Allow guest pagetables to go out of sync.  Instead of emulating write
accesses to guest pagetables, or unshadowing them, we un-write-protect
the page table and allow the guest to modify it at will.  We rely on
invlpg executions to synchronize individual ptes, and will synchronize
the entire pagetable on tlb flushes.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@redhat.com>

With pages out of sync invlpg needs to be trapped. For now simply nuke
the entry.

Untested on AMD.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@redhat.com>

Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@redhat.com>

The vcpu should process pending SIPI message before entering guest mode again.
kvm_arch_vcpu_runnable() returns true if the vcpu is in SIPI state, so
we can't call it here.
Signed-off-by: NGleb Natapov <gleb@qumranet.com>
Signed-off-by: NAvi Kivity <avi@redhat.com>

Noticed by sparse:
arch/x86/kvm/x86.c:3591:5: warning: symbol 'kvm_load_realmode_segment' was not declared. Should it be static?
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NAvi Kivity <avi@redhat.com>

Convert gfn_to_pfn to use get_user_pages_fast, which can do lockless
pagetable lookups on x86. Kernel compilation on 4-way guest is 3.7%
faster on VMX.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@redhat.com>

When an IRQ allocation fails, we free up the device structures and
disable the device so that we can unregister the device in the
userspace and not expose it to the guest at all.
Signed-off-by: NAmit Shah <amit.shah@redhat.com>
Signed-off-by: NAvi Kivity <avi@redhat.com>

Based on a patch by: Kay, Allen M <allen.m.kay@intel.com>

This patch enables PCI device assignment based on VT-d support.
When a device is assigned to the guest, the guest memory is pinned and
the mapping is updated in the VT-d IOMMU.

[Amit: Expose KVM_CAP_IOMMU so we can check if an IOMMU is present
and also control enable/disable from userspace]
Signed-off-by: NKay, Allen M <allen.m.kay@intel.com>
Signed-off-by: NWeidong Han <weidong.han@intel.com>
Signed-off-by: NBen-Ami Yassour <benami@il.ibm.com>
Signed-off-by: NAmit Shah <amit.shah@qumranet.com>
Acked-by: NMark Gross <mgross@linux.intel.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Since "KVM: x86: do not execute halted vcpus", HLT by vcpu0 before system
reset by the IO thread will hang the guest.

Mark vcpu as runnable in such case.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Offline or uninitialized vcpu's can be executed if requested to perform
userspace work.

Follow Avi's suggestion to handle halted vcpu's in the main loop,
simplifying kvm_emulate_halt(). Introduce a new vcpu->requests bit to
indicate events that promote state from halted to running.

Also standardize vcpu wake sites.

Signed-off-by: Marcelo Tosatti <mtosatti <at> redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

These can help show whether a guest is making progress or not.
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Currently KVM implements MC0-MC4_MISC read support. When booting Linux this
results in KVM warnings in the kernel log when the guest tries to read
MC5_MISC. Fix this warnings with this patch.
Signed-off-by: NJoerg Roedel <joerg.roedel@amd.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

There is no reason to share internal memory slots with fork()ed instances.
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Real mode segments to not reference the GDT or LDT; they simply compute
base = selector * 16.
Signed-off-by: NAvi Kivity <avi@qumranet.com>

sparse says:

arch/x86/kvm/x86.c:107:32: warning: symbol 'kvm_find_assigned_dev' was not declared. Should it be static?
arch/x86/kvm/i8254.c:225:6: warning: symbol 'kvm_pit_ack_irq' was not declared. Should it be static?
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

... instead of using the pic and ioapic variants
Signed-off-by: NAmit Shah <amit.shah@qumranet.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Even though we don't share irqs at the moment, we should ensure
regular user processes don't try to allocate system resources.

We check for capability to access IO devices (CAP_SYS_RAWIO) before
we request_irq on behalf of the guest.

Noticed by Avi.
Signed-off-by: NAmit Shah <amit.shah@qumranet.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

The vcpu thread can be preempted after the guest_debug_pre() callback,
resulting in invalid debug registers on the new vcpu.

Move it inside the non-preemptable section.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

[sheng: fix KVM_GET_LAPIC using wrong size]
Signed-off-by: NDave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: NSheng Yang <sheng.yang@intel.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

On my machine with gcc 3.4, kvm uses ~2k of stack in a few
select functions.  This is mostly because gcc fails to
notice that the different case: statements could have their
stack usage combined.  It overflows very nicely if interrupts
happen during one of these large uses.

This patch uses two methods for reducing stack usage.
1. dynamically allocate large objects instead of putting
   on the stack.
2. Use a union{} member for all of the case variables. This
   tricks gcc into combining them all into a single stack
   allocation. (There's also a comment on this)
Signed-off-by: NDave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Based on a patch from: Amit Shah <amit.shah@qumranet.com>

This patch adds support for handling PCI devices that are assigned to
the guest.

The device to be assigned to the guest is registered in the host kernel
and interrupt delivery is handled.  If a device is already assigned, or
the device driver for it is still loaded on the host, the device
assignment is failed by conveying a -EBUSY reply to the userspace.

Devices that share their interrupt line are not supported at the moment.

By itself, this patch will not make devices work within the guest.
The VT-d extension is required to enable the device to perform DMA.
Another alternative is PVDMA.
Signed-off-by: NAmit Shah <amit.shah@qumranet.com>
Signed-off-by: NBen-Ami Yassour <benami@il.ibm.com>
Signed-off-by: NWeidong Han <weidong.han@intel.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Netware writes to DEBUGCTL and reads from the DEBUGCTL and LAST*IP MSRs
without further checks and is really confused to receive a #GP during that.
To make it happy we should just make them stubs, which is exactly what SVM
already does.

Writes to DEBUGCTL that are vendor-specific are resembled to behave as if the
virtual CPU does not know them.
Signed-off-by: NAlexander Graf <agraf@suse.de>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

If we're emulating an instruction, either it will succeed, in which case
any previously queued exception will be spurious, or we will requeue the
same exception.
Signed-off-by: NAvi Kivity <avi@qumranet.com>

As suggested by Avi, introduce accessors to read/write guest registers.
This simplifies the ->cache_regs/->decache_regs interface, and improves
register caching which is important for VMX, where the cost of
vmcs_read/vmcs_write is significant.

[avi: fix warnings]
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Signed-off-by: NAvi Kivity <avi@qumranet.com>

This allows reading memslots with only the mmu_lock hold for mmu
notifiers that runs in atomic context and with mmu_lock held.
Signed-off-by: NAndrea Arcangeli <andrea@qumranet.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

This allows the mmu notifier code to run unalias_gfn with only the
mmu_lock held.  Only alias writes need the mmu_lock held. Readers will
either take the slots_lock in read mode or the mmu_lock.
Signed-off-by: NAndrea Arcangeli <andrea@qumranet.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

If 'g' is one then limit is 4kb granular.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

There is no guarantee that the old TSS descriptor in the GDT contains
the proper base address. This is the case for Windows installation's
reboot-via-triplefault.

Use guest registers instead. Also translate the address properly.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

The segment base is always a linear address, so translate before
accessing guest memory.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Flush the shadow mmu before removing regions to avoid stale entries.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Fixes compilation with CONFIG_VMI enabled.
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Signed-off-by: NAvi Kivity <avi@qumranet.com>

There is no need to grab slots_lock if the vapic_page will not
be touched.
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Instead of prefetching all segment bases before emulation, read them at the
last moment.  Since most of them are unneeded, we save some cycles on
Intel machines where this is a bit expensive.
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Emulation failure reports are useful, so allow more than one per the lifetime
of the module.
Signed-off-by: NAvi Kivity <avi@qumranet.com>

If we're not gonna do anything (case in which failure is already
reported), we do not need to even bother with calculating the linear rip.
Signed-off-by: NGlauber Costa <gcosta@redhat.com>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

This patch enables coalesced MMIO for x86 architecture.
It defines KVM_MMIO_PAGE_OFFSET and KVM_CAP_COALESCED_MMIO.
It enables the compilation of coalesced_mmio.c.
Signed-off-by: NLaurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Modify member in_range() of structure kvm_io_device to pass length and the type
of the I/O (write or read).

This modification allows to use kvm_io_device with coalesced MMIO.
Signed-off-by: NLaurent Vivier <Laurent.Vivier@bull.net>
Signed-off-by: NAvi Kivity <avi@qumranet.com>

Prefixes functions that will be exported with kvm_.
We also prefixed set_segment() even if it still static
to be coherent.
signed-off-by: NGuillaume Thouvenin <guillaume.thouvenin@ext.bull.net>
Signed-off-by: NLaurent Vivier <laurent.vivier@bull.net>
Signed-off-by: NAvi Kivity <avi@qumranet.com>