This patch fixes two corner cases in nested (L2) handling of TSC-related
issues:
1. Somewhat suprisingly, according to the Intel spec, if L1 allows WRMSR to
the TSC MSR without an exit, then this should set L1's TSC value itself - not
offset by vmcs12.TSC_OFFSET (like was wrongly done in the previous code).
2. Allow L1 to disable the TSC_OFFSETING control, and then correctly ignore
the vmcs12.TSC_OFFSET.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
KVM assumed in several places that reading the TSC MSR returns the value for
L1. This is incorrect, because when L2 is running, the correct TSC read exit
emulation is to return L2's value.
We therefore add a new x86_ops function, read_l1_tsc, to use in places that
specifically need to read the L1 TSC, NOT the TSC of the current level of
guest.
Note that one change, of one line in kvm_arch_vcpu_load, is made redundant
by a different patch sent by Zachary Amsden (and not yet applied):
kvm_arch_vcpu_load() should not read the guest TSC, and if it didn't, of
course we didn't have to change the call of kvm_get_msr() to read_l1_tsc().
[avi: moved callback to kvm_x86_ops tsc block]
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Acked-by: Zachary Amsdem <zamsden@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Use BUG_ON(x) rather than if(x) BUG();
The semantic patch that fixes this problem is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@ identifier x; @@
-if (x) BUG();
+BUG_ON(x);
@@ identifier x; @@
-if (!x) BUG();
+BUG_ON(!x);
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The vmexit tracepoints format the exit_reason to make it human-readable.
Since the exit_reason depends on the instruction set (vmx or svm),
formatting is handled with ftrace_print_symbols_seq() by referring to
the appropriate exit reason table.
However, the ftrace_print_symbols_seq() function is not meant to be used
directly in tracepoints since it does not export the formatting table
which userspace tools like trace-cmd and perf use to format traces.
In practice perf dies when formatting vmexit-related events and
trace-cmd falls back to printing the numeric value (with extra
formatting code in the kvm plugin to paper over this limitation). Other
userspace consumers of vmexit-related tracepoints would be in similar
trouble.
To avoid significant changes to the kvm_exit tracepoint, this patch
moves the vmx and svm exit reason tables into arch/x86/kvm/trace.h and
selects the right table with __print_symbolic() depending on the
instruction set. Note that __print_symbolic() is designed for exporting
the formatting table to userspace and allows trace-cmd and perf to work.
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The idea is from Avi:
| We could cache the result of a miss in an spte by using a reserved bit, and
| checking the page fault error code (or seeing if we get an ept violation or
| ept misconfiguration), so if we get repeated mmio on a page, we don't need to
| search the slot list/tree.
| (https://lkml.org/lkml/2011/2/22/221)
When the page fault is caused by mmio, we cache the info in the shadow page
table, and also set the reserved bits in the shadow page table, so if the mmio
is caused again, we can quickly identify it and emulate it directly
Searching mmio gfn in memslots is heavy since we need to walk all memeslots, it
can be reduced by this feature, and also avoid walking guest page table for
soft mmu.
[jan: fix operator precedence issue]
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The idea is from Avi:
| Maybe it's time to kill off bypass_guest_pf=1. It's not as effective as
| it used to be, since unsync pages always use shadow_trap_nonpresent_pte,
| and since we convert between the two nonpresent_ptes during sync and unsync.
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The nested VMX feature is supposed to fully emulate VMX for the guest. This
(theoretically) not only allows it to run its own guests, but also also
to further emulate VMX for its own guests, and allow arbitrarily deep nesting.
This patch fixes a bug (discovered by Kevin Tian) in handling a VMLAUNCH
by L2, which prevented deeper nesting.
Deeper nesting now works (I only actually tested L3), but is currently
*absurdly* slow, to the point of being unusable.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Small corrections of KVM (spelling, etc.) not directly related to nested VMX.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
If the "nested" module option is enabled, add the "VMX" CPU feature to the
list of CPU features KVM advertises with the KVM_GET_SUPPORTED_CPUID ioctl.
Qemu uses this ioctl, and intersects KVM's list with its own list of desired
cpu features (depending on the -cpu option given to qemu) to determine the
final list of features presented to the guest.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
In the unlikely case that L1 does not capture MSR_IA32_TSC, L0 needs to
emulate this MSR write by L2 by modifying vmcs02.tsc_offset. We also need to
set vmcs12.tsc_offset, for this change to survive the next nested entry (see
prepare_vmcs02()).
Additionally, we also need to modify vmx_adjust_tsc_offset: The semantics
of this function is that the TSC of all guests on this vcpu, L1 and possibly
several L2s, need to be adjusted. To do this, we need to adjust vmcs01's
tsc_offset (this offset will also apply to each L2s we enter). We can't set
vmcs01 now, so we have to remember this adjustment and apply it when we
later exit to L1.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
KVM's "Lazy FPU loading" means that sometimes L0 needs to set CR0.TS, even
if a guest didn't set it. Moreover, L0 must also trap CR0.TS changes and
NM exceptions, even if we have a guest hypervisor (L1) who didn't want these
traps. And of course, conversely: If L1 wanted to trap these events, we
must let it, even if L0 is not interested in them.
This patch fixes some existing KVM code (in update_exception_bitmap(),
vmx_fpu_activate(), vmx_fpu_deactivate()) to do the correct merging of L0's
and L1's needs. Note that handle_cr() was already fixed in the above patch,
and that new code in introduced in previous patches already handles CR0
correctly (see prepare_vmcs02(), prepare_vmcs12(), and nested_vmx_vmexit()).
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When L2 tries to modify CR0 or CR4 (with mov or clts), and modifies a bit
which L1 asked to shadow (via CR[04]_GUEST_HOST_MASK), we already do the right
thing: we let L1 handle the trap (see nested_vmx_exit_handled_cr() in a
previous patch).
When L2 modifies bits that L1 doesn't care about, we let it think (via
CR[04]_READ_SHADOW) that it did these modifications, while only changing
(in GUEST_CR[04]) the bits that L0 doesn't shadow.
This is needed for corect handling of CR0.TS for lazy FPU loading: L0 may
want to leave TS on, while pretending to allow the guest to change it.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch adds correct handling of IDT_VECTORING_INFO_FIELD for the nested
case.
When a guest exits while delivering an interrupt or exception, we get this
information in IDT_VECTORING_INFO_FIELD in the VMCS. When L2 exits to L1,
there's nothing we need to do, because L1 will see this field in vmcs12, and
handle it itself. However, when L2 exits and L0 handles the exit itself and
plans to return to L2, L0 must inject this event to L2.
In the normal non-nested case, the idt_vectoring_info case is discovered after
the exit, and the decision to inject (though not the injection itself) is made
at that point. However, in the nested case a decision of whether to return
to L2 or L1 also happens during the injection phase (see the previous
patches), so in the nested case we can only decide what to do about the
idt_vectoring_info right after the injection, i.e., in the beginning of
vmx_vcpu_run, which is the first time we know for sure if we're staying in
L2.
Therefore, when we exit L2 (is_guest_mode(vcpu)), we disable the regular
vmx_complete_interrupts() code which queues the idt_vectoring_info for
injection on next entry - because such injection would not be appropriate
if we will decide to exit to L1. Rather, we just save the idt_vectoring_info
and related fields in vmcs12 (which is a convenient place to save these
fields). On the next entry in vmx_vcpu_run (*after* the injection phase,
potentially exiting to L1 to inject an event requested by user space), if
we find ourselves in L1 we don't need to do anything with those values
we saved (as explained above). But if we find that we're in L2, or rather
*still* at L2 (it's not nested_run_pending, meaning that this is the first
round of L2 running after L1 having just launched it), we need to inject
the event saved in those fields - by writing the appropriate VMCS fields.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Similar to the previous patch, but concerning injection of exceptions rather
than external interrupts.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The code in this patch correctly emulates external-interrupt injection
while a nested guest L2 is running.
Because of this code's relative un-obviousness, I include here a longer-than-
usual justification for what it does - much longer than the code itself ;-)
To understand how to correctly emulate interrupt injection while L2 is
running, let's look first at what we need to emulate: How would things look
like if the extra L0 hypervisor layer is removed, and instead of L0 injecting
an interrupt, we had hardware delivering an interrupt?
Now we have L1 running on bare metal with a guest L2, and the hardware
generates an interrupt. Assuming that L1 set PIN_BASED_EXT_INTR_MASK to 1, and
VM_EXIT_ACK_INTR_ON_EXIT to 0 (we'll revisit these assumptions below), what
happens now is this: The processor exits from L2 to L1, with an external-
interrupt exit reason but without an interrupt vector. L1 runs, with
interrupts disabled, and it doesn't yet know what the interrupt was. Soon
after, it enables interrupts and only at that moment, it gets the interrupt
from the processor. when L1 is KVM, Linux handles this interrupt.
Now we need exactly the same thing to happen when that L1->L2 system runs
on top of L0, instead of real hardware. This is how we do this:
When L0 wants to inject an interrupt, it needs to exit from L2 to L1, with
external-interrupt exit reason (with an invalid interrupt vector), and run L1.
Just like in the bare metal case, it likely can't deliver the interrupt to
L1 now because L1 is running with interrupts disabled, in which case it turns
on the interrupt window when running L1 after the exit. L1 will soon enable
interrupts, and at that point L0 will gain control again and inject the
interrupt to L1.
Finally, there is an extra complication in the code: when nested_run_pending,
we cannot return to L1 now, and must launch L2. We need to remember the
interrupt we wanted to inject (and not clear it now), and do it on the
next exit.
The above explanation shows that the relative strangeness of the nested
interrupt injection code in this patch, and the extra interrupt-window
exit incurred, are in fact necessary for accurate emulation, and are not
just an unoptimized implementation.
Let's revisit now the two assumptions made above:
If L1 turns off PIN_BASED_EXT_INTR_MASK (no hypervisor that I know
does, by the way), things are simple: L0 may inject the interrupt directly
to the L2 guest - using the normal code path that injects to any guest.
We support this case in the code below.
If L1 turns on VM_EXIT_ACK_INTR_ON_EXIT, things look very different from the
description above: L1 expects to see an exit from L2 with the interrupt vector
already filled in the exit information, and does not expect to be interrupted
again with this interrupt. The current code does not (yet) support this case,
so we do not allow the VM_EXIT_ACK_INTR_ON_EXIT exit-control to be turned on
by L1.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch contains the logic of whether an L2 exit should be handled by L0
and then L2 should be resumed, or whether L1 should be run to handle this
exit (using the nested_vmx_vmexit() function of the previous patch).
The basic idea is to let L1 handle the exit only if it actually asked to
trap this sort of event. For example, when L2 exits on a change to CR0,
we check L1's CR0_GUEST_HOST_MASK to see if L1 expressed interest in any
bit which changed; If it did, we exit to L1. But if it didn't it means that
it is we (L0) that wished to trap this event, so we handle it ourselves.
The next two patches add additional logic of what to do when an interrupt or
exception is injected: Does L0 need to do it, should we exit to L1 to do it,
or should we resume L2 and keep the exception to be injected later.
We keep a new flag, "nested_run_pending", which can override the decision of
which should run next, L1 or L2. nested_run_pending=1 means that we *must* run
L2 next, not L1. This is necessary in particular when L1 did a VMLAUNCH of L2
and therefore expects L2 to be run (and perhaps be injected with an event it
specified, etc.). Nested_run_pending is especially intended to avoid switching
to L1 in the injection decision-point described above.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch adds a bunch of tests of the validity of the vmcs12 fields,
according to what the VMX spec and our implementation allows. If fields
we cannot (or don't want to) honor are discovered, an entry failure is
emulated.
According to the spec, there are two types of entry failures: If the problem
was in vmcs12's host state or control fields, the VMLAUNCH instruction simply
fails. But a problem is found in the guest state, the behavior is more
similar to that of an exit.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch implements nested_vmx_vmexit(), called when the nested L2 guest
exits and we want to run its L1 parent and let it handle this exit.
Note that this will not necessarily be called on every L2 exit. L0 may decide
to handle a particular exit on its own, without L1's involvement; In that
case, L0 will handle the exit, and resume running L2, without running L1 and
without calling nested_vmx_vmexit(). The logic for deciding whether to handle
a particular exit in L1 or in L0, i.e., whether to call nested_vmx_vmexit(),
will appear in a separate patch below.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Before nested VMX support, the exit handler for a guest executing a VMX
instruction (vmclear, vmlaunch, vmptrld, vmptrst, vmread, vmread, vmresume,
vmwrite, vmon, vmoff), was handle_vmx_insn(). This handler simply threw a #UD
exception. Now that all these exit reasons are properly handled (and emulate
the respective VMX instruction), nothing calls this dummy handler and it can
be removed.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Implement the VMLAUNCH and VMRESUME instructions, allowing a guest
hypervisor to run its own guests.
This patch does not include some of the necessary validity checks on
vmcs12 fields before the entry. These will appear in a separate patch
below.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch contains code to prepare the VMCS which can be used to actually
run the L2 guest, vmcs02. prepare_vmcs02 appropriately merges the information
in vmcs12 (the vmcs that L1 built for L2) and in vmcs01 (our desires for our
own guests).
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Move some of the control field setup to common functions. These functions will
also be needed for running L2 guests - L0's desires (expressed in these
functions) will be appropriately merged with L1's desires.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Move the setting of constant host-state fields (fields that do not change
throughout the life of the guest) from vmx_vcpu_setup to a new common function
vmx_set_constant_host_state(). This function will also be used to set the
host state when running L2 guests.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Implement the VMREAD and VMWRITE instructions. With these instructions, L1
can read and write to the VMCS it is holding. The values are read or written
to the fields of the vmcs12 structure introduced in a previous patch.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
VMX instructions specify success or failure by setting certain RFLAGS bits.
This patch contains common functions to do this, and they will be used in
the following patches which emulate the various VMX instructions.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
In this patch we add to vmcs12 (the VMCS that L1 keeps for L2) all the
standard VMCS fields.
Later patches will enable L1 to read and write these fields using VMREAD/
VMWRITE, and they will be used during a VMLAUNCH/VMRESUME in preparing vmcs02,
a hardware VMCS for running L2.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
We saw in a previous patch that L1 controls its L2 guest with a vcms12.
L0 needs to create a real VMCS for running L2. We call that "vmcs02".
A later patch will contain the code, prepare_vmcs02(), for filling the vmcs02
fields. This patch only contains code for allocating vmcs02.
In this version, prepare_vmcs02() sets *all* of vmcs02's fields each time we
enter from L1 to L2, so keeping just one vmcs02 for the vcpu is enough: It can
be reused even when L1 runs multiple L2 guests. However, in future versions
we'll probably want to add an optimization where vmcs02 fields that rarely
change will not be set each time. For that, we may want to keep around several
vmcs02s of L2 guests that have recently run, so that potentially we could run
these L2s again more quickly because less vmwrites to vmcs02 will be needed.
This patch adds to each vcpu a vmcs02 pool, vmx->nested.vmcs02_pool,
which remembers the vmcs02s last used to run up to VMCS02_POOL_SIZE L2s.
As explained above, in the current version we choose VMCS02_POOL_SIZE=1,
I.e., one vmcs02 is allocated (and loaded onto the processor), and it is
reused to enter any L2 guest. In the future, when prepare_vmcs02() is
optimized not to set all fields every time, VMCS02_POOL_SIZE should be
increased.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch includes a utility function for decoding pointer operands of VMX
instructions issued by L1 (a guest hypervisor)
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When the guest can use VMX instructions (when the "nested" module option is
on), it should also be able to read and write VMX MSRs, e.g., to query about
VMX capabilities. This patch adds this support.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
An implementation of VMX needs to define a VMCS structure. This structure
is kept in guest memory, but is opaque to the guest (who can only read or
write it with VMX instructions).
This patch starts to define the VMCS structure which our nested VMX
implementation will present to L1. We call it "vmcs12", as it is the VMCS
that L1 keeps for its L2 guest. We will add more content to this structure
in later patches.
This patch also adds the notion (as required by the VMX spec) of L1's "current
VMCS", and finally includes utility functions for mapping the guest-allocated
VMCSs in host memory.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch allows the guest to enable the VMXE bit in CR4, which is a
prerequisite to running VMXON.
Whether to allow setting the VMXE bit now depends on the architecture (svm
or vmx), so its checking has moved to kvm_x86_ops->set_cr4(). This function
now returns an int: If kvm_x86_ops->set_cr4() returns 1, __kvm_set_cr4()
will also return 1, and this will cause kvm_set_cr4() will throw a #GP.
Turning on the VMXE bit is allowed only when the nested VMX feature is
enabled, and turning it off is forbidden after a vmxon.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch allows a guest to use the VMXON and VMXOFF instructions, and
emulates them accordingly. Basically this amounts to checking some
prerequisites, and then remembering whether the guest has enabled or disabled
VMX operation.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch adds to kvm_intel a module option "nested". This option controls
whether the guest can use VMX instructions, i.e., whether we allow nested
virtualization. A similar, but separate, option already exists for the
SVM module.
This option currently defaults to 0, meaning that nested VMX must be
explicitly enabled by giving nested=1. When nested VMX matures, the default
should probably be changed to enable nested VMX by default - just like
nested SVM is currently enabled by default.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
In VMX, before we bring down a CPU we must VMCLEAR all VMCSs loaded on it
because (at least in theory) the processor might not have written all of its
content back to memory. Since a patch from June 26, 2008, this is done using
a per-cpu "vcpus_on_cpu" linked list of vcpus loaded on each CPU.
The problem is that with nested VMX, we no longer have the concept of a
vcpu being loaded on a cpu: A vcpu has multiple VMCSs (one for L1, a pool for
L2s), and each of those may be have been last loaded on a different cpu.
So instead of linking the vcpus, we link the VMCSs, using a new structure
loaded_vmcs. This structure contains the VMCS, and the information pertaining
to its loading on a specific cpu (namely, the cpu number, and whether it
was already launched on this cpu once). In nested we will also use the same
structure to hold L2 VMCSs, and vmx->loaded_vmcs is a pointer to the
currently active VMCS.
Signed-off-by: Nadav Har'El <nyh@il.ibm.com>
Acked-by: Acked-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
vmcs_readl() and friends are really short, but gcc thinks they are long because of
the out-of-line exception handlers. Mark them always_inline to clear the
misunderstanding.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
We clean up a failed VMREAD by clearing the output register. Do
it in the exception handler instead of unconditionally. This is
worthwhile since there are more than a hundred call sites.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Only decache guest CR3 value if vcpu->arch.cr3 is stale.
Fixes loadvm with live guest.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Tested-by: Markus Schade <markus.schade@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Since the emulator now checks segment limits and access rights, it
generates a lot more accesses to the vmcs segment fields. Undo some
of the performance hit by cacheing those fields in a read-only cache
(the entire cache is invalidated on any write, or on guest exit).
Signed-off-by: Avi Kivity <avi@redhat.com>
When doing a soft int, we need to bump eip before pushing it to
the stack. Otherwise we'll do the int a second time.
[apw@canonical.com: merged eip update as per Jan's recommendation.]
Signed-off-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
In case certain allocations fail, vmx_create_vcpu may return 0 as error
instead of a negative value encoded via ERR_PTR. This causes a NULL
pointer dereferencing later on in kvm_vm_ioctl_vcpu_create.
Reported-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
With TSC scaling in SVM the tsc-offset needs to be
calculated differently. This patch propagates this
calculation into the architecture specific modules so that
this complexity can be handled there.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch implements a call-back into the architecture code
to allow the propagation of changes to the virtual tsc_khz
of the vcpu.
On SVM it updates the tsc_ratio variable, on VMX it does
nothing.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch adds a callback into kvm_x86_ops so that svm and
vmx code can do intercept checks on emulated instructions.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Use vmx_set_nmi_mask() instead of open-coding management of
the hardware bit and the software hint (nmi_known_unmasked).
There's a slight change of behaviour when running without
hardware virtual NMI support - we now clear the NMI mask if
NMI delivery faulted in that case as well. This improves
emulation accuracy.
Signed-off-by: Avi Kivity <avi@redhat.com>
When we haven't injected an interrupt, we don't need to recover
the nmi blocking state (since the guest can't set it by itself).
This allows us to avoid a VMREAD later on.
Signed-off-by: Avi Kivity <avi@redhat.com>
We may read the cpl quite often in the same vmexit (instruction privilege
check, memory access checks for instruction and operands), so we gain
a bit if we cache the value.
Signed-off-by: Avi Kivity <avi@redhat.com>
In long mode, vm86 mode is disallowed, so we need not check for
it. Reading rflags.vm may require a VMREAD, so it is expensive.
Signed-off-by: Avi Kivity <avi@redhat.com>
Some rflags bits are owned by the host, not guest, so we need to use
kvm_get_rflags() to strip those bits away or kvm_set_rflags() to add them
back.
Signed-off-by: Avi Kivity <avi@redhat.com>
Commit 6440e5967bc broke old userspaces that do not set tss address
before entering vcpu. Unbreak it by setting tss address to a safe
value on the first vcpu entry. New userspaces should set tss address,
so print warning in case it doesn't.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Access to this page is mostly done through the regs member which holds
the address to this page. The exceptions are in vmx_vcpu_reset() and
kvm_free_lapic() and these both can easily be converted to using regs.
Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Avi Kivity <avi@redhat.com>
Currently vm86 task is initialized on each real mode entry and vcpu
reset. Initialization is done by zeroing TSS and updating relevant
fields. But since all vcpus are using the same TSS there is a race where
one vcpu may use TSS while other vcpu is initializing it, so the vcpu
that uses TSS will see wrong TSS content and will behave incorrectly.
Fix that by initializing TSS only once.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
When rmode.vm86 is active TR descriptor is updated with vm86 task values,
but selector is left intact. vmx_set_segment() makes sure that if TR
register is written into while vm86 is active the new values are saved
for use after vm86 is deactivated, but since selector is not updated on
vm86 activation/deactivation new value is lost. Fix this by writing new
selector into vmcs immediately.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The changelog of 104f226 said "adds the __noclone attribute",
but it was missing in its patch. I think it is still needed.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch fixes the logic used to detect whether BIOS has disabled VMX, for
the case where VMX is enabled only under SMX, but tboot is not active.
Signed-off-by: Joseph Cihula <joseph.cihula@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Instead of exchanging the guest and host rcx, have separate storage
for each. This allows us to avoid using the xchg instruction, which
is is a little slower than normal operations.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Change
push top-of-stack
pop guest-rcx
pop dummy
to
pop guest-rcx
which is the same thing, only simpler.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
On some CPUs, a ple_gap of 41 is simply insufficient to ever trigger
PLE exits, even with the minimalistic PLE test from kvm-unit-tests.
http://git.kernel.org/?p=virt/kvm/kvm-unit-tests.git;a=commitdiff;h=eda71b28fa122203e316483b35f37aaacd42f545
For example, the Xeon X5670 CPU needs a ple_gap of at least 48 in
order to get pause loop exits:
# modprobe kvm_intel ple_gap=47
# taskset 1 /usr/local/bin/qemu-system-x86_64 \
-device testdev,chardev=log -chardev stdio,id=log \
-kernel x86/vmexit.flat -append ple-round-robin -smp 2
VNC server running on `::1:5900'
enabling apic
enabling apic
ple-round-robin 58298446
# rmmod kvm_intel
# modprobe kvm_intel ple_gap=48
# taskset 1 /usr/local/bin/qemu-system-x86_64 \
-device testdev,chardev=log -chardev stdio,id=log \
-kernel x86/vmexit.flat -append ple-round-robin -smp 2
VNC server running on `::1:5900'
enabling apic
enabling apic
ple-round-robin 36616
Increase the ple_gap to 128 to be on the safe side.
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Zhai, Edwin <edwin.zhai@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
When emulating real mode, we fake some state:
- tr.base points to a fake vm86 tss
- segment registers are made to conform to vm86 restrictions
change vmx_get_segment() not to expose this fake state to userspace;
instead, return the original state.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When emulating real mode we play with tr hidden state, but leave
tr.selector alone. That works well, except for save/restore, since
loading TR writes it to the hidden state in vmx->rmode.
Fix by also saving and restoring the tr selector; this makes things
more consistent and allows migration to work during the early
boot stages of Windows XP.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Instead of syncing the guest cr3 every exit, which is expensince on vmx
with ept enabled, sync it only on demand.
[sheng: fix incorrect cr3 seen by Windows XP]
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
'error' is byte sized, so use a byte register constraint.
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When NX is enabled on the host but not on the guest, we use the entry/exit
msr load facility, which is slow. Optimize it to use entry/exit efer load,
which is ~1200 cycles faster.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
In case of a nested page fault or an intercepted #PF newer SVM
implementations provide a copy of the faulting instruction bytes
in the VMCB.
Use these bytes to feed the instruction emulator and avoid the costly
guest instruction fetch in this case.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
emulate_instruction had many callers, but only one used all
parameters. One parameter was unused, another one is now
hidden by a wrapper function (required for a future addition
anyway), so most callers use now a shorter parameter list.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
move the complete_insn_gp() helper function out of the VMX part
into the generic x86 part to make it usable by SVM.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The handling of CR8 writes in KVM is currently somewhat cumbersome.
This patch makes it look like the other CR register handlers
and fixes a possible issue in VMX, where the RIP would be incremented
despite an injected #GP.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
In certain use-cases, we want to allocate guests fixed time slices where idle
guest cycles leave the machine idling. There are many approaches to achieve
this but the most direct is to simply avoid trapping the HLT instruction which
lets the guest directly execute the instruction putting the processor to sleep.
Introduce this as a module-level option for kvm-vmx.ko since if you do this
for one guest, you probably want to do it for all.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
If we execute VMREAD during reboot we'll just skip over it. Instead of
returning garbage, return 0, which has a much smaller chance of confusing
the code. Otherwise we risk a flood of debug printk()s which block the
reboot process if a serial console or netconsole is enabled.
Signed-off-by: Avi Kivity <avi@redhat.com>
The exit reason alone is insufficient to understand exactly why an exit
occured; add ISA-specific trace parameters for additional information.
Because fetching these parameters is expensive on vmx, and because these
parameters are fetched even if tracing is disabled, we fetch the
parameters via a callback instead of as traditional trace arguments.
Signed-off-by: Avi Kivity <avi@redhat.com>
exit_reason's meaning depend on the instruction set; record it so a trace
taken on one machine can be interpreted on another.
Signed-off-by: Avi Kivity <avi@redhat.com>
cea15c2 ("KVM: Move KVM context switch into own function") split vmx_vcpu_run()
to prevent multiple copies of the context switch from being generated (causing
problems due to a label). This patch folds them back together again and adds
the __noclone attribute to prevent the label from being duplicated.
Signed-off-by: Avi Kivity <avi@redhat.com>
Inform user to either disable TXT in the BIOS or do TXT launch
with tboot before enabling KVM since some BIOSes do not set
FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX bit when TXT is enabled.
Signed-off-by: Shane Wang <shane.wang@intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
While not mandated by the spec, Linux relies on NMI being blocked by an
IF-enabling STI. VMX also refuses to enter a guest in this state, at
least on some implementations.
Disallow NMI while blocked by STI by checking for the condition, and
requesting an interrupt window exit if it occurs.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Currently the exit is unhandled, so guest halts with error if it tries
to execute INVD instruction. Call into emulator when INVD instruction
is executed by a guest instead. This instruction is not needed by ordinary
guests, but firmware (like OpenBIOS) use it and fail.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The EPT present/writable bits use the same position as normal
pagetable bits.
Since direct_map passes ACC_ALL to mmu_set_spte, thus always setting
the writable bit on sptes, use the generic PT_PRESENT shadow_base_pte.
Also pass present/writable error code information from EPT violation
to generic pagefault handler.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
gcc 4.5 with some special options is able to duplicate the VMX
context switch asm in vmx_vcpu_run(). This results in a compile error
because the inline asm sequence uses an on local label. The non local
label is needed because other code wants to set up the return address.
This patch moves the asm code into an own function and marks
that explicitely noinline to avoid this problem.
Better would be probably to just move it into an .S file.
The diff looks worse than the change really is, it's all just
code movement and no logic change.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
To support xsave properly for the guest the SVM module need
software support for it. As long as this is not present do
not report the xsave as supported feature in cpuid.
As a side-effect this patch moves the bit() helper function
into the x86.h file so that it can be used in svm.c too.
KVM-Stable-Tag.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
We now use load_gs_index() to load gs safely; unfortunately this also
changes MSR_KERNEL_GS_BASE, which we managed separately. This resulted
in confusion and breakage running 32-bit host userspace on a 64-bit kernel.
Fix by
- saving guest MSR_KERNEL_GS_BASE before we we reload the host's gs
- doing the host save/load unconditionally, instead of only when in guest
long mode
Things can be cleaned up further, but this is the minmal fix for now.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
If fs or gs refer to the ldt, they must be reloaded after the ldt. Reorder
the code to that effect.
Userspace code that uses the ldt with kvm is nonexistent, so this doesn't fix
a user-visible bug.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
By chance this caused no harm so far. We overwrite AX during switch
to/from guest context, so we must declare this.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
If an interrupt is pending, we need to stop emulation so we
can inject it.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Replace the inject-as-software-interrupt hack we currently have with
emulated injection.
Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Change the interrupt injection code to work from preemptible, interrupts
enabled context. This works by adding a ->cancel_injection() operation
that undoes an injection in case we were not able to actually enter the guest
(this condition could never happen with atomic injection).
Signed-off-by: Avi Kivity <avi@redhat.com>
Currently vmx_complete_interrupts() can decode event information from vmx
exit fields into the generic kvm event queues. Make it able to decode
the information from the entry fields as well by parametrizing it.
Signed-off-by: Avi Kivity <avi@redhat.com>
Nadav Har'El