cc: stable-rt@vger.kernel.org
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
This patch enables transactional execution for KVM guests
on s390 systems zec12 or later.
We rework the allocation of the page containing the sie_block
to also back the Interception Transaction Diagnostic Block.
If available the TE facilities will be enabled.
Setting bit 73 and 50 in vfacilities bitmask reveals the HW
facilities Transactional Memory and Constraint Transactional
Memory respectively to the KVM guest.
Furthermore, the patch restores the Program-Interruption TDB
from the Interception TDB in case a program interception has
occurred and the ITDB has a valid format.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Now when the main kvm code relying on these defines has been moved to
the x86 specific part of the world, we can get rid of these.
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
The need for SIE_INTERCEPT_RERUNVCPU has been removed long ago already,
with the following commit:
f7850c9288
[S390] remove kvm mmu reload on s390
Since the remainders are dead code, they are now removed by this patch.
Signed-off-by: Thomas Huth <thuth@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Current common code uses PAGE_OFFSET to indicate a bad host virtual address.
As this check won't work on architectures that don't map kernel and user memory
into the same address space (e.g. s390), such architectures can now provide
their own KVM_HVA_ERR_BAD defines.
Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Renamed the PGM_PRIVILEGED_OPERATION define to PGM_PRIVILEGED_OP since this
define was way longer than the other PGM_* defines and caused the code often
to exceed the 80 columns limit when not split to multiple lines.
Signed-off-by: Thomas Huth <thuth@linux.vnet.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch is based on an original patch of David Hildenbrand.
The perf core implementation calls architecture specific code in order
to ask for specific information for a particular sample:
perf_instruction_pointer()
When perf core code asks for the instruction pointer, architecture
specific code must detect if a KVM guest was running when the sample
was taken. A sample can be associated with a KVM guest when the PSW
supervisor state bit is set and the PSW instruction pointer part
contains the address of 'sie_exit'.
A KVM guest's instruction pointer information is then retrieved via
gpsw entry pointed to by the sie control-block.
perf_misc_flags()
perf code code calls this function in order to associate the kernel
vs. user state infomation with a particular sample. Architecture
specific code must also first detectif a KVM guest was running
at the time the sample was taken.
Signed-off-by: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Lets use the common waitqueue for kvm cpus on s390. By itself it is
just a cleanup, but it should also improve the accuracy of diag 0x44
which is implemented via kvm_vcpu_on_spin. kvm_vcpu_on_spin has
an explicit check for waiting on the waitqueue to optimize the
yielding.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch enables kvm to give large pages to the guest. The heavy
lifting is done by the hardware, the host only has to take care
of the PFMF instruction, which is also part of EDAT-1.
We also support the non-quiescing key setting facility if the host
supports it, to behave similar to the interpretation of sske.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Lets provide functions to prevent KVM from reentering SIE and
to kick cpus out of SIE. We cannot use the common kvm_vcpu_kick code,
since we need to kick out guests in places that hold architecture
specific locks (e.g. pgste lock) which might be necessary on the
other cpus - so no waiting possible.
So lets provide a bit in a private field of the sie control block
that acts as a gate keeper, after we claimed we are in SIE.
Please note that we do not reuse prog0c, since we want to access
that bit without atomic ops.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Lets track in a private bit if the sie control block is active.
We want to track this as closely as possible, so we also have to
instrument the interrupt and program check handler. Lets use the
existing HANDLE_SIE_INTERCEPT macro.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Add a new capability, KVM_CAP_S390_CSS_SUPPORT, which will pass
intercepts for channel I/O instructions to userspace. Only I/O
instructions interacting with I/O interrupts need to be handled
in-kernel:
- TEST PENDING INTERRUPTION (tpi) dequeues and stores pending
interrupts entirely in-kernel.
- TEST SUBCHANNEL (tsch) dequeues pending interrupts in-kernel
and exits via KVM_EXIT_S390_TSCH to userspace for subchannel-
related processing.
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Add support for injecting machine checks (only repressible
conditions for now).
This is a bit more involved than I/O interrupts, for these reasons:
- Machine checks come in both floating and cpu varieties.
- We don't have a bit for machine checks enabling, but have to use
a roundabout approach with trapping PSW changing instructions and
watching for opened machine checks.
Reviewed-by: Alexander Graf <agraf@suse.de>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Add support for handling I/O interrupts (standard, subchannel-related
ones and rudimentary adapter interrupts).
The subchannel-identifying parameters are encoded into the interrupt
type.
I/O interrupts are floating, so they can't be injected on a specific
vcpu.
Reviewed-by: Alexander Graf <agraf@suse.de>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Seems like everyone copied x86 and defined 4 private memory slots
that never actually get used. Even x86 only uses 3 of the 4. These
aren't exposed so there's no need to add padding.
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
It's easy to confuse KVM_MEMORY_SLOTS and KVM_MEM_SLOTS_NUM. One is
the user accessible slots and the other is user + private. Make this
more obvious.
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Remove the file name from the comment at top of many files. In most
cases the file name was wrong anyway, so it's rather pointless.
Also unify the IBM copyright statement. We did have a lot of sightly
different statements and wanted to change them one after another
whenever a file gets touched. However that never happened. Instead
people start to take the old/"wrong" statements to use as a template
for new files.
So unify all of them in one go.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
This patch implements the directed yield hypercall found on other
System z hypervisors. It delegates execution time to the virtual cpu
specified in the instruction's parameter.
Useful to avoid long spinlock waits in the guest.
Christian Borntraeger: moved common code in virt/kvm/
Signed-off-by: Konstantin Weitz <WEITZKON@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Some members of kvm_memory_slot are not used by every architecture.
This patch is the first step to make this difference clear by
introducing kvm_memory_slot::arch; lpage_info is moved into it.
Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch adds the access registers to the kvm_run structure.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch adds the general purpose registers to the kvm_run structure.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch fixes definition of the idle_mask and the local_int array
in kvm_s390_float_interrupt. Previous definition had 64 cpus max
hardcoded instead of using KVM_MAX_VCPUS.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
SIGP sense running may cause an intercept on higher level
virtualization, so handle it by checking the CPUSTAT_RUNNING flag.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
CPUSTAT_RUNNING was implemented signifying that a vcpu is not stopped.
This is not, however, what the architecture says: RUNNING should be
set when the host is acting on the behalf of the guest operating
system.
CPUSTAT_RUNNING has been changed to be set in kvm_arch_vcpu_load()
and to be unset in kvm_arch_vcpu_put().
For signifying stopped state of a vcpu, a host-controlled bit has
been used and is set/unset basically on the reverse as the old
CPUSTAT_RUNNING bit (including pushing it down into stop handling
proper in handle_stop()).
Cc: stable@kernel.org
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Linux on System z uses a ballooner based on diagnose 0x10. (aka as
collaborative memory management). This patch implements diagnose
0x10 on the guest address space.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Implement sigp external call, which might be required for guests that
issue an external call instead of an emergency signal for IPI.
This fixes an issue with "KVM: unknown SIGP: 0x02" when booting
such an SMP guest.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
SIGP emerg needs to pass the source vpu adress into __LC_CPU_ADDRESS of the
target guest.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch removes kvm-s390 internal assumption of a linear mapping
of guest address space to user space. Previously, guest memory was
translated to user addresses using a fixed offset (gmsor). The new
code uses gmap_fault to resolve guest addresses.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch switches kvm from using (Qemu's) user address space to
Martin's gmap address space. This way QEMU does not have to use a
linker script in order to fit large guests at low addresses in its
address space.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
When running a kvm guest we can get intercepts for tprot, if the host
page table is read-only or not populated. This patch implements the
most common case (linux memory detection).
This also allows host copy on write for guest memory on newer systems.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch converts unnecessary divide and modulo operations
in the KVM large page related code into logical operations.
This allows to convert gfn_t to u64 while not breaking 32
bit builds.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Newer (guest) kernels use sigp sense running in their spinlock
implementation to check if the other cpu is running before yielding
the processor. This revealed some wrong guest settings, causing
unnecessary exits for every sigp sense running.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
* 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (202 commits)
MAINTAINERS: update KVM entry
KVM: correct error-handling code
KVM: fix compile warnings on s390
KVM: VMX: Check cpl before emulating debug register access
KVM: fix misreporting of coalesced interrupts by kvm tracer
KVM: x86: drop duplicate kvm_flush_remote_tlb calls
KVM: VMX: call vmx_load_host_state() only if msr is cached
KVM: VMX: Conditionally reload debug register 6
KVM: Use thread debug register storage instead of kvm specific data
KVM guest: do not batch pte updates from interrupt context
KVM: Fix coalesced interrupt reporting in IOAPIC
KVM guest: fix bogus wallclock physical address calculation
KVM: VMX: Fix cr8 exiting control clobbering by EPT
KVM: Optimize kvm_mmu_unprotect_page_virt() for tdp
KVM: Document KVM_CAP_IRQCHIP
KVM: Protect update_cr8_intercept() when running without an apic
KVM: VMX: Fix EPT with WP bit change during paging
KVM: Use kvm_{read,write}_guest_virt() to read and write segment descriptors
KVM: x86 emulator: Add adc and sbb missing decoder flags
KVM: Add missing #include
...
Merge cpuid.h header file into cpu.h.
While at it convert from typedef to struct declaration and also
convert cio code to use proper lowcore structure instead of casts.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch relocates the variables kvm-s390 uses to track guest mem addr/size.
As discussed dropping the variables at struct kvm_arch level allows to use the
common vcpu->request based mechanism to reload guest memory if e.g. changes
via set_memory_region.
The kick mechanism introduced in this series is used to ensure running vcpus
leave guest state to catch the update.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
To ensure vcpu's come out of guest context in certain cases this patch adds a
s390 specific way to kick them out of guest context. Currently it kicks them
out to rerun the vcpu_run path in the s390 code, but the mechanism itself is
expandable and with a new flag we could also add e.g. kicks to userspace etc.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2.6.31-rc introduced an architecture level set checker based on facility
bits. e.g. if the kernel is compiled to run only on z9, several facility
bits are checked very early and the kernel refuses to boot if a z9 specific
facility is missing.
Until now kvm on s390 did not implement the store facility extended (STFLE)
instruction. A 2.6.31-rc kernel that was compiled for z9 or higher did not
boot in kvm. This patch implements stfle.
This patch should go in before 2.6.31.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch reworks the s390 clock comparator wakeup to hrtimer. The clock
comparator is a per-cpu value that is compared against the TOD clock. If
ckc <= TOD an external interrupt 1004 is triggered. Since the clock comparator
and the TOD clock have a much higher resolution than jiffies we should use
hrtimers to trigger the wakeup. This speeds up guest nanosleep for small
values.
Since hrtimers callbacks run in hard-irq context, I added a tasklet to do
the actual work with enabled interrupts.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Ehrhardt <ehrhardt@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Currently the storage of the machine flags is a globally exported unsigned
long long variable. By moving the storage location into the lowcore struct we
allow assembler code to check machine_flags directly even without needing a
register. Addtionally the lowcore and therefore the machine flags too will be
in cache most of the time.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Remove the remaining arch fragments of the old guest debug interface
that now break non-x86 builds.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Marcelo Tosatti
Michael Mueller
Christoffer Dall
Thomas Huth
Dominik Dingel
Heinz Graalfs
Christian Borntraeger
Cornelia Huck
Alex Williamson
Heiko Carstens
Konstantin Weitz
Takuya Yoshikawa
Carsten Otte
Linus Torvalds
Christian Ehrhardt
Joerg Roedel
Jan Kiszka
Martin Schwidefsky