On AMD CPUs sometimes the DB bit in the stack segment
descriptor is left as 1, although the whole segment has
been made unusable. Clear it here to pass an Intel VMX
entry check when cross vendor migrating.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Sheng Yang [Mon, 27 Apr 2009 12:35:43 +0000 (20:35 +0800)]
KVM: Enable snooping control for supported hardware
Memory aliases with different memory type is a problem for guest. For the guest
without assigned device, the memory type of guest memory would always been the
same as host(WB); but for the assigned device, some part of memory may be used
as DMA and then set to uncacheable memory type(UC/WC), which would be a conflict of
host memory type then be a potential issue.
Snooping control can guarantee the cache correctness of memory go through the
DMA engine of VT-d.
[avi: fix build on ia64]
Signed-off-by: Sheng Yang <sheng@linux.intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Start to use interrupt/exception queues like VMX does.
This also fix the bug that if exit was caused by a guest
internal exception access to IDT the exception was not
reinjected.
Use EVENTINJ to inject interrupts. Use VINT only for detecting when IRQ
windows is open again. EVENTINJ ensures
the interrupt is injected immediately and not delayed.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
KVM: ia64: restore irq state before calling kvm_vcpu_init
Make sure to restore the psr after calling kvm_insert_vmm_mapping()
which calls ia64_itr_entry() as it disables local interrupts and
kvm_vcpu_init() may sleep.
KVM: x86: check for cr3 validity in ioctl_set_sregs
Matt T. Yourst notes that kvm_arch_vcpu_ioctl_set_sregs lacks validity
checking for the new cr3 value:
"Userspace callers of KVM_SET_SREGS can pass a bogus value of cr3 to
the kernel. This will trigger a NULL pointer access in gfn_to_rmap()
when userspace next tries to call KVM_RUN on the affected VCPU and kvm
attempts to activate the new non-existent page table root.
This happens since kvm only validates that cr3 points to a valid guest
physical memory page when code *inside* the guest sets cr3. However, kvm
currently trusts the userspace caller (e.g. QEMU) on the host machine to
always supply a valid page table root, rather than properly validating
it along with the rest of the reloaded guest state."
nathan binkert [Sat, 28 Mar 2009 04:53:05 +0000 (21:53 -0700)]
KVM: Make kvm header C++ friendly
Two things needed fixing: 1) g++ does not allow a named structure type
within an anonymous union and 2) Avoid name clash between two padding
fields within the same struct by giving them different names as is
done elsewhere in the header.
Signed-off-by: Nathan Binkert <nate@binkert.org> Signed-off-by: Avi Kivity <avi@redhat.com>
Assuming that PIT counter reads should return 0 for an expired timer
is wrong: when it is active, the counter never stops (see comment on
__kpit_elapsed).
Also arm a one shot timer for mode 0.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Sheng Yang [Thu, 2 Apr 2009 02:28:37 +0000 (10:28 +0800)]
KVM: MMU: Discard reserved bits checking on PDE bit 7-8
1. It's related to a Linux kernel bug which fixed by Ingo on 07a66d7c53a538e1a9759954a82bb6c07365eff9. The original code exists for quite a
long time, and it would convert a PDE for large page into a normal PDE. But it
fail to fit normal PDE well. With the code before Ingo's fix, the kernel would
fall reserved bit checking with bit 8 - the remaining global bit of PTE. So the
kernel would receive a double-fault.
2. After discussion, we decide to discard PDE bit 7-8 reserved checking for now.
For this marked as reserved in SDM, but didn't checked by the processor in
fact...
Signed-off-by: Sheng Yang <sheng@linux.intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Gleb Natapov [Mon, 30 Mar 2009 13:03:29 +0000 (16:03 +0300)]
KVM: Fix unneeded instruction skipping during task switching.
There is no need to skip instruction if the reason for a task switch
is a task gate in IDT and access to it is caused by an external even.
The problem is currently solved only for VMX since there is no reliable
way to skip an instruction in SVM. We should emulate it instead.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Gleb Natapov [Mon, 30 Mar 2009 13:03:18 +0000 (16:03 +0300)]
KVM: VMX: Do not zero idt_vectoring_info in vmx_complete_interrupts().
We will need it later in task_switch().
Code in handle_exception() is dead. is_external_interrupt(vect_info)
will always be false since idt_vectoring_info is zeroed in
vmx_complete_interrupts().
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Gleb Natapov [Mon, 30 Mar 2009 13:03:13 +0000 (16:03 +0300)]
KVM: VMX: Rewrite vmx_complete_interrupt()'s twisted maze of if() statements
...with a more straightforward switch().
Also fix a bug when NMI could be dropped on exit. Although this should
never happen in practice, since NMIs can only be injected, never triggered
internally by the guest like exceptions.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Gleb Natapov [Mon, 30 Mar 2009 13:03:08 +0000 (16:03 +0300)]
KVM: VMX: Fix handling of a fault during NMI unblocked due to IRET
Bit 12 is undefined in any of the following cases:
If the VM exit sets the valid bit in the IDT-vectoring information field.
If the VM exit is due to a double fault.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Avi Kivity [Tue, 31 Mar 2009 08:31:54 +0000 (11:31 +0300)]
KVM: MMU: Use different shadows when EFER.NXE changes
A pte that is shadowed when the guest EFER.NXE=1 is not valid when
EFER.NXE=0; if bit 63 is set, the pte should cause a fault, and since the
shadow EFER always has NX enabled, this won't happen.
Fix by using a different shadow page table for different EFER.NXE bits. This
allows vcpus to run correctly with different values of EFER.NXE, and for
transitions on this bit to be handled correctly without requiring a full
flush.
Dong, Eddie [Mon, 30 Mar 2009 08:21:08 +0000 (16:21 +0800)]
KVM: MMU: Emulate #PF error code of reserved bits violation
Detect, indicate, and propagate page faults where reserved bits are set.
Take care to handle the different paging modes, each of which has different
sets of reserved bits.
[avi: fix pte reserved bits for efer.nxe=0]
Signed-off-by: Eddie Dong <eddie.dong@intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Yang Zhang [Mon, 23 Mar 2009 07:31:04 +0000 (03:31 -0400)]
KVM: ia64: enable external interrupt in vmm
Currently, the interrupt enable bit is cleared when in
the vmm. This patch sets the bit and the external interrupts can
be dealt with when in the vmm. This improves the I/O performance.
Signed-off-by: Yang Zhang <yang.zhang@intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Gleb Natapov [Mon, 23 Mar 2009 13:11:44 +0000 (15:11 +0200)]
KVM: Timer event should not unconditionally unhalt vcpu.
Currently timer events are processed before entering guest mode. Move it
to main vcpu event loop since timer events should be processed even while
vcpu is halted. Timer may cause interrupt/nmi to be injected and only then
vcpu will be unhalted.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Amit Shah [Fri, 20 Mar 2009 07:09:00 +0000 (12:39 +0530)]
KVM: x86: Ignore reads to EVNTSEL MSRs
We ignore writes to the performance counters and performance event
selector registers already. Kaspersky antivirus reads the eventsel
MSR causing it to crash with the current behaviour.
Return 0 as data when the eventsel registers are read to stop the
crash.
Signed-off-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Sheng Yang [Thu, 12 Mar 2009 13:45:39 +0000 (21:45 +0800)]
KVM: Device assignment framework rework
After discussion with Marcelo, we decided to rework device assignment framework
together. The old problems are kernel logic is unnecessary complex. So Marcelo
suggest to split it into a more elegant way:
1. Split host IRQ assign and guest IRQ assign. And userspace determine the
combination. Also discard msi2intx parameter, userspace can specific
KVM_DEV_IRQ_HOST_MSI | KVM_DEV_IRQ_GUEST_INTX in assigned_irq->flags to
enable MSI to INTx convertion.
2. Split assign IRQ and deassign IRQ. Import two new ioctls:
KVM_ASSIGN_DEV_IRQ and KVM_DEASSIGN_DEV_IRQ.
This patch also fixed the reversed _IOR vs _IOW in definition(by deprecated the
old interface).
[avi: replace homemade bitcount() by hweight_long()]
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Sheng Yang <sheng@linux.intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Hannes Eder [Tue, 10 Mar 2009 21:51:09 +0000 (22:51 +0100)]
KVM: make 'lapic_timer_ops' and 'kpit_ops' static
Fix this sparse warnings:
arch/x86/kvm/lapic.c:916:22: warning: symbol 'lapic_timer_ops' was not declared. Should it be static?
arch/x86/kvm/i8254.c:268:22: warning: symbol 'kpit_ops' was not declared. Should it be static?
Signed-off-by: Hannes Eder <hannes@hanneseder.net> Signed-off-by: Avi Kivity <avi@redhat.com>
Jes Sorensen [Wed, 25 Feb 2009 16:38:55 +0000 (10:38 -0600)]
KVM: ia64: Drop in SN2 replacement of fast path ITC emulation fault handler
Copy in SN2 RTC based ITC emulation for fast exit. The two versions
have the same size, so a dropin is simpler than patching the branch
instruction to hit the SN2 version.
Jes Sorensen [Wed, 25 Feb 2009 16:38:53 +0000 (10:38 -0600)]
KVM: ia64: Create inline function kvm_get_itc() to centralize ITC reading.
Move all reading of special register 'AR_ITC' into two functions, one
in the kernel and one in the VMM module. When running on SN2, base the
result on the RTC rather the system ITC, as the ITC isn't
synchronized.
Gleb Natapov [Thu, 5 Mar 2009 14:34:59 +0000 (16:34 +0200)]
KVM: change the way how lowest priority vcpu is calculated
The new way does not require additional loop over vcpus to calculate
the one with lowest priority as one is chosen during delivery bitmap
construction.
Use kvm_apic_match_dest() in kvm_get_intr_delivery_bitmask() instead
of duplicating the same code. Use kvm_get_intr_delivery_bitmask() in
apic_send_ipi() to figure out ipi destination instead of reimplementing
the logic.
Sheng Yang [Wed, 4 Mar 2009 05:33:02 +0000 (13:33 +0800)]
KVM: Merge kvm_ioapic_get_delivery_bitmask into kvm_get_intr_delivery_bitmask
Gleb fixed bitmap ops usage in kvm_ioapic_get_delivery_bitmask.
Sheng merged two functions, as well as fixed several issues in
kvm_get_intr_delivery_bitmask
1. deliver_bitmask is a bitmap rather than a unsigned long intereger.
2. Lowest priority target bitmap wrong calculated by mistake.
3. Prevent potential NULL reference.
4. Declaration in include/kvm_host.h caused powerpc compilation warning.
5. Add warning for guest broadcast interrupt with lowest priority delivery mode.
6. Removed duplicate bitmap clean up in caller of kvm_get_intr_delivery_bitmask.
Marcelo Tosatti [Mon, 23 Feb 2009 13:57:41 +0000 (10:57 -0300)]
KVM: unify part of generic timer handling
Hide the internals of vcpu awakening / injection from the in-kernel
emulated timers. This makes future changes in this logic easier and
decreases the distance to more generic timer handling.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
KVM: declare ioapic functions only on affected hardware
Since "KVM: Unify the delivery of IOAPIC and MSI interrupts"
I get the following warnings:
CC [M] arch/s390/kvm/kvm-s390.o
In file included from arch/s390/kvm/kvm-s390.c:22:
include/linux/kvm_host.h:357: warning: 'struct kvm_ioapic' declared inside parameter list
include/linux/kvm_host.h:357: warning: its scope is only this definition or declaration, which is probably not what you want
This patch limits IOAPIC functions for architectures that have one.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Avi Kivity <avi@redhat.com>
As it turns out, the call trace is messed up due to gcc's inlining, but
I isolated the problem anyway: kvm_write_guest_time() is being used in a
non-thread-safe manner on preemptable kernels.
Basically kvm_write_guest_time()'s body needs to be surrounded by
preempt_disable() and preempt_enable(), since the kernel won't let us
query any per-CPU data (indirectly using smp_processor_id()) without
preemption disabled. The attached patch fixes this issue by disabling
preemption inside kvm_write_guest_time().
[marcelo: surround only __get_cpu_var calls since the warning
is harmless]
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Sheng Yang [Wed, 25 Feb 2009 09:22:28 +0000 (17:22 +0800)]
KVM: Enable MSI-X for KVM assigned device
This patch finally enable MSI-X.
What we need for MSI-X:
1. Intercept one page in MMIO region of device. So that we can get guest desired
MSI-X table and set up the real one. Now this have been done by guest, and
transfer to kernel using ioctl KVM_SET_MSIX_NR and KVM_SET_MSIX_ENTRY.
2. Information for incoming interrupt. Now one device can have more than one
interrupt, and they are all handled by one workqueue structure. So we need to
identify them. The previous patch enable gsi_msg_pending_bitmap get this done.
3. Mapping from host IRQ to guest gsi as well as guest gsi to real MSI/MSI-X
message address/data. We used same entry number for the host and guest here, so
that it's easy to find the correlated guest gsi.
What we lack for now:
1. The PCI spec said nothing can existed with MSI-X table in the same page of
MMIO region, except pending bits. The patch ignore pending bits as the first
step (so they are always 0 - no pending).
2. The PCI spec allowed to change MSI-X table dynamically. That means, the OS
can enable MSI-X, then mask one MSI-X entry, modify it, and unmask it. The patch
didn't support this, and Linux also don't work in this way.
3. The patch didn't implement MSI-X mask all and mask single entry. I would
implement the former in driver/pci/msi.c later. And for single entry, userspace
should have reposibility to handle it.
Signed-off-by: Sheng Yang <sheng@linux.intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
projects / linux-beck.git / log