There are two classes of page faults trapped by kvm:
- host page faults, where the fault is needed to allow kvm to install
the shadow pte or update the guest accessed and dirty bits
- guest page faults, where the guest has faulted and kvm simply injects
the fault back into the guest to handle
The second class, guest page faults, is pure overhead. We can eliminate
some of it on vmx using the following evil trick:
- when we set up a shadow page table entry, if the corresponding guest pte
is not present, set up the shadow pte as not present
- if the guest pte _is_ present, mark the shadow pte as present but also
set one of the reserved bits in the shadow pte
- tell the vmx hardware not to trap faults which have the present bit clear
With this, normal page-not-present faults go directly to the guest,
bypassing kvm entirely.
Unfortunately, this trick only works on Intel hardware, as AMD lacks a
way to discriminate among page faults based on error code. It is also
a little risky since it uses reserved bits which might become unreserved
in the future, so a module parameter is provided to disable it.
Signed-off-by: Avi Kivity <avi@qumranet.com>
Move emulate_ctxt to kvm_vcpu to keep emulate context when we exit from kvm
module. Call x86_decode_insn() only when needed. Modify x86_emulate_insn() to
not modify the context if it must be re-entered.
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
emulate_instruction() calls now x86_decode_insn() and x86_emulate_insn().
x86_emulate_insn() is x86_emulate_memop() without the decoding part.
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This patch refactors the current hypercall infrastructure to better
support live migration and SMP. It eliminates the hypercall page by
trapping the UD exception that would occur if you used the wrong hypercall
instruction for the underlying architecture and replacing it with the right
one lazily.
A fall-out of this patch is that the unhandled hypercalls no longer trap to
userspace. There is very little reason though to use a hypercall to
communicate with userspace as PIO or MMIO can be used. There is no code
in tree that uses userspace hypercalls.
[avi: fix #ud injection on vmx]
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
All kobjects require a dynamically allocated name now. We no longer
need to keep track if the name is statically assigned, we can just
unconditionally free() all kobject names on cleanup.
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
The clts code didn't use set_cr0 properly, so our lazy FPU
processing wasn't being done by the clts instruction at all.
(this isn't called on Intel as the hardware does the decode for us)
Signed-off-by: Amit Shah <amit.shah@qumranet.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
In kvm_flush_remote_tlbs(), replace a loop using smp_call_function_single()
by a single call to smp_call_function_mask() (which is new for x86_64).
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
We need to make sure that the timer interrupt happens before we clear
PF_VCPU, so the accounting code actually sees guest mode.
http://lkml.org/lkml/2007/10/15/114
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
If we defer updating rip until pio instructions are executed, we have a
problem with reset: a pio reset updates rip, and when the instruction
completes we skip the emulated instruction, pointing rip somewhere completely
unrelated.
Fix by updating rip when we see decode the instruction, not after emulation.
Signed-off-by: Avi Kivity <avi@qumranet.com>
This patch just renames the current (misnamed) _arch namings to _x86 to
ensure better readability when a real arch layer takes place.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
The mutex->splinlock convertion alllows us to make some code simplifications.
As we can keep the lock longer, we don't have to release it and then
have to check if the environment has not been modified before re-taking it. We
can remove kvm->busy and kvm->memory_config_version.
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
SVM gets the DB and L bits for the cs by decoding the segment. This
is in fact the completely generic code, so hoist it for kvm-lite to use.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
We don't update the vcpu control registers in various places. We
should do so.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This was missed when moving stuff around in fbc4f2e
Fixes Solaris guests and bug #1773613
Signed-off-by: Amit Shah <amit.shah@qumranet.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This patch enables INIT/SIPI handling using in-kernel APIC by
introducing a ->mp_state field to emulate the SMP state transition.
[avi: remove smp_processor_id() warning]
Signed-off-by: Qing He <qing.he@intel.com>
Signed-off-by: Xin Li <xin.b.li@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
APIC timer IRQ is set every time when a certain period
expires at host time, but the guest may be descheduled
at that time and thus the irq be overwritten by later fire.
This patch keep track of firing irq numbers and decrease
only when the IRQ is injected to guest or buffered in
APIC.
Signed-off-by: Yaozu (Eddie) Dong <Eddie.Dong@intel.com>
Signed-off-by: Qing He <qing.he@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This patch adds a new vcpu-based IOCTL to save and restore the local
apic registers for a single vcpu. The kernel only copies the apic page as
a whole, extraction of registers is left to userspace side. On restore, the
APIC timer is restarted from the initial count, this introduces a little
delay, but works fine.
Signed-off-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Signed-off-by: Qing He <qing.he@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This patch adds support for in-kernel ioapic save and restore (to
and from userspace). It uses the same get/set_irqchip ioctl as
in-kernel PIC.
Signed-off-by: Qing He <qing.he@intel.com>
Signed-off-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
vcpu->irq_pending is saved in get/set_sreg IOCTL, but when in-kernel
local APIC is used, doing this may occasionally overwrite vcpu->apic to
an invalid value, as in the vm restore path.
Signed-off-by: Qing He <qing.he@intel.com>
This patch adds two new ioctls to dump and write kernel irqchips for
save/restore and live migration. PIC s/r and l/m is implemented in this
patch.
Signed-off-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Signed-off-by: Qing He <qing.he@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
pio operation and IRQ_LINE kvm_vm_ioctl is not kvm->lock
protected. Add lock to same with IOAPIC MMIO operations.
Signed-off-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
By sleeping in the kernel when hlt is executed, we simplify the in-kernel
guest interrupt path considerably.
Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Because lightweight exits (exits which don't involve userspace) are many
times faster than heavyweight exits, it makes sense to emulate high usage
devices in the kernel. The local APIC is one such device, especially for
Windows and for SMP, so we add an APIC model to kvm.
It also allows in-kernel host-side drivers to inject interrupts without
going through userspace.
[compile fix on i386 from Jindrich Makovicka]
Signed-off-by: Yaozu (Eddie) Dong <Eddie.Dong@intel.com>
Signed-off-by: Qing He <qing.he@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This patch is to wrap APIC base register and CR8 operation which can
provide a unique API for user level irqchip and kernel irqchip.
This is a preparation of merging lapic/ioapic patch.
Signed-off-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Split kvm_setup_pio() into two functions, one to setup in/out pio
(kvm_emulate_pio()) and one to setup ins/outs pio (kvm_emulate_pio_string()).
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Both vmx and svm decode the I/O instructions, and both botch the job,
requiring the instruction prefixes to be fetched in order to completely
decode the instruction.
So, if we see a string I/O instruction, use the x86 emulator to decode it,
as it already has all the prefix decoding machinery.
This patch defines ins/outs opcodes in x86_emulate.c and calls
emulate_instruction() from io_interception() (svm.c) and from handle_io()
(vmx.c). It removes all vmx/svm prefix instruction decoders
(get_addr_size(), io_get_override(), io_address(), get_io_count())
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Line 1809 of kvm_main.c is useless, value is overwritten in line 1815:
1809 now = min(count, PAGE_SIZE / size);
1810
1811 if (!down)
1812 in_page = PAGE_SIZE - offset_in_page(address);
1813 else
1814 in_page = offset_in_page(address) + size;
1815 now = min(count, (unsigned long)in_page / size);
1816 if (!now) {
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
All guest-invokable printks should be ratelimited to prevent malicious
guests from flooding logs. This is a start.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
We shouldn't define stat_set on the debug attributes, since that will
cause silent failure on writing: without a set argument, userspace
will get -EACCESS.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
For some reason, mark_page_dirty open-codes __gfn_to_memslot().
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
All the physical CPUs on the board should support the same VMX feature
set. Add check_processor_compatibility to kvm_arch_ops for the consistency
check.
Signed-off-by: Sheng Yang <sheng.yang@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
kvm_vm_ioctl_get_dirty_log scans bitmap to see it it's all zero, but
doesn't use that information.
Avi says:
Looks like it was used to guard kvm_mmu_slot_remove_write_access();
optimizing the case where the guest just leaves the screen alone (which
it usually does, especially in benchmarks).
I'd rather reinstate that optimization. See
90cb0529dd where the damage was done.
It's pretty simple: if the bitmap is all zero, we don't need to do anything to
clean it.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Now we use a kmem cache for allocating vcpus, we can get the 16-byte
alignment required by fxsave & fxrstor instructions, and avoid
manually aligning the buffer.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Avi wants the allocations of vcpus centralized again. The easiest way
is to add a "size" arg to kvm_init_arch, and expose the thus-prepared
cache to the modules.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
... in favor of the more general emulator_{read,write}_*.
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
... instead of a x86_emulate_ctxt, so that other callers can use it easily.
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: Avi Kivity <avi@qumranet.com>
There are several places where hardcoded numbers are used in place of
the easily-available constant, which is poor form.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Now that kvm generally runs with preemption enabled, we need to protect
the fpu intialization sequence.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This allows the kvm mmu to perform sleepy operations, such as memory
allocation.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Current kvm disables preemption while the new virtualization registers are
in use. This of course is not very good for latency sensitive workloads (one
use of virtualization is to offload user interface and other latency
insensitive stuff to a container, so that it is easier to analyze the
remaining workload). This patch re-enables preemption for kvm; preemption
is now only disabled when switching the registers in and out, and during
the switch to guest mode and back.
Contains fixes from Shaohua Li <shaohua.li@intel.com>.
Signed-off-by: Avi Kivity <avi@qumranet.com>
Add the hypercall number to kvm_run and initialize it. This changes the ABI,
but as this particular ABI was unusable before this no users are affected.
Signed-off-by: Jeff Dike <jdike@linux.intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
