n_requested_mmu_pages/n_free_mmu_pages are used by
kvm_mmu_change_mmu_pages to calculate the number of pages to zap.
alloc_mmu_pages, called from the vcpu initialization path, modifies this
variables without proper locking, which can result in a negative value
in kvm_mmu_change_mmu_pages (say, with cpu hotplug).
KVM: Reduce runnability interface with arch support code
Remove kvm_cpu_has_interrupt() and kvm_arch_interrupt_allowed() from
interface between general code and arch code. kvm_arch_vcpu_runnable()
checks for interrupts instead.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
ioeventfd is a mechanism to register PIO/MMIO regions to trigger an eventfd
signal when written to by a guest. Host userspace can register any
arbitrary IO address with a corresponding eventfd and then pass the eventfd
to a specific end-point of interest for handling.
Normal IO requires a blocking round-trip since the operation may cause
side-effects in the emulated model or may return data to the caller.
Therefore, an IO in KVM traps from the guest to the host, causes a VMX/SVM
"heavy-weight" exit back to userspace, and is ultimately serviced by qemu's
device model synchronously before returning control back to the vcpu.
However, there is a subclass of IO which acts purely as a trigger for
other IO (such as to kick off an out-of-band DMA request, etc). For these
patterns, the synchronous call is particularly expensive since we really
only want to simply get our notification transmitted asychronously and
return as quickly as possible. All the sychronous infrastructure to ensure
proper data-dependencies are met in the normal IO case are just unecessary
overhead for signalling. This adds additional computational load on the
system, as well as latency to the signalling path.
Therefore, we provide a mechanism for registration of an in-kernel trigger
point that allows the VCPU to only require a very brief, lightweight
exit just long enough to signal an eventfd. This also means that any
clients compatible with the eventfd interface (which includes userspace
and kernelspace equally well) can now register to be notified. The end
result should be a more flexible and higher performance notification API
for the backend KVM hypervisor and perhipheral components.
To test this theory, we built a test-harness called "doorbell". This
module has a function called "doorbell_ring()" which simply increments a
counter for each time the doorbell is signaled. It supports signalling
from either an eventfd, or an ioctl().
We then wired up two paths to the doorbell: One via QEMU via a registered
io region and through the doorbell ioctl(). The other is direct via
ioeventfd.
I didn't measure qemu-pio, because I have to figure out how to register a
PIO region with qemu's device model, and I got lazy. However, for now we
can extrapolate based on the data from the NULLIO runs of +2.56us for MMIO,
and -350ns for HC, we get:
Today kvm_io_bus_regsiter_dev() returns void and will internally BUG_ON
if it fails. We want to create dynamic MMIO/PIO entries driven from
userspace later in the series, so we need to enhance the code to be more
robust with the following changes:
1) Add a return value to the registration function
2) Fix up all the callsites to check the return code, handle any
failures, and percolate the error up to the caller.
3) Add an unregister function that collapses holes in the array
Signed-off-by: Gregory Haskins <ghaskins@novell.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Beth Kon [Tue, 7 Jul 2009 15:50:38 +0000 (11:50 -0400)]
KVM: PIT support for HPET legacy mode
When kvm is in hpet_legacy_mode, the hpet is providing the timer
interrupt and the pit should not be. So in legacy mode, the pit timer
is destroyed, but the *state* of the pit is maintained. So if kvm or
the guest tries to modify the state of the pit, this modification is
accepted, *except* that the timer isn't actually started. When we exit
hpet_legacy_mode, the current state of the pit (which is up to date
since we've been accepting modifications) is used to restart the pit
timer.
The saved_mode code in kvm_pit_load_count temporarily changes mode to
0xff in order to destroy the timer, but then restores the actual
value, again maintaining "current" state of the pit for possible later
reenablement.
[avi: add some reserved storage in the ioctl; make SET_PIT2 IOW]
[marcelo: fix memory corruption due to reserved storage]
Signed-off-by: Beth Kon <eak@us.ibm.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Thu, 2 Jul 2009 13:04:14 +0000 (15:04 +0200)]
KVM: fix MMIO_CONF_BASE MSR access
Some Windows versions check whether the BIOS has setup MMI/O for
config space accesses on AMD Fam10h CPUs, we say "no" by returning 0 on
reads and only allow disabling of MMI/O CfgSpace setup by igoring "0" writes.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
To my understanding, it became obsolete with the advent of the more
robust check in mmu_alloc_roots (89da4ff17f). Moreover, it prevents
the conceptually safe pattern
1. set sregs
2. register mem-slots
3. run vcpu
by setting a sticky triple fault during step 1.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Fri, 3 Jul 2009 14:00:14 +0000 (16:00 +0200)]
KVM: handle AMD microcode MSR
Windows 7 tries to update the CPU's microcode on some processors,
so we ignore the MSR write here. The patchlevel register is already handled
(returning 0), because the MSR number is the same as Intel's.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Wed, 24 Jun 2009 13:37:05 +0000 (15:37 +0200)]
KVM: Ignore PCI ECS I/O enablement
Linux guests will try to enable access to the extended PCI config space
via the I/O ports 0xCF8/0xCFC on AMD Fam10h CPU. Since we (currently?)
don't use ECS, simply ignore write and read attempts.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
This changes bus accesses to use high-level kvm_io_bus_read/kvm_io_bus_write
functions. in_range now becomes unused so it is removed from device ops in
favor of read/write callbacks performing range checks internally.
This allows aliasing (mostly for in-kernel virtio), as well as better error
handling by making it possible to pass errors up to userspace.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Use slots_lock to protect device list on the bus. slots_lock is already
taken for read everywhere, so we only need to take it for write when
registering devices. This is in preparation to removing in_range and
kvm->lock around it.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
switch pit creation to slots_lock. slots_lock is already taken for read
everywhere, so we only need to take it for write when creating pit.
This is in preparation to removing in_range and kvm->lock around it.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
switch coalesced mmio slots_lock. slots_lock is already taken for read
everywhere, so we only need to take it for write when changing zones.
This is in preparation to removing in_range and kvm->lock around it.
[avi: fix build]
Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Thu, 25 Jun 2009 10:36:49 +0000 (12:36 +0200)]
KVM: introduce module parameter for ignoring unknown MSRs accesses
KVM will inject a #GP into the guest if that tries to access unhandled
MSRs. This will crash many guests. Although it would be the correct
way to actually handle these MSRs, we introduce a runtime switchable
module param called "ignore_msrs" (defaults to 0). If this is Y, unknown
MSR reads will return 0, while MSR writes are simply dropped. In both cases
we print a message to dmesg to inform the user about that.
You can change the behaviour at any time by saying:
Andre Przywara [Wed, 24 Jun 2009 10:44:34 +0000 (12:44 +0200)]
KVM: ignore reads from AMDs C1E enabled MSR
If the Linux kernel detects an C1E capable AMD processor (K8 RevF and
higher), it will access a certain MSR on every attempt to go to halt.
Explicitly handle this read and return 0 to let KVM run a Linux guest
with the native AMD host CPU propagated to the guest.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Wed, 24 Jun 2009 10:44:33 +0000 (12:44 +0200)]
KVM: ignore AMDs HWCR register access to set the FFDIS bit
Linux tries to disable the flush filter on all AMD K8 CPUs. Since KVM
does not handle the needed MSR, the injected #GP will panic the Linux
kernel. Ignore setting of the HWCR.FFDIS bit in this MSR to let Linux
boot with an AMD K8 family guest CPU.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
s390 uses the values of the memslot instead of doing everything in the arch
ioctl handler of the KVM_SET_USER_MEMORY_REGION. Unfortunately we missed to
set the userspace_addr of our memslot due to our s390 ifdef in
__kvm_set_memory_region.
Old s390 userspace launchers did not notice, since they started the guest at
userspace address 0.
Because of CONFIG_DEFAULT_MMAP_MIN_ADDR we now put the guest at 1M userspace,
which does not work. This patch makes sure that new.userspace_addr is set
on s390.
This fix should go in quickly. Nevertheless, looking at the code we should
clean up that ifdef in the long term. Any kernel janitors?
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Thu, 18 Jun 2009 10:56:02 +0000 (12:56 +0200)]
KVM: x86 emulator: Add sysexit emulation
Handle #UD intercept of the sysexit instruction in 64bit mode returning to
32bit compat mode on an AMD host.
Setup the segment descriptors for CS and SS and the EIP/ESP registers
according to the manual.
Signed-off-by: Christoph Egger <christoph.egger@amd.com> Signed-off-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Thu, 18 Jun 2009 10:56:01 +0000 (12:56 +0200)]
KVM: x86 emulator: Add sysenter emulation
Handle #UD intercept of the sysenter instruction in 32bit compat mode on
an AMD host.
Setup the segment descriptors for CS and SS and the EIP/ESP registers
according to the manual.
Signed-off-by: Christoph Egger <christoph.egger@amd.com> Signed-off-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Thu, 18 Jun 2009 10:56:00 +0000 (12:56 +0200)]
KVM: x86 emulator: add syscall emulation
Handle #UD intercept of the syscall instruction in 32bit compat mode on
an Intel host.
Setup the segment descriptors for CS and SS and the EIP/ESP registers
according to the manual. Save the RIP and EFLAGS to the correct registers.
[avi: fix build on i386 due to missing R11]
Signed-off-by: Christoph Egger <christoph.egger@amd.com> Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Wed, 17 Jun 2009 13:50:33 +0000 (15:50 +0200)]
KVM: x86 emulator: Prepare for emulation of syscall instructions
Add the flags needed for syscall, sysenter and sysexit to the opcode table.
Catch (but for now ignore) the opcodes in the emulation switch/case.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Christoph Egger <christoph.egger@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Wed, 17 Jun 2009 13:50:32 +0000 (15:50 +0200)]
KVM: x86 emulator: Add missing EFLAGS bit definitions
Signed-off-by: Christoph Egger <christoph.egger@amd.com> Signed-off-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Wed, 17 Jun 2009 13:50:31 +0000 (15:50 +0200)]
KVM: Allow emulation of syscalls instructions on #UD
Add the opcodes for syscall, sysenter and sysexit to the list of instructions
handled by the undefined opcode handler.
Signed-off-by: Christoph Egger <christoph.egger@amd.com> Signed-off-by: Amit Shah <amit.shah@redhat.com> Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Jan Kiszka [Tue, 9 Jun 2009 13:37:03 +0000 (15:37 +0200)]
KVM: Drop useless atomic test from timer function
The current code tries to optimize the setting of
KVM_REQ_PENDING_TIMER but used atomic_inc_and_test - which always
returns true unless pending had the invalid value of -1 on entry. This
patch drops the test part preserving the original semantic but
expressing it less confusingly.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Jan Kiszka [Tue, 9 Jun 2009 13:37:01 +0000 (15:37 +0200)]
KVM: Fix racy event propagation in timer
Minor issue that likely had no practical relevance: the kvm timer
function so far incremented the pending counter and then may reset it
again to 1 in case reinjection was disabled. This opened a small racy
window with the corresponding VCPU loop that may have happened to run
on another (real) CPU and already consumed the value.
Fix it by skipping the incrementation in case pending is already > 0.
This opens a different race windows, but may only rarely cause lost
events in case we do not care about them anyway (!reinject).
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Gleb Natapov [Thu, 11 Jun 2009 08:06:51 +0000 (11:06 +0300)]
KVM: Optimize searching for highest IRR
Most of the time IRR is empty, so instead of scanning the whole IRR on
each VM entry keep a variable that tells us if IRR is not empty. IRR
will have to be scanned twice on each IRQ delivery, but this is much
more rare than VM entry.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Andre Przywara [Fri, 12 Jun 2009 20:01:29 +0000 (22:01 +0200)]
KVM: Move performance counter MSR access interception to generic x86 path
The performance counter MSRs are different for AMD and Intel CPUs and they
are chosen mainly by the CPUID vendor string. This patch catches writes to
all addresses (regardless of VMX/SVM path) and handles them in the generic
MSR handler routine. Writing a 0 into the event select register is something
we perfectly emulate ;-), so don't print out a warning to dmesg in this
case.
This fixes booting a 64bit Windows guest with an AMD CPUID on an Intel host.
Signed-off-by: Andre Przywara <andre.przywara@amd.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Marcelo Tosatti [Wed, 10 Jun 2009 15:27:07 +0000 (12:27 -0300)]
KVM: MMU audit: audit_mappings tweaks
- Fail early in case gfn_to_pfn returns is_error_pfn.
- For the pre pte write case, avoid spurious "gva is valid but spte is notrap"
messages (the emulation code does the guest write first, so this particular
case is OK).
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Gleb Natapov [Tue, 9 Jun 2009 12:56:28 +0000 (15:56 +0300)]
KVM: Break dependency between vcpu index in vcpus array and vcpu_id.
Archs are free to use vcpu_id as they see fit. For x86 it is used as
vcpu's apic id. New ioctl is added to configure boot vcpu id that was
assumed to be 0 till now.
Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Nitin A Kamble [Mon, 8 Jun 2009 18:34:16 +0000 (11:34 -0700)]
KVM: VMX: Support Unrestricted Guest feature
"Unrestricted Guest" feature is added in the VMX specification.
Intel Westmere and onwards processors will support this feature.
It allows kvm guests to run real mode and unpaged mode
code natively in the VMX mode when EPT is turned on. With the
unrestricted guest there is no need to emulate the guest real mode code
in the vm86 container or in the emulator. Also the guest big real mode
code works like native.
The attached patch enhances KVM to use the unrestricted guest feature
if available on the processor. It also adds a new kernel/module
parameter to disable the unrestricted guest feature at the boot time.
Signed-off-by: Nitin A Kamble <nitin.a.kamble@intel.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Marcelo Tosatti [Thu, 4 Jun 2009 18:08:24 +0000 (15:08 -0300)]
KVM: switch irq injection/acking data structures to irq_lock
Protect irq injection/acking data structures with a separate irq_lock
mutex. This fixes the following deadlock:
CPU A CPU B
kvm_vm_ioctl_deassign_dev_irq()
mutex_lock(&kvm->lock); worker_thread()
-> kvm_deassign_irq() -> kvm_assigned_dev_interrupt_work_handler()
-> deassign_host_irq() mutex_lock(&kvm->lock);
-> cancel_work_sync() [blocked]
[gleb: fix ia64 path]
Reported-by: Alex Williamson <alex.williamson@hp.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Avi Kivity [Thu, 4 Jun 2009 15:09:08 +0000 (18:09 +0300)]
KVM: Calculate available entries in coalesced mmio ring
Instead of checking whether we'll wrap around, calculate how many entries
are available, and check whether we have enough (just one) for the pending
mmio.
By itself, this doesn't change anything, but it paves the way for making
this function lockless.
Avi Kivity [Sun, 31 May 2009 15:41:29 +0000 (18:41 +0300)]
KVM: VMX: Simplify pdptr and cr3 management
Instead of reading the PDPTRs from memory after every exit (which is slow
and wrong, as the PDPTRs are stored on the cpu), sync the PDPTRs from
memory to the VMCS before entry, and from the VMCS to memory after exit.
Do the same for cr3.
projects / linux-beck.git / log