We need to hide SMRAM from guests not running in SMM. Therefore,
all uses of kvm_read_guest* and kvm_write_guest* must be changed to
check whether the VCPU is in system management mode and use a
different set of memslots. Switch from kvm_* to the newly-introduced
kvm_vcpu_*, which call into kvm_arch_vcpu_memslots_id.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The big ugly one. This patch adds support for switching in and out of
system management mode, respectively upon receiving KVM_REQ_SMI and upon
executing a RSM instruction. Both 32- and 64-bit formats are supported
for the SMM state save area.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Do not process INITs immediately while in system management mode, keep
it instead in apic->pending_events. Tell userspace if an INIT is
pending when they issue GET_VCPU_EVENTS, and similarly handle the
new field in SET_VCPU_EVENTS.
Note that the same treatment should be done while in VMX non-root mode.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch adds the interface between x86.c and the emulator: the
SMBASE register, a new emulator flag, the RSM instruction. It also
adds a new request bit that will be used by the KVM_SMI ioctl.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch includes changes to the external API for SMM support.
Userspace can predicate the availability of the new fields and
ioctls on a new capability, KVM_CAP_X86_SMM, which is added at the end
of the patch series.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The hflags field will contain information about system management mode
and will be useful for the emulator. Pass the entire field rather than
just the guest-mode information.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
SMBASE is only readable from SMM for the VCPU, but it must be always
accessible if userspace is accessing it. Thus, all functions that
read MSRs are changed to accept a struct msr_data; the host_initiated
and index fields are pre-initialized, while the data field is filled
on return.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We will want to filter away MSR_IA32_SMBASE from the emulated_msrs if
the host CPU does not support SMM virtualization. Introduce the
logic to do that, and also move paravirt MSRs to emulated_msrs for
simplicity and to get rid of KVM_SAVE_MSRS_BEGIN.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Initialize kvmclock base, on kvmclock system MSR write time,
so that the guest sees kvmclock counting from zero.
This matches baremetal behaviour when kvmclock in guest
sets sched clock stable.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
[Remove unnecessary comment. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The periodic kvmclock sync can be an undesired source of latencies.
When running cyclictest on a guest, a latency spike is visible.
With kvmclock periodic sync disabled, the spike is gone.
Guests should use ntp which means the propagations of ntp corrections
from the host clock are unnecessary.
v2:
-> Make parameter read-only (Radim)
-> Return early on kvmclock_sync_fn (Andrew)
Reported-and-tested-by: Luiz Capitulino <lcapitulino@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This lets the function access the new memory slot without going through
kvm_memslots and id_to_memslot. It will simplify the code when more
than one address space will be supported.
Unfortunately, the "const"ness of the new argument must be casted
away in two places. Fixing KVM to accept const struct kvm_memory_slot
pointers would require modifications in pretty much all architectures,
and is left for later.
Reviewed-by: Radim Krcmar <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Architecture-specific helpers are not supposed to muck with
struct kvm_userspace_memory_region contents. Add const to
enforce this.
In order to eliminate the only write in __kvm_set_memory_region,
the cleaning of deleted slots is pulled up from update_memslots
to __kvm_set_memory_region.
Reviewed-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Reviewed-by: Radim Krcmar <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_memslots provides lockdep checking. Use it consistently instead of
explicit dereferencing of kvm->memslots.
Reviewed-by: Radim Krcmar <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The MPX feature requires eager KVM FPU restore support. We have verified
that MPX cannot work correctly with the current lazy KVM FPU restore
mechanism. Eager KVM FPU restore should be enabled if the MPX feature is
exposed to VM.
Signed-off-by: Yang Zhang <yang.z.zhang@intel.com>
Signed-off-by: Liang Li <liang.z.li@intel.com>
[Also activate the FPU on AMD processors. - Paolo]
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
CR0.CD and CR0.NW are not used by shadow page table so that need
not adjust mmu if these two bit are changed
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently, whenever guest MTRR registers are changed
kvm_mmu_reset_context is called to switch to the new root shadow page
table, however, it's useless since:
1) the cache type is not cached into shadow page's attribute so that
the original root shadow page will be reused
2) the cache type is set on the last spte, that means we should sync
the last sptes when MTRR is changed
This patch fixs this issue by drop all the spte in the gfn range which
is being updated by MTRR
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM may turn a user page to a kernel page when kernel writes a readonly
user page if CR0.WP = 1. This shadow page entry will be reused after
SMAP is enabled so that kernel is allowed to access this user page
Fix it by setting SMAP && !CR0.WP into shadow page's role and reset mmu
once CR4.SMAP is updated
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM may turn a user page to a kernel page when kernel writes a readonly
user page if CR0.WP = 1. This shadow page entry will be reused after
SMAP is enabled so that kernel is allowed to access this user page
Fix it by setting SMAP && !CR0.WP into shadow page's role and reset mmu
once CR4.SMAP is updated
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
PAT should be 0007_0406_0007_0406h on RESET and not modified on INIT.
VMX used a wrong value (host's PAT) and while SVM used the right one,
it never got to arch.pat.
This is not an issue with QEMU as it will force the correct value.
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently KVM will clear the FPU bits in CR0.TS in the VMCS, and trap to
re-load them every time the guest accesses the FPU after a switch back into
the guest from the host.
This patch copies the x86 task switch semantics for FPU loading, with the
FPU loaded eagerly after first use if the system uses eager fpu mode,
or if the guest uses the FPU frequently.
In the latter case, after loading the FPU for 255 times, the fpu_counter
will roll over, and we will revert to loading the FPU on demand, until
it has been established that the guest is still actively using the FPU.
This mirrors the x86 task switch policy, which seems to work.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Extended struct kvm_lapic_irq with bool msi_redir_hint, which will
be used to determine if the delivery of the MSI should target only
the lowest priority CPU in the logical group specified for delivery.
(In physical dest mode, the RH bit is not relevant). Initialized the value
of msi_redir_hint to true when RH=1 in kvm_set_msi_irq(), and initialized
to false in all other cases.
Added value of msi_redir_hint to a debug message dump of an IRQ in
apic_send_ipi().
Signed-off-by: James Sullivan <sullivan.james.f@gmail.com>
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
x86 architecture defines differences between the reset and INIT sequences.
INIT does not initialize the FPU (including MMX, XMM, YMM, etc.), TSC, PMU,
MSRs (in general), MTRRs machine-check, APIC ID, APIC arbitration ID and BSP.
References (from Intel SDM):
"If the MP protocol has completed and a BSP is chosen, subsequent INITs (either
to a specific processor or system wide) do not cause the MP protocol to be
repeated." [8.4.2: MP Initialization Protocol Requirements and Restrictions]
[Table 9-1. IA-32 Processor States Following Power-up, Reset, or INIT]
"If the processor is reset by asserting the INIT# pin, the x87 FPU state is not
changed." [9.2: X87 FPU INITIALIZATION]
"The state of the local APIC following an INIT reset is the same as it is after
a power-up or hardware reset, except that the APIC ID and arbitration ID
registers are not affected." [10.4.7.3: Local APIC State After an INIT Reset
("Wait-for-SIPI" State)]
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Message-Id: <1428924848-28212-1-git-send-email-namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Introducing KVM_CAP_DISABLE_QUIRKS for disabling x86 quirks that were previous
created in order to overcome QEMU issues. Those issue were mostly result of
invalid VM BIOS. Currently there are two quirks that can be disabled:
1. KVM_QUIRK_LINT0_REENABLED - LINT0 was enabled after boot
2. KVM_QUIRK_CD_NW_CLEARED - CD and NW are cleared after boot
These two issues are already resolved in recent releases of QEMU, and would
therefore be disabled by QEMU.
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Message-Id: <1428879221-29996-1-git-send-email-namit@cs.technion.ac.il>
[Report capability from KVM_CHECK_EXTENSION too. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Use __kvm_guest_{enter|exit} instead of kvm_guest_{enter|exit}
where interrupts are disabled.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The kvmclock spec says that the host will increment a version field to
an odd number, then update stuff, then increment it to an even number.
The host is buggy and doesn't do this, and the result is observable
when one vcpu reads another vcpu's kvmclock data.
There's no good way for a guest kernel to keep its vdso from reading
a different vcpu's kvmclock data, but we don't need to care about
changing VCPUs as long as we read a consistent data from kvmclock.
(VCPU can change outside of this loop too, so it doesn't matter if we
return a value not fit for this VCPU.)
Based on a patch by Radim Krčmář.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Acked-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_init_msr_list is currently called before hardware_setup. As a result,
vmx_mpx_supported always returns false when kvm_init_msr_list checks whether to
save MSR_IA32_BNDCFGS.
Move kvm_init_msr_list after vmx_hardware_setup is called to fix this issue.
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Message-Id: <1428864435-4732-1-git-send-email-namit@cs.technion.ac.il>
Cc: stable@vger.kernel.org # 3.15+
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull timer updates from Ingo Molnar:
"The main changes in this cycle were:
- clockevents state machine cleanups and enhancements (Viresh Kumar)
- clockevents broadcast notifier horror to state machine conversion
and related cleanups (Thomas Gleixner, Rafael J Wysocki)
- clocksource and timekeeping core updates (John Stultz)
- clocksource driver updates and fixes (Ben Dooks, Dmitry Osipenko,
Hans de Goede, Laurent Pinchart, Maxime Ripard, Xunlei Pang)
- y2038 fixes (Xunlei Pang, John Stultz)
- NMI-safe ktime_get_raw_fast() and general refactoring of the clock
code, in preparation to perf's per event clock ID support (Peter
Zijlstra)
- generic sched/clock fixes, optimizations and cleanups (Daniel
Thompson)
- clockevents cpu_down() race fix (Preeti U Murthy)"
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (94 commits)
timers/PM: Drop unnecessary braces from tick_freeze()
timers/PM: Fix up tick_unfreeze()
timekeeping: Get rid of stale comment
clockevents: Cleanup dead cpu explicitely
clockevents: Make tick handover explicit
clockevents: Remove broadcast oneshot control leftovers
sched/idle: Use explicit broadcast oneshot control function
ARM: Tegra: Use explicit broadcast oneshot control function
ARM: OMAP: Use explicit broadcast oneshot control function
intel_idle: Use explicit broadcast oneshot control function
ACPI/idle: Use explicit broadcast control function
ACPI/PAD: Use explicit broadcast oneshot control function
x86/amd/idle, clockevents: Use explicit broadcast oneshot control functions
clockevents: Provide explicit broadcast oneshot control functions
clockevents: Remove the broadcast control leftovers
ARM: OMAP: Use explicit broadcast control function
intel_idle: Use explicit broadcast control function
cpuidle: Use explicit broadcast control function
ACPI/processor: Use explicit broadcast control function
ACPI/PAD: Use explicit broadcast control function
...
ARM/ARM64: fixes for live migration, irqfd and ioeventfd support (enabling
vhost, too), page aging
s390: interrupt handling rework, allowing to inject all local interrupts
via new ioctl and to get/set the full local irq state for migration
and introspection. New ioctls to access memory by virtual address,
and to get/set the guest storage keys. SIMD support.
MIPS: FPU and MIPS SIMD Architecture (MSA) support. Includes some patches
from Ralf Baechle's MIPS tree.
x86: bugfixes (notably for pvclock, the others are small) and cleanups.
Another small latency improvement for the TSC deadline timer.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
iQEcBAABAgAGBQJVJ9vmAAoJEL/70l94x66DoMEH/R3rh8IMf4jTiWRkcqohOMPX
k1+NaSY/lCKayaSgggJ2hcQenMbQoXEOdslvaA/H0oC+VfJGK+lmU6E63eMyyhjQ
Y+Px6L85NENIzDzaVu/TIWWuhil5PvIRr3VO8cvntExRoCjuekTUmNdOgCvN2ObW
wswN2qRdPIeEj2kkulbnye+9IV4G0Ne9bvsmUdOdfSSdi6ZcV43JcvrpOZT++mKj
RrKB+3gTMZYGJXMMLBwMkdl8mK1ozriD+q0mbomT04LUyGlPwYLl4pVRDBqyksD7
KsSSybaK2E4i5R80WEljgDMkNqrCgNfg6VZe4n9Y+CfAAOToNnkMJaFEi+yuqbs=
=yu2b
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
"First batch of KVM changes for 4.1
The most interesting bit here is irqfd/ioeventfd support for ARM and
ARM64.
Summary:
ARM/ARM64:
fixes for live migration, irqfd and ioeventfd support (enabling
vhost, too), page aging
s390:
interrupt handling rework, allowing to inject all local interrupts
via new ioctl and to get/set the full local irq state for migration
and introspection. New ioctls to access memory by virtual address,
and to get/set the guest storage keys. SIMD support.
MIPS:
FPU and MIPS SIMD Architecture (MSA) support. Includes some
patches from Ralf Baechle's MIPS tree.
x86:
bugfixes (notably for pvclock, the others are small) and cleanups.
Another small latency improvement for the TSC deadline timer"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
KVM: use slowpath for cross page cached accesses
kvm: mmu: lazy collapse small sptes into large sptes
KVM: x86: Clear CR2 on VCPU reset
KVM: x86: DR0-DR3 are not clear on reset
KVM: x86: BSP in MSR_IA32_APICBASE is writable
KVM: x86: simplify kvm_apic_map
KVM: x86: avoid logical_map when it is invalid
KVM: x86: fix mixed APIC mode broadcast
KVM: x86: use MDA for interrupt matching
kvm/ppc/mpic: drop unused IRQ_testbit
KVM: nVMX: remove unnecessary double caching of MAXPHYADDR
KVM: nVMX: checks for address bits beyond MAXPHYADDR on VM-entry
KVM: x86: cache maxphyaddr CPUID leaf in struct kvm_vcpu
KVM: vmx: pass error code with internal error #2
x86: vdso: fix pvclock races with task migration
KVM: remove kvm_read_hva and kvm_read_hva_atomic
KVM: x86: optimize delivery of TSC deadline timer interrupt
KVM: x86: extract blocking logic from __vcpu_run
kvm: x86: fix x86 eflags fixed bit
KVM: s390: migrate vcpu interrupt state
...
Dirty logging tracks sptes in 4k granularity, meaning that large sptes
have to be split. If live migration is successful, the guest in the
source machine will be destroyed and large sptes will be created in the
destination. However, the guest continues to run in the source machine
(for example if live migration fails), small sptes will remain around
and cause bad performance.
This patch introduce lazy collapsing of small sptes into large sptes.
The rmap will be scanned in ioctl context when dirty logging is stopped,
dropping those sptes which can be collapsed into a single large-page spte.
Later page faults will create the large-page sptes.
Reviewed-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Message-Id: <1428046825-6905-1-git-send-email-wanpeng.li@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
CR2 is not cleared as it should after reset. See Intel SDM table named "IA-32
Processor States Following Power-up, Reset, or INIT".
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Message-Id: <1427933438-12782-5-git-send-email-namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
DR0-DR3 are not cleared as they should during reset and when they are set from
userspace. It appears to be caused by c77fb5fe6f ("KVM: x86: Allow the guest
to run with dirty debug registers").
Force their reload on these situations.
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Message-Id: <1427933438-12782-4-git-send-email-namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
After reset, the CPU can change the BSP, which will be used upon INIT. Reset
should return the BSP which QEMU asked for, and therefore handled accordingly.
To quote: "If the MP protocol has completed and a BSP is chosen, subsequent
INITs (either to a specific processor or system wide) do not cause the MP
protocol to be repeated."
[Intel SDM 8.4.2: MP Initialization Protocol Requirements and Restrictions]
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Message-Id: <1427933438-12782-3-git-send-email-namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
cpuid_maxphyaddr(), which performs lot of memory accesses is called
extensively across KVM, especially in nVMX code.
This patch adds a cached value of maxphyaddr to vcpu.arch to reduce the
pressure onto CPU cache and simplify the code of cpuid_maxphyaddr()
callers. The cached value is initialized in kvm_arch_vcpu_init() and
reloaded every time CPUID is updated by usermode. It is obvious that
these reloads occur infrequently.
Signed-off-by: Eugene Korenevsky <ekorenevsky@gmail.com>
Message-Id: <20150329205612.GA1223@gnote>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The newly-added tracepoint shows the following results on
the tscdeadline_latency test:
qemu-kvm-8387 [002] 6425.558974: kvm_vcpu_wakeup: poll time 10407 ns
qemu-kvm-8387 [002] 6425.558984: kvm_vcpu_wakeup: poll time 0 ns
qemu-kvm-8387 [002] 6425.561242: kvm_vcpu_wakeup: poll time 10477 ns
qemu-kvm-8387 [002] 6425.561251: kvm_vcpu_wakeup: poll time 0 ns
and so on. This is because we need to go through kvm_vcpu_block again
after the timer IRQ is injected. Avoid it by polling once before
entering kvm_vcpu_block.
On my machine (Xeon E5 Sandy Bridge) this removes about 500 cycles (7%)
from the latency of the TSC deadline timer.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rename the old __vcpu_run to vcpu_run, and extract part of it to a new
function vcpu_block.
The next patch will add a new condition in vcpu_block, avoid extra
indentation.
Reviewed-by: David Matlack <dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In preparation of adding another tkr field, rename this one to
tkr_mono. Also rename tk_read_base::base_mono to tk_read_base::base,
since the structure is not specific to CLOCK_MONOTONIC and the mono
name got added to the tk_read_base instance.
Lots of trivial churn.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: John Stultz <john.stultz@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150319093400.344679419@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This is needed in e.g. ARM vGIC emulation, where the MMIO handling
depends on the VCPU that does the access.
Signed-off-by: Nikolay Nikolaev <n.nikolaev@virtualopensystems.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
This patch fix the following sparse warnings:
for arch/x86/kvm/x86.c:
warning: symbol 'emulator_read_write' was not declared. Should it be static?
warning: symbol 'emulator_write_emulated' was not declared. Should it be static?
warning: symbol 'emulator_get_dr' was not declared. Should it be static?
warning: symbol 'emulator_set_dr' was not declared. Should it be static?
for arch/x86/kvm/pmu.c:
warning: symbol 'fixed_pmc_events' was not declared. Should it be static?
Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch fix the following sparse warning:
for file arch/x86/kvm/x86.c:
warning: Using plain integer as NULL pointer
Signed-off-by: Xiubo Li <lixiubo@cmss.chinamobile.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
POWER supports irqfds but forgot to advertise them. Some userspace does
not check for the capability, but others check it---thus they work on
x86 and s390 but not POWER.
To avoid that other architectures in the future make the same mistake, let
common code handle KVM_CAP_IRQFD the same way as KVM_CAP_IRQFD_RESAMPLE.
Reported-and-tested-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org
Fixes: 297e21053a
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Currently kvm_emulate() skips the instruction but kvm_emulate_* sometimes
don't. The end reult is the caller ends up doing the skip themselves.
Let's make them consistant.
Signed-off-by: Joel Schopp <joel.schopp@amd.com>
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
kvm_kvfree() provides exactly the same functionality as the
new common kvfree() function - so let's simply replace the
kvm function with the common function.
Signed-off-by: Thomas Huth <thuth@linux.vnet.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch introduces a new module parameter for the KVM module; when it
is present, KVM attempts a bit of polling on every HLT before scheduling
itself out via kvm_vcpu_block.
This parameter helps a lot for latency-bound workloads---in particular
I tested it with O_DSYNC writes with a battery-backed disk in the host.
In this case, writes are fast (because the data doesn't have to go all
the way to the platters) but they cannot be merged by either the host or
the guest. KVM's performance here is usually around 30% of bare metal,
or 50% if you use cache=directsync or cache=writethrough (these
parameters avoid that the guest sends pointless flush requests, and
at the same time they are not slow because of the battery-backed cache).
The bad performance happens because on every halt the host CPU decides
to halt itself too. When the interrupt comes, the vCPU thread is then
migrated to a new physical CPU, and in general the latency is horrible
because the vCPU thread has to be scheduled back in.
With this patch performance reaches 60-65% of bare metal and, more
important, 99% of what you get if you use idle=poll in the guest. This
means that the tunable gets rid of this particular bottleneck, and more
work can be done to improve performance in the kernel or QEMU.
Of course there is some price to pay; every time an otherwise idle vCPUs
is interrupted by an interrupt, it will poll unnecessarily and thus
impose a little load on the host. The above results were obtained with
a mostly random value of the parameter (500000), and the load was around
1.5-2.5% CPU usage on one of the host's core for each idle guest vCPU.
The patch also adds a new stat, /sys/kernel/debug/kvm/halt_successful_poll,
that can be used to tune the parameter. It counts how many HLT
instructions received an interrupt during the polling period; each
successful poll avoids that Linux schedules the VCPU thread out and back
in, and may also avoid a likely trip to C1 and back for the physical CPU.
While the VM is idle, a Linux 4 VCPU VM halts around 10 times per second.
Of these halts, almost all are failed polls. During the benchmark,
instead, basically all halts end within the polling period, except a more
or less constant stream of 50 per second coming from vCPUs that are not
running the benchmark. The wasted time is thus very low. Things may
be slightly different for Windows VMs, which have a ~10 ms timer tick.
The effect is also visible on Marcelo's recently-introduced latency
test for the TSC deadline timer. Though of course a non-RT kernel has
awful latency bounds, the latency of the timer is around 8000-10000 clock
cycles compared to 20000-120000 without setting halt_poll_ns. For the TSC
deadline timer, thus, the effect is both a smaller average latency and
a smaller variance.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch adds PML support in VMX. A new module parameter 'enable_pml' is added
to allow user to enable/disable it manually.
Signed-off-by: Kai Huang <kai.huang@linux.intel.com>
Reviewed-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini