Commit Graph

1738 Commits

Author SHA1 Message Date
Hillf Danton
cb16a7b387 KVM: MMU: fix counting of rmap entries in rmap_add()
It seems that rmap entries are under counted.

Signed-off-by: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:59 +02:00
Gleb Natapov
a0a07cd2c5 KVM: SVM: do not generate "external interrupt exit" if other exit is pending
Nested SVM checks for external interrupt after injecting nested exception.
In case there is external interrupt pending the code generates "external
interrupt exit" and overwrites previous exit info. If previously injected
exception already generated exit it will be lost.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Acked-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:56 +02:00
Avi Kivity
f4f5105087 KVM: Convert PIC lock from raw spinlock to ordinary spinlock
The PIC code used to be called from preempt_disable() context, which
wasn't very good for PREEMPT_RT.  That is no longer the case, so move
back from raw_spinlock_t to spinlock_t.

Signed-off-by: Avi Kivity <avi@redhat.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:56 +02:00
Zachary Amsden
28e4639adf KVM: x86: Fix kvmclock bug
If preempted after kvmclock values are updated, but before hardware
virtualization is entered, the last tsc time as read by the guest is
never set.  It underflows the next time kvmclock is updated if there
has not yet been a successful entry / exit into hardware virt.

Fix this by simply setting last_tsc to the newly read tsc value so
that any computed nsec advance of kvmclock is nulled.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:56 +02:00
Joerg Roedel
0959ffacf3 KVM: MMU: Don't track nested fault info in error-code
This patch moves the detection whether a page-fault was
nested or not out of the error code and moves it into a
separate variable in the fault struct.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:55 +02:00
Avi Kivity
625831a3f4 KVM: VMX: Move fixup_rmode_irq() to avoid forward declaration
No code changes.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:54 +02:00
Avi Kivity
b463a6f744 KVM: Non-atomic interrupt injection
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>
2010-10-24 10:52:54 +02:00
Avi Kivity
83422e17c1 KVM: VMX: Parameterize vmx_complete_interrupts() for both exit and entry
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>
2010-10-24 10:52:52 +02:00
Avi Kivity
537b37e267 KVM: VMX: Move real-mode interrupt injection fixup to vmx_complete_interrupts()
This allows reuse of vmx_complete_interrupts() for cancelling injections.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:51 +02:00
Avi Kivity
51aa01d13d KVM: VMX: Split up vmx_complete_interrupts()
vmx_complete_interrupts() does too much, split it up:
 - vmx_vcpu_run() gets the "cache important vmcs fields" part
 - a new vmx_complete_atomic_exit() gets the parts that must be done atomically
 - a new vmx_recover_nmi_blocking() does what its name says
 - vmx_complete_interrupts() retains the event injection recovery code

This helps in reducing the work done in atomic context.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:51 +02:00
Avi Kivity
3842d135ff KVM: Check for pending events before attempting injection
Instead of blindly attempting to inject an event before each guest entry,
check for a possible event first in vcpu->requests.  Sites that can trigger
event injection are modified to set KVM_REQ_EVENT:

- interrupt, nmi window opening
- ppr updates
- i8259 output changes
- local apic irr changes
- rflags updates
- gif flag set
- event set on exit

This improves non-injecting entry performance, and sets the stage for
non-atomic injection.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:50 +02:00
Avi Kivity
b0bc3ee2b5 KVM: MMU: Fix regression with ept memory types merged into non-ept page tables
Commit "KVM: MMU: Make tdp_enabled a mmu-context parameter" made real-mode
set ->direct_map, and changed the code that merges in the memory type depend
on direct_map instead of tdp_enabled.  However, in this case what really
matters is tdp, not direct_map, since tdp changes the pte format regardless
of whether the mapping is direct or not.

As a result, real-mode shadow mappings got corrupted with ept memory types.
The result was a huge slowdown, likely due to the cache being disabled.

Change it back as the simplest fix for the regression (real fix is to move
all that to vmx code, and not use tdp_enabled as a synonym for ept).

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:49 +02:00
Joerg Roedel
4c62a2dc92 KVM: X86: Report SVM bit to userspace only when supported
This patch fixes a bug in KVM where it _always_ reports the
support of the SVM feature to userspace. But KVM only
supports SVM on AMD hardware and only when it is enabled in
the kernel module. This patch fixes the wrong reporting.

Cc: stable@kernel.org
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:48 +02:00
Joerg Roedel
3d4aeaad8b KVM: SVM: Report Nested Paging support to userspace
This patch implements the reporting of the nested paging
feature support to userspace.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:47 +02:00
Joerg Roedel
55c5e464fc KVM: SVM: Expect two more candiates for exit_int_info
This patch adds INTR and NMI intercepts to the list of
expected intercepts with an exit_int_info set. While this
can't happen on bare metal it is architectural legal and may
happen with KVMs SVM emulation.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:46 +02:00
Joerg Roedel
4b16184c1c KVM: SVM: Initialize Nested Nested MMU context on VMRUN
This patch adds code to initialize the Nested Nested Paging
MMU context when the L1 guest executes a VMRUN instruction
and has nested paging enabled in its VMCB.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:46 +02:00
Joerg Roedel
5bd2edc341 KVM: SVM: Implement MMU helper functions for Nested Nested Paging
This patch adds the helper functions which will be used in
the mmu context for handling nested nested page faults.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:45 +02:00
Joerg Roedel
2d48a985c7 KVM: MMU: Track NX state in struct kvm_mmu
With Nested Paging emulation the NX state between the two
MMU contexts may differ. To make sure that always the right
fault error code is recorded this patch moves the NX state
into struct kvm_mmu so that the code can distinguish between
L1 and L2 NX state.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:44 +02:00
Joerg Roedel
81407ca553 KVM: MMU: Allow long mode shadows for legacy page tables
Currently the KVM softmmu implementation can not shadow a 32
bit legacy or PAE page table with a long mode page table.
This is a required feature for nested paging emulation
because the nested page table must alway be in host format.
So this patch implements the missing pieces to allow long
mode page tables for page table types.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:43 +02:00
Joerg Roedel
651dd37a9c KVM: MMU: Refactor mmu_alloc_roots function
This patch factors out the direct-mapping paths of the
mmu_alloc_roots function into a seperate function. This
makes it a lot easier to avoid all the unnecessary checks
done in the shadow path which may break when running direct.
In fact, this patch already fixes a problem when running PAE
guests on a PAE shadow page table.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:42 +02:00
Joerg Roedel
d41d1895eb KVM: MMU: Introduce kvm_pdptr_read_mmu
This function is implemented to load the pdptr pointers of
the currently running guest (l1 or l2 guest). Therefore it
takes care about the current paging mode and can read pdptrs
out of l2 guest physical memory.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:42 +02:00
Joerg Roedel
ff03a073e7 KVM: MMU: Add kvm_mmu parameter to load_pdptrs function
This function need to be able to load the pdptrs from any
mmu context currently in use. So change this function to
take an kvm_mmu parameter to fit these needs.
As a side effect this patch also moves the cached pdptrs
from vcpu_arch into the kvm_mmu struct.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:41 +02:00
Joerg Roedel
d47f00a62b KVM: X86: Propagate fetch faults
KVM currently ignores fetch faults in the instruction
emulator. With nested-npt we could have such faults. This
patch adds the code to handle these.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:41 +02:00
Joerg Roedel
d4f8cf664e KVM: MMU: Propagate the right fault back to the guest after gva_to_gpa
This patch implements logic to make sure that either a
page-fault/page-fault-vmexit or a nested-page-fault-vmexit
is propagated back to the guest.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:40 +02:00
Joerg Roedel
02f59dc9f1 KVM: MMU: Introduce init_kvm_nested_mmu()
This patch introduces the init_kvm_nested_mmu() function
which is used to re-initialize the nested mmu when the l2
guest changes its paging mode.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:39 +02:00
Joerg Roedel
3d06b8bfd4 KVM: MMU: Introduce kvm_read_nested_guest_page()
This patch introduces the kvm_read_guest_page_x86 function
which reads from the physical memory of the guest. If the
guest is running in guest-mode itself with nested paging
enabled it will read from the guest's guest physical memory
instead.
The patch also changes changes the code to use this function
where it is necessary.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:38 +02:00
Joerg Roedel
2329d46d21 KVM: MMU: Make walk_addr_generic capable for two-level walking
This patch uses kvm_read_guest_page_tdp to make the
walk_addr_generic functions suitable for two-level page
table walking.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:38 +02:00
Joerg Roedel
ec92fe44e7 KVM: X86: Add kvm_read_guest_page_mmu function
This patch adds a function which can read from the guests
physical memory or from the guest's guest physical memory.
This will be used in the two-dimensional page table walker.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:37 +02:00
Joerg Roedel
6539e738f6 KVM: MMU: Implement nested gva_to_gpa functions
This patch adds the functions to do a nested l2_gva to
l1_gpa page table walk.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:36 +02:00
Joerg Roedel
14dfe855f9 KVM: X86: Introduce pointer to mmu context used for gva_to_gpa
This patch introduces the walk_mmu pointer which points to
the mmu-context currently used for gva_to_gpa translations.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:35 +02:00
Joerg Roedel
c30a358d33 KVM: MMU: Add infrastructure for two-level page walker
This patch introduces a mmu-callback to translate gpa
addresses in the walk_addr code. This is later used to
translate l2_gpa addresses into l1_gpa addresses.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:34 +02:00
Joerg Roedel
1e301feb07 KVM: MMU: Introduce generic walk_addr function
This is the first patch in the series towards a generic
walk_addr implementation which could walk two-dimensional
page tables in the end. In this first step the walk_addr
function is renamed into walk_addr_generic which takes a
mmu context as an additional parameter.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:33 +02:00
Joerg Roedel
8df25a328a KVM: MMU: Track page fault data in struct vcpu
This patch introduces a struct with two new fields in
vcpu_arch for x86:

	* fault.address
	* fault.error_code

This will be used to correctly propagate page faults back
into the guest when we could have either an ordinary page
fault or a nested page fault. In the case of a nested page
fault the fault-address is different from the original
address that should be walked. So we need to keep track
about the real fault-address.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:33 +02:00
Joerg Roedel
3241f22da8 KVM: MMU: Let is_rsvd_bits_set take mmu context instead of vcpu
This patch changes is_rsvd_bits_set() function prototype to
take only a kvm_mmu context instead of a full vcpu.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:32 +02:00
Joerg Roedel
52fde8df7d KVM: MMU: Introduce kvm_init_shadow_mmu helper function
Some logic of the init_kvm_softmmu function is required to
build the Nested Nested Paging context. So factor the
required logic into a seperate function and export it.
Also make the whole init path suitable for more than one mmu
context.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:32 +02:00
Joerg Roedel
cb659db8a7 KVM: MMU: Introduce inject_page_fault function pointer
This patch introduces an inject_page_fault function pointer
into struct kvm_mmu which will be used to inject a page
fault. This will be used later when Nested Nested Paging is
implemented.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:31 +02:00
Joerg Roedel
5777ed340d KVM: MMU: Introduce get_cr3 function pointer
This function pointer in the MMU context is required to
implement Nested Nested Paging.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:31 +02:00
Joerg Roedel
1c97f0a04c KVM: X86: Introduce a tdp_set_cr3 function
This patch introduces a special set_tdp_cr3 function pointer
in kvm_x86_ops which is only used for tpd enabled mmu
contexts. This allows to remove some hacks from svm code.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:30 +02:00
Joerg Roedel
f43addd461 KVM: MMU: Make set_cr3 a function pointer in kvm_mmu
This is necessary to implement Nested Nested Paging. As a
side effect this allows some cleanups in the SVM nested
paging code.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:29 +02:00
Joerg Roedel
c5a78f2b64 KVM: MMU: Make tdp_enabled a mmu-context parameter
This patch changes the tdp_enabled flag from its global
meaning to the mmu-context and renames it to direct_map
there. This is necessary for Nested SVM with emulation of
Nested Paging where we need an extra MMU context to shadow
the Nested Nested Page Table.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:28 +02:00
Joerg Roedel
957446afce KVM: MMU: Check for root_level instead of long mode
The walk_addr function checks for !is_long_mode in its 64
bit version. But what is meant here is a check for pae
paging. Change the condition to really check for pae paging
so that it also works with nested nested paging.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:52:27 +02:00
Jes Sorensen
7b91409822 KVM: x86: Emulate MSR_EBC_FREQUENCY_ID
Some operating systems store data about the host processor at the
time of installation, and when booted on a more uptodate cpu tries
to read MSR_EBC_FREQUENCY_ID. This has been found with XP.

Signed-off-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:27 +02:00
Roedel, Joerg
b75f4eb341 KVM: SVM: Clean up rip handling in vmrun emulation
This patch changes the rip handling in the vmrun emulation
path from using next_rip to the generic kvm register access
functions.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:25 +02:00
Joerg Roedel
cda0008299 KVM: SVM: Restore correct registers after sel_cr0 intercept emulation
This patch implements restoring of the correct rip, rsp, and
rax after the svm emulation in KVM injected a selective_cr0
write intercept into the guest hypervisor. The problem was
that the vmexit is emulated in the instruction emulation
which later commits the registers right after the write-cr0
instruction. So the l1 guest will continue to run with the
l2 rip, rsp and rax resulting in unpredictable behavior.

This patch is not the final word, it is just an easy patch
to fix the issue. The real fix will be done when the
instruction emulator is made aware of nested virtualization.
Until this is done this patch fixes the issue and provides
an easy way to fix this in -stable too.

Cc: stable@kernel.org
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:24 +02:00
Joerg Roedel
f87f928882 KVM: MMU: Fix 32 bit legacy paging with NPT
This patch fixes 32 bit legacy paging with NPT enabled. The
mmu_check_root call on the top-level of the loop causes
root_gfn to take values (in the tdp_enabled path) which are
outside of guest memory. So the mmu_check_root call fails at
some point in the loop interation causing the guest to
tiple-fault.
This patch changes the mmu_check_root calls to the places
where they are really necessary. As a side-effect it
introduces a check for the root of a pae page table too.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:52:23 +02:00
Xiao Guangrong
30644b902c KVM: MMU: lower the aduit frequency
The audit is very high overhead, so we need lower the frequency to assure
the guest is running.

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:59 +02:00
Xiao Guangrong
eb2591865a KVM: MMU: improve spte audit
Both audit_mappings() and audit_sptes_have_rmaps() need to walk vcpu's page
table, so we can do these checking in a spte walking

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:58 +02:00
Xiao Guangrong
49edf87806 KVM: MMU: improve active sp audit
Both audit_rmap() and audit_write_protection() need to walk all active sp, so
we can do these checking in a sp walking

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:57 +02:00
Xiao Guangrong
2f4f337248 KVM: MMU: move audit to a separate file
Move the audit code from arch/x86/kvm/mmu.c to arch/x86/kvm/mmu_audit.c

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:57 +02:00
Xiao Guangrong
8b1fe17cc7 KVM: MMU: support disable/enable mmu audit dynamicly
Add a r/w module parameter named 'mmu_audit', it can control audit
enable/disable:

enable:
  echo 1 > /sys/module/kvm/parameters/mmu_audit

disable:
  echo 0 > /sys/module/kvm/parameters/mmu_audit

This patch not change the logic

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:56 +02:00
Jes Sorensen
84e0cefa8d KVM: Fix guest kernel crash on MSR_K7_CLK_CTL
MSR_K7_CLK_CTL is a no longer documented MSR, which is only relevant
on said old AMD CPU models. This change returns the expected value,
which the Linux kernel is expecting to avoid writing back the MSR,
plus it ignores all writes to the MSR.

Signed-off-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:55 +02:00
Avi Kivity
9ed049c3b6 KVM: i8259: Make ICW1 conform to spec
ICW is not a full reset, instead it resets a limited number of registers
in the PIC.  Change ICW1 emulation to only reset those registers.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:54 +02:00
Avi Kivity
7d9ddaedd8 KVM: x86 emulator: clean up control flow in x86_emulate_insn()
x86_emulate_insn() is full of things like

    if (rc != X86EMUL_CONTINUE)
        goto done;
    break;

consolidate all of those at the end of the switch statement.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:54 +02:00
Avi Kivity
a4d4a7c188 KVM: x86 emulator: fix group 11 decoding for reg != 0
These are all undefined.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:53 +02:00
Avi Kivity
b9eac5f4d1 KVM: x86 emulator: use single stage decoding for mov instructions
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:52 +02:00
Avi Kivity
e90aa41e6c KVM: Don't save/restore MSR_IA32_PERF_STATUS
It is read/only; restoring it only results in annoying messages.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:51 +02:00
Marcelo Tosatti
eaa48512ba KVM: SVM: init_vmcb should reset vcpu->efer
Otherwise EFER_LMA bit is retained across a SIPI reset.

Fixes guest cpu onlining.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:51 +02:00
Marcelo Tosatti
678041ad9d KVM: SVM: reset mmu context in init_vmcb
Since commit aad827034e no mmu reinitialization is performed
via init_vmcb.

Zero vcpu->arch.cr0 and pass the reset value as a parameter to
kvm_set_cr0.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:50 +02:00
Avi Kivity
c41a15dd46 KVM: Fix pio trace direction
out = write, in = read, not the other way round.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:49 +02:00
Xiao Guangrong
8e0e8afa82 KVM: MMU: remove count_rmaps()
Nothing is checked in count_rmaps(), so remove it

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:49 +02:00
Xiao Guangrong
365fb3fdf6 KVM: MMU: rewrite audit_mappings_page() function
There is a bugs in this function, we call gfn_to_pfn() and kvm_mmu_gva_to_gpa_read() in
atomic context(kvm_mmu_audit() is called under the spinlock(mmu_lock)'s protection).

This patch fix it by:
- introduce gfn_to_pfn_atomic instead of gfn_to_pfn
- get the mapping gfn from kvm_mmu_page_get_gfn()

And it adds 'notrap' ptes check in unsync/direct sps

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:48 +02:00
Xiao Guangrong
bc32ce2152 KVM: MMU: fix wrong not write protected sp report
The audit code reports some sp not write protected in current code, it's just the
bug in audit_write_protection(), since:

- the invalid sp not need write protected
- using uninitialize local variable('gfn')
- call kvm_mmu_audit() out of mmu_lock's protection

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:47 +02:00
Xiao Guangrong
0beb8d6604 KVM: MMU: check rmap for every spte
The read-only spte also has reverse mapping, so fix the code to check them,
also modify the function name to fit its doing

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:46 +02:00
Xiao Guangrong
9ad17b1001 KVM: MMU: fix compile warning in audit code
fix:

arch/x86/kvm/mmu.c: In function ‘kvm_mmu_unprotect_page’:
arch/x86/kvm/mmu.c:1741: warning: format ‘%lx’ expects type ‘long unsigned int’, but argument 3 has type ‘gfn_t’
arch/x86/kvm/mmu.c:1745: warning: format ‘%lx’ expects type ‘long unsigned int’, but argument 3 has type ‘gfn_t’
arch/x86/kvm/mmu.c: In function ‘mmu_unshadow’:
arch/x86/kvm/mmu.c:1761: warning: format ‘%lx’ expects type ‘long unsigned int’, but argument 3 has type ‘gfn_t’
arch/x86/kvm/mmu.c: In function ‘set_spte’:
arch/x86/kvm/mmu.c:2005: warning: format ‘%lx’ expects type ‘long unsigned int’, but argument 3 has type ‘gfn_t’
arch/x86/kvm/mmu.c: In function ‘mmu_set_spte’:
arch/x86/kvm/mmu.c:2033: warning: format ‘%lx’ expects type ‘long unsigned int’, but argument 7 has type ‘gfn_t’

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:46 +02:00
Jason Wang
23e7a7944f KVM: pit: Do not check pending pit timer in vcpu thread
Pit interrupt injection was done by workqueue, so no need to check
pending pit timer in vcpu thread which could lead unnecessary
unblocking of vcpu.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:45 +02:00
Avi Kivity
6230f7fc04 KVM: x86 emulator: simplify ALU opcode block decode further
The ALU opcode block is very regular; introduce D6ALU() to define decode
flags for 6 instructions at a time.

Suggested by Paolo Bonzini.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:43 +02:00
Avi Kivity
217fc9cfca KVM: Fix build error due to 64-bit division in nsec_to_cycles()
Use do_div() instead.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:43 +02:00
Avi Kivity
34d1f4905e KVM: x86 emulator: trap and propagate #DE from DIV and IDIV
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:42 +02:00
Avi Kivity
f6b3597bde KVM: x86 emulator: add macros for executing instructions that may trap
Like DIV and IDIV.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:41 +02:00
Avi Kivity
739ae40606 KVM: x86 emulator: simplify instruction decode flags for opcodes 0F 00-FF
Use the new byte/word dual opcode decode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:41 +02:00
Avi Kivity
d269e3961a KVM: x86 emulator: simplify instruction decode flags for opcodes E0-FF
Use the new byte/word dual opcode decode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:40 +02:00
Avi Kivity
d2c6c7adb1 KVM: x86 emulator: simplify instruction decode flags for opcodes C0-DF
Use the new byte/word dual opcode decode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:39 +02:00
Avi Kivity
50748613d1 KVM: x86 emulator: simplify instruction decode flags for opcodes A0-AF
Use the new byte/word dual opcode decode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:38 +02:00
Avi Kivity
76e8e68d44 KVM: x86 emulator: simplify instruction decode flags for opcodes 80-8F
Use the new byte/word dual opcode decode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:38 +02:00
Avi Kivity
48fe67b5f7 KVM: x86 emulator: simplify string instruction decode flags
Use the new byte/word dual opcode decode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:37 +02:00
Avi Kivity
5315fbb223 KVM: x86 emulator: simplify ALU block (opcodes 00-3F) decode flags
Use the new byte/word dual opcode decode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:36 +02:00
Avi Kivity
8d8f4e9f66 KVM: x86 emulator: support byte/word opcode pairs
Many x86 instructions come in byte and word variants distinguished with bit
0 of the opcode.  Add macros to aid in defining them.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:35 +02:00
Avi Kivity
081bca0e6b KVM: x86 emulator: refuse SrcMemFAddr (e.g. LDS) with register operand
SrcMemFAddr is not defined with the modrm operand designating a register
instead of a memory address.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:35 +02:00
Gleb Natapov
d2ddd1c483 KVM: x86 emulator: get rid of "restart" in emulation context.
x86_emulate_insn() will return 1 if instruction can be restarted
without re-entering a guest.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:34 +02:00
Gleb Natapov
3e2f65d57a KVM: x86 emulator: move string instruction completion check into separate function
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:33 +02:00
Gleb Natapov
6e2fb2cadd KVM: x86 emulator: Rename variable that shadows another local variable.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:32 +02:00
Wei Yongjun
cc4feed57f KVM: x86 emulator: add CALL FAR instruction emulation (opcode 9a)
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:31 +02:00
Xiao Guangrong
189be38db3 KVM: MMU: combine guest pte read between fetch and pte prefetch
Combine guest pte read between guest pte check in the fetch path and pte prefetch

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:28 +02:00
Xiao Guangrong
957ed9effd KVM: MMU: prefetch ptes when intercepted guest #PF
Support prefetch ptes when intercept guest #PF, avoid to #PF by later
access

If we meet any failure in the prefetch path, we will exit it and
not try other ptes to avoid become heavy path

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:27 +02:00
Zachary Amsden
1d5f066e0b KVM: x86: Fix a possible backwards warp of kvmclock
Kernel time, which advances in discrete steps may progress much slower
than TSC.  As a result, when kvmclock is adjusted to a new base, the
apparent time to the guest, which runs at a much higher, nsec scaled
rate based on the current TSC, may have already been observed to have
a larger value (kernel_ns + scaled tsc) than the value to which we are
setting it (kernel_ns + 0).

We must instead compute the clock as potentially observed by the guest
for kernel_ns to make sure it does not go backwards.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:24 +02:00
Zachary Amsden
ca84d1a24c KVM: x86: Add clock sync request to hardware enable
If there are active VCPUs which are marked as belonging to
a particular hardware CPU, request a clock sync for them when
enabling hardware; the TSC could be desynchronized on a newly
arriving CPU, and we need to recompute guests system time
relative to boot after a suspend event.

This covers both cases.

Note that it is acceptable to take the spinlock, as either
no other tasks will be running and no locks held (BSP after
resume), or other tasks will be guaranteed to drop the lock
relatively quickly (AP on CPU_STARTING).

Noting we now get clock synchronization requests for VCPUs
which are starting up (or restarting), it is tempting to
attempt to remove the arch/x86/kvm/x86.c CPU hot-notifiers
at this time, however it is not correct to do so; they are
required for systems with non-constant TSC as the frequency
may not be known immediately after the processor has started
until the cpufreq driver has had a chance to run and query
the chipset.

Updated: implement better locking semantics for hardware_enable

Removed the hack of dropping and retaking the lock by adding the
semantic that we always hold kvm_lock when hardware_enable is
called.  The one place that doesn't need to worry about it is
resume, as resuming a frozen CPU, the spinlock won't be taken.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:24 +02:00
Zachary Amsden
46543ba45f KVM: x86: Robust TSC compensation
Make the match of TSC find TSC writes that are close to each other
instead of perfectly identical; this allows the compensator to also
work in migration / suspend scenarios.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:23 +02:00
Zachary Amsden
759379dd68 KVM: x86: Add helper functions for time computation
Add a helper function to compute the kernel time and convert nanoseconds
back to CPU specific cycles.  Note that these must not be called in preemptible
context, as that would mean the kernel could enter software suspend state,
which would cause non-atomic operation.

Also, convert the KVM_SET_CLOCK / KVM_GET_CLOCK ioctls to use the kernel
time helper, these should be bootbased as well.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:23 +02:00
Zachary Amsden
48434c20e1 KVM: x86: Fix deep C-state TSC desynchronization
When CPUs with unstable TSCs enter deep C-state, TSC may stop
running.  This causes us to require resynchronization.  Since
we can't tell when this may potentially happen, we assume the
worst by forcing re-compensation for it at every point the VCPU
task is descheduled.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:23 +02:00
Zachary Amsden
e48672fa25 KVM: x86: Unify TSC logic
Move the TSC control logic from the vendor backends into x86.c
by adding adjust_tsc_offset to x86 ops.  Now all TSC decisions
can be done in one place.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:23 +02:00
Zachary Amsden
6755bae8e6 KVM: x86: Warn about unstable TSC
If creating an SMP guest with unstable host TSC, issue a warning

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:22 +02:00
Zachary Amsden
8cfdc00085 KVM: x86: Make cpu_tsc_khz updates use local CPU
This simplifies much of the init code; we can now simply always
call tsc_khz_changed, optionally passing it a new value, or letting
it figure out the existing value (while interrupts are disabled, and
thus, by inference from the rule, not raceful against CPU hotplug or
frequency updates, which will issue IPIs to the local CPU to perform
this very same task).

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:22 +02:00
Zachary Amsden
f38e098ff3 KVM: x86: TSC reset compensation
Attempt to synchronize TSCs which are reset to the same value.  In the
case of a reliable hardware TSC, we can just re-use the same offset, but
on non-reliable hardware, we can get closer by adjusting the offset to
match the elapsed time.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:22 +02:00
Zachary Amsden
99e3e30aee KVM: x86: Move TSC offset writes to common code
Also, ensure that the storing of the offset and the reading of the TSC
are never preempted by taking a spinlock.  While the lock is overkill
now, it is useful later in this patch series.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:22 +02:00
Zachary Amsden
f4e1b3c8bd KVM: x86: Convert TSC writes to TSC offset writes
Change svm / vmx to be the same internally and write TSC offset
instead of bare TSC in helper functions.  Isolated as a single
patch to contain code movement.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:22 +02:00
Zachary Amsden
ae38436b78 KVM: x86: Drop vm_init_tsc
This is used only by the VMX code, and is not done properly;
if the TSC is indeed backwards, it is out of sync, and will
need proper handling in the logic at each and every CPU change.
For now, drop this test during init as misguided.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:21 +02:00
Wei Yongjun
45bf21a8ce KVM: MMU: fix missing percpu counter destroy
commit ad05c88266b4cce1c820928ce8a0fb7690912ba1
(KVM: create aggregate kvm_total_used_mmu_pages value)
introduce percpu counter kvm_total_used_mmu_pages but never
destroy it, this may cause oops when rmmod & modprobe.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Acked-by: Tim Pepper <lnxninja@linux.vnet.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:21 +02:00
Xiaotian Feng
80b63faf02 KVM: MMU: fix regression from rework mmu_shrink() code
Latest kvm mmu_shrink code rework makes kernel changes kvm->arch.n_used_mmu_pages/
kvm->arch.n_max_mmu_pages at kvm_mmu_free_page/kvm_mmu_alloc_page, which is called
by kvm_mmu_commit_zap_page. So the kvm->arch.n_used_mmu_pages or
kvm_mmu_available_pages(vcpu->kvm) is unchanged after kvm_mmu_prepare_zap_page(),
This caused kvm_mmu_change_mmu_pages/__kvm_mmu_free_some_pages loops forever.
Moving kvm_mmu_commit_zap_page would make the while loop performs as normal.

Reported-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
Tested-by: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Tim Pepper <lnxninja@linux.vnet.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:21 +02:00
Wei Yongjun
e4abac67b7 KVM: x86 emulator: add JrCXZ instruction emulation
Add JrCXZ instruction emulation (opcode 0xe3)
Used by FreeBSD boot loader.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:20 +02:00
Wei Yongjun
09b5f4d3c4 KVM: x86 emulator: add LDS/LES/LFS/LGS/LSS instruction emulation
Add LDS/LES/LFS/LGS/LSS instruction emulation.
(opcode 0xc4, 0xc5, 0x0f 0xb2, 0x0f 0xb4~0xb5)

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:51:20 +02:00
Dave Hansen
45221ab668 KVM: create aggregate kvm_total_used_mmu_pages value
Of slab shrinkers, the VM code says:

 * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
 * querying the cache size, so a fastpath for that case is appropriate.

and it *means* it.  Look at how it calls the shrinkers:

    nr_before = (*shrinker->shrink)(0, gfp_mask);
    shrink_ret = (*shrinker->shrink)(this_scan, gfp_mask);

So, if you do anything stupid in your shrinker, the VM will doubly
punish you.

The mmu_shrink() function takes the global kvm_lock, then acquires
every VM's kvm->mmu_lock in sequence.  If we have 100 VMs, then
we're going to take 101 locks.  We do it twice, so each call takes
202 locks.  If we're under memory pressure, we can have each cpu
trying to do this.  It can get really hairy, and we've seen lock
spinning in mmu_shrink() be the dominant entry in profiles.

This is guaranteed to optimize at least half of those lock
aquisitions away.  It removes the need to take any of the locks
when simply trying to count objects.

A 'percpu_counter' can be a large object, but we only have one
of these for the entire system.  There are not any better
alternatives at the moment, especially ones that handle CPU
hotplug.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Tim Pepper <lnxninja@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:19 +02:00
Dave Hansen
49d5ca2663 KVM: replace x86 kvm n_free_mmu_pages with n_used_mmu_pages
Doing this makes the code much more readable.  That's
borne out by the fact that this patch removes code.  "used"
also happens to be the number that we need to return back to
the slab code when our shrinker gets called.  Keeping this
value as opposed to free makes the next patch simpler.

So, 'struct kvm' is kzalloc()'d.  'struct kvm_arch' is a
structure member (and not a pointer) of 'struct kvm'.  That
means they start out zeroed.  I _think_ they get initialized
properly by kvm_mmu_change_mmu_pages().  But, that only happens
via kvm ioctls.

Another benefit of storing 'used' intead of 'free' is
that the values are consistent from the moment the structure is
allocated: no negative "used" value.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Tim Pepper <lnxninja@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:18 +02:00
Dave Hansen
39de71ec53 KVM: rename x86 kvm->arch.n_alloc_mmu_pages
arch.n_alloc_mmu_pages is a poor choice of name. This value truly
means, "the number of pages which _may_ be allocated".  But,
reading the name, "n_alloc_mmu_pages" implies "the number of allocated
mmu pages", which is dead wrong.

It's really the high watermark, so let's give it a name to match:
nr_max_mmu_pages.  This change will make the next few patches
much more obvious and easy to read.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Tim Pepper <lnxninja@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:18 +02:00
Dave Hansen
e0df7b9f6c KVM: abstract kvm x86 mmu->n_free_mmu_pages
"free" is a poor name for this value.  In this context, it means,
"the number of mmu pages which this kvm instance should be able to
allocate."  But "free" implies much more that the objects are there
and ready for use.  "available" is a much better description, especially
when you see how it is calculated.

In this patch, we abstract its use into a function.  We'll soon
replace the function's contents by calculating the value in a
different way.

All of the reads of n_free_mmu_pages are taken care of in this
patch.  The modification sites will be handled in a patch
later in the series.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Tim Pepper <lnxninja@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:17 +02:00
Avi Kivity
6142914280 KVM: x86 emulator: implement CWD (opcode 99)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:16 +02:00
Avi Kivity
d46164dbd9 KVM: x86 emulator: implement IMUL REG, R/M, IMM (opcode 69)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:16 +02:00
Avi Kivity
7db41eb762 KVM: x86 emulator: add Src2Imm decoding
Needed for 3-operand IMUL.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:15 +02:00
Avi Kivity
39f21ee546 KVM: x86 emulator: consolidate immediate decode into a function
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:14 +02:00
Avi Kivity
48bb5d3c40 KVM: x86 emulator: implement RDTSC (opcode 0F 31)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:14 +02:00
Avi Kivity
7077aec0bc KVM: x86 emulator: remove SrcImplicit
Useless.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:13 +02:00
Avi Kivity
5c82aa2998 KVM: x86 emulator: implement IMUL REG, R/M (opcode 0F AF)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:12 +02:00
Avi Kivity
f3a1b9f496 KVM: x86 emulator: implement IMUL REG, R/M, imm8 (opcode 6B)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:12 +02:00
Avi Kivity
40ece7c729 KVM: x86 emulator: implement RET imm16 (opcode C2)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:12 +02:00
Avi Kivity
b250e60589 KVM: x86 emulator: add SrcImmU16 operand type
Used for RET NEAR instructions.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:12 +02:00
Avi Kivity
0ef753b8c3 KVM: x86 emulator: implement CALL FAR (FF /3)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:12 +02:00
Avi Kivity
7af04fc05c KVM: x86 emulator: implement DAS (opcode 2F)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:11 +02:00
Avi Kivity
fb2c264105 KVM: x86 emulator: Use a register for ____emulate_2op() destination
Most x86 two operand instructions allow the destination to be a memory operand,
but IMUL (for example) requires that the destination be a register.  Change
____emulate_2op() to take a register for both source and destination so we
can invoke IMUL.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:11 +02:00
Avi Kivity
b3b3d25a12 KVM: x86 emulator: pass destination type to ____emulate_2op()
We'll need it later so we can use a register for the destination.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:11 +02:00
Wei Yongjun
f2f3184534 KVM: x86 emulator: add LOOP/LOOPcc instruction emulation
Add LOOP/LOOPcc instruction emulation (opcode 0xe0~0xe2).

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:11 +02:00
Wei Yongjun
e8b6fa70e3 KVM: x86 emulator: add CBW/CWDE/CDQE instruction emulation
Add CBW/CWDE/CDQE instruction emulation.(opcode 0x98)
Used by FreeBSD's boot loader.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:11 +02:00
Avi Kivity
0fa6ccbd28 KVM: x86 emulator: fix REPZ/REPNZ termination condition
EFLAGS.ZF needs to be checked after each iteration, not before.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:10 +02:00
Avi Kivity
f6b33fc504 KVM: x86 emulator: implement SCAS (opcodes AE, AF)
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:10 +02:00
Avi Kivity
5c56e1cf7a KVM: x86 emulator: fix INTn emulation not pushing EFLAGS and CS
emulate_push() only schedules a push; it doesn't actually push anything.
Call writeback() to flush out the write.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:09 +02:00
Wei Yongjun
a13a63faa6 KVM: x86 emulator: remove dup code of in/out instruction
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:09 +02:00
Wei Yongjun
41167be544 KVM: x86 emulator: change OUT instruction to use dst instead of src
Change OUT instruction to use dst instead of src, so we can
reuse those code for all out instructions.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:09 +02:00
Wei Yongjun
943858e275 KVM: x86 emulator: introduce DstImmUByte for dst operand decode
Introduce DstImmUByte for dst operand decode, which
will be used for out instruction.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:09 +02:00
Wei Yongjun
c483c02ad3 KVM: x86 emulator: remove useless label from x86_emulate_insn()
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:09 +02:00
Wei Yongjun
ee45b58efe KVM: x86 emulator: add setcc instruction emulation
Add setcc instruction emulation (opcode 0x0f 0x90~0x9f)

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:08 +02:00
Wei Yongjun
92f738a52b KVM: x86 emulator: add XADD instruction emulation
Add XADD instruction emulation (opcode 0x0f 0xc0~0xc1)

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:06 +02:00
Wei Yongjun
31be40b398 KVM: x86 emulator: put register operand write back to a function
Introduce function write_register_operand() to write back the
register operand.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:06 +02:00
Mohammed Gamal
8ec4722dd2 KVM: Separate emulation context initialization in a separate function
The code for initializing the emulation context is duplicated at two
locations (emulate_instruction() and kvm_task_switch()). Separate it
in a separate function and call it from there.

Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:04 +02:00
Wei Yongjun
d9574a25af KVM: x86 emulator: add bsf/bsr instruction emulation
Add bsf/bsr instruction emulation (opcode 0x0f 0xbc~0xbd)

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:04 +02:00
Mohammed Gamal
8c5eee30a9 KVM: x86 emulator: Fix emulate_grp3 return values
This patch lets emulate_grp3() return X86EMUL_* return codes instead
of hardcoded ones.

Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:04 +02:00
Mohammed Gamal
3f9f53b0d5 KVM: x86 emulator: Add unary mul, imul, div, and idiv instructions
This adds unary mul, imul, div, and idiv instructions (group 3 r/m 4-7).

Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:04 +02:00
Wei Yongjun
ba7ff2b76d KVM: x86 emulator: mask group 8 instruction as BitOp
Mask group 8 instruction as BitOp, so we can share the
code for adjust the source operand.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:03 +02:00
Wei Yongjun
3885f18fe3 KVM: x86 emulator: do not adjust the address for immediate source
adjust the dst address for a register source but not adjust the
address for an immediate source.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:02 +02:00
Wei Yongjun
35c843c485 KVM: x86 emulator: fix negative bit offset BitOp instruction emulation
If bit offset operands is a negative number, BitOp instruction
will return wrong value. This patch fix it.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:01 +02:00
Mohammed Gamal
8744aa9aad KVM: x86 emulator: Add stc instruction (opcode 0xf9)
Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:01 +02:00
Wei Yongjun
c034da8b92 KVM: x86 emulator: using SrcOne for instruction d0/d1 decoding
Using SrcOne for instruction d0/d1 decoding.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:00 +02:00
Wei Yongjun
36089fed70 KVM: x86 emulator: disable writeback when decode dest operand
This patch change to disable writeback when decode dest
operand if the dest type is ImplicitOps or not specified.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:00 +02:00
Wei Yongjun
06cb704611 KVM: x86 emulator: use SrcAcc to simplify stos decoding
Use SrcAcc to simplify stos decoding.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:00 +02:00
Mohammed Gamal
6e154e56b4 KVM: x86 emulator: Add into, int, and int3 instructions (opcodes 0xcc-0xce)
This adds support for int instructions to the emulator.

Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:51:00 +02:00
Mohammed Gamal
160ce1f1a8 KVM: x86 emulator: Allow accessing IDT via emulator ops
The patch adds a new member get_idt() to x86_emulate_ops.
It also adds a function to get the idt in order to be used by the emulator.

This is needed for real mode interrupt injection and the emulation of int
instructions.

Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:59 +02:00
Wei Yongjun
d3ad624329 KVM: x86 emulator: simplify two-byte opcode check
Two-byte opcode always start with 0x0F and the decode flags
of opcode 0xF0 is always 0, so remove dup check.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:59 +02:00
Mohammed Gamal
34698d8c61 KVM: x86 emulator: Fix nop emulation
If a nop instruction is encountered, we jump directly to the done label.
This skip updating rip. Break from the switch case instead

Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:41 +02:00
Avi Kivity
2dbd0dd711 KVM: x86 emulator: Decode memory operands directly into a 'struct operand'
Since modrm operand can be either register or memory, decoding it into
a 'struct operand', which can represent both, is simpler.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:40 +02:00
Avi Kivity
1f6f05800e KVM: x86 emulator: change invlpg emulation to use src.mem.addr
Instead of using modrm_ea, which will soon be gone.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:39 +02:00
Avi Kivity
342fc63095 KVM: x86 emulator: switch LEA to use SrcMem decoding
The NoAccess flag will prevent memory from being accessed.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:38 +02:00
Avi Kivity
5a506b125f KVM: x86 emulator: add NoAccess flag for memory instructions that skip access
Use for INVLPG, which accesses the tlb, not memory.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:37 +02:00
Avi Kivity
b27f38563d KVM: x86 emulator: use struct operand for mov reg,dr and mov dr,reg for reg op
This is an ordinary modrm source or destination; use the standard structure
representing it.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:36 +02:00
Avi Kivity
1a0c7d44e4 KVM: x86 emulator: use struct operand for mov reg,cr and mov cr,reg for reg op
This is an ordinary modrm source or destination; use the standard structure
representing it.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:35 +02:00
Avi Kivity
cecc9e3916 KVM: x86 emulator: mark mov cr and mov dr as 64-bit instructions in long mode
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:35 +02:00
Avi Kivity
7f9b4b75be KVM: x86 emulator: introduce Op3264 for mov cr and mov dr instructions
The operands for these instructions are 32 bits or 64 bits, depending on
long mode, and ignoring REX prefixes, or the operand size prefix.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:35 +02:00
Avi Kivity
1e87e3efe7 KVM: x86 emulator: simplify REX.W check
(x && (x & y)) == (x & y)

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:34 +02:00
Avi Kivity
d4709c78ee KVM: x86 emulator: drop use_modrm_ea
Unused (and has never been).

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:34 +02:00
Avi Kivity
91ff3cb43c KVM: x86 emulator: put register operand fetch into a function
The code is repeated three times, put it into fetch_register_operand()

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:33 +02:00
Avi Kivity
3d9e77dff8 KVM: x86 emulator: use SrcAcc to simplify xchg decoding
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:33 +02:00
Avi Kivity
4515453964 KVM: x86 emulator: simplify xchg decode tables
Use X8() to avoid repetition.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:33 +02:00
Avi Kivity
1a6440aef6 KVM: x86 emulator: use correct type for memory address in operands
Currently we use a void pointer for memory addresses.  That's wrong since
these are guest virtual addresses which are not directly dereferencable by
the host.

Use the correct type, unsigned long.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:33 +02:00
Avi Kivity
09ee57cdae KVM: x86 emulator: push segment override out of decode_modrm()
Let it compute modrm_seg instead, and have the caller apply it.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:33 +02:00
Joerg Roedel
dbe7758482 KVM: SVM: Check for asid != 0 on nested vmrun
This patch lets a nested vmrun fail if the L1 hypervisor
left the asid zero. This fixes the asid_zero unit test.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:32 +02:00
Joerg Roedel
52c65a30a5 KVM: SVM: Check for nested vmrun intercept before emulating vmrun
This patch lets the nested vmrun fail if the L1 hypervisor
has not intercepted vmrun. This fixes the "vmrun intercept
check" unit test.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:32 +02:00
Xiao Guangrong
4132779b17 KVM: MMU: mark page dirty only when page is really written
Mark page dirty only when this page is really written, it's more exacter,
and also can fix dirty page marking in speculation path

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:32 +02:00
Xiao Guangrong
8672b7217a KVM: MMU: move bits lost judgement into a separate function
Introduce spte_has_volatile_bits() function to judge whether spte
bits will miss, it's more readable and can help us to cleanup code
later

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:31 +02:00
Xiao Guangrong
251464c464 KVM: MMU: using kvm_set_pfn_accessed() instead of mark_page_accessed()
It's a small cleanup that using using kvm_set_pfn_accessed() instead
of mark_page_accessed()

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:30 +02:00
Gleb Natapov
4fc40f076f KVM: x86 emulator: check io permissions only once for string pio
Do not recheck io permission on every iteration.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:29 +02:00
Avi Kivity
9928ff608b KVM: x86 emulator: fix LMSW able to clear cr0.pe
LMSW is documented not to be able to clear cr0.pe; make it so.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-10-24 10:50:28 +02:00
Gleb Natapov
e85d28f8e8 KVM: x86 emulator: don't update vcpu state if instruction is restarted
No need to update vcpu state since instruction is in the middle of the
emulation.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:27 +02:00
Avi Kivity
63540382cc KVM: x86 emulator: convert some push instructions to direct decode
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:26 +02:00
Avi Kivity
d0e533255d KVM: x86 emulator: allow repeat macro arguments to contain commas
Needed for repeating instructions with execution functions.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:25 +02:00
Avi Kivity
73fba5f4fe KVM: x86 emulator: move decode tables downwards
So they can reference execution functions.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:25 +02:00
Avi Kivity
dde7e6d12a KVM: x86 emulator: move x86_decode_insn() downwards
No code changes.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:24 +02:00
Avi Kivity
ef65c88912 KVM: x86 emulator: allow storing emulator execution function in decode tables
Instead of looking up the opcode twice (once for decode flags, once for
the big execution switch) look up both flags and function in the decode tables.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:22 +02:00
Avi Kivity
9aabc88fc8 KVM: x86 emulator: store x86_emulate_ops in emulation context
It doesn't ever change, so we don't need to pass it around everywhere.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:21 +02:00
Avi Kivity
ab85b12b1a KVM: x86 emulator: move ByteOp and Dst back to bits 0:3
Now that the group index no longer exists, the space is free.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:20 +02:00
Avi Kivity
3885d530b0 KVM: x86 emulator: drop support for old-style groups
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:19 +02:00
Avi Kivity
9f5d3220e3 KVM: x86 emulator: convert group 9 to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:18 +02:00
Avi Kivity
2cb20bc8af KVM: x86 emulator: convert group 8 to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:18 +02:00
Avi Kivity
2f3a9bc9eb KVM: x86 emulator: convert group 7 to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:16 +02:00
Avi Kivity
b67f9f0741 KVM: x86 emulator: convert group 5 to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:15 +02:00
Avi Kivity
591c9d20a3 KVM: x86 emulator: convert group 4 to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:14 +02:00
Avi Kivity
ee70ea30ee KVM: x86 emulator: convert group 3 to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:13 +02:00
Avi Kivity
99880c5cd5 KVM: x86 emulator: convert group 1A to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:12 +02:00
Avi Kivity
5b92b5faff KVM: x86 emulator: convert group 1 to new style
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:11 +02:00
Avi Kivity
120df8902d KVM: x86 emulator: allow specifying group directly in opcode
Instead of having a group number, store the group table pointer directly in
the opcode.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:10 +02:00
Avi Kivity
793d5a8d6b KVM: x86 emulator: reserve group code 0
We'll be using that to distinguish between new-style and old-style groups.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:09 +02:00
Avi Kivity
42a1c52095 KVM: x86 emulator: move group tables to top
No code changes.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:08 +02:00
Avi Kivity
fd853310a1 KVM: x86 emulator: Add wrappers for easily defining opcodes
Once 'struct opcode' grows, its initializer will become more complicated.
Wrap the simple initializers in a D() macro, and replace the empty initializers
with an even simpler N macro.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:08 +02:00
Avi Kivity
d65b1dee40 KVM: x86 emulator: introduce 'struct opcode'
This will hold all the information known about the opcode.  Currently, this
is just the decode flags.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:07 +02:00
Avi Kivity
ea9ef04e19 KVM: x86 emulator: drop parentheses in repreat macros
The parenthese make is impossible to use the macros with initializers that
require braces.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:06 +02:00
Mohammed Gamal
62bd430e6d KVM: x86 emulator: Add IRET instruction
Ths patch adds IRET instruction (opcode 0xcf).
Currently, only IRET in real mode is emulated. Protected mode support is to be added later if needed.

Signed-off-by: Mohammed Gamal <m.gamal005@gmail.com>
Reviewed-by: Avi Kivity <avi@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:05 +02:00
Joerg Roedel
7a190667bb KVM: SVM: Emulate next_rip svm feature
This patch implements the emulations of the svm next_rip
feature in the nested svm implementation in kvm.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:04 +02:00
Joerg Roedel
3f6a9d1693 KVM: SVM: Sync efer back into nested vmcb
This patch fixes a bug in a nested hypervisor that heavily
switches between real-mode and long-mode. The problem is
fixed by syncing back efer into the guest vmcb on emulated
vmexit.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:03 +02:00
Xiao Guangrong
19ada5c4b6 KVM: MMU: remove valueless output message
After commit 53383eaad08d, the '*spte' has updated before call
rmap_remove()(in most case it's 'shadow_trap_nonpresent_pte'), so
remove this information from error message

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:02 +02:00
Avi Kivity
d359192fea KVM: VMX: Use host_gdt variable wherever we need the host gdt
Now that we have the host gdt conveniently stored in a variable, make use
of it instead of querying the cpu.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:01 +02:00
Avi Kivity
e071edd5ba KVM: x86 emulator: unify the two Group 3 variants
Use just one group table for byte (F6) and word (F7) opcodes.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:50:00 +02:00
Avi Kivity
dfe11481d8 KVM: x86 emulator: Allow LOCK prefix for NEG and NOT
Opcodes F6/2, F6/3, F7/2, F7/3.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:59 +02:00
Avi Kivity
4968ec4e26 KVM: x86 emulator: simplify Group 1 decoding
Move operand decoding to the opcode table, keep lock decoding in the group
table.  This allows us to get consolidate the four variants of Group 1 into one
group.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:58 +02:00
Avi Kivity
52811d7de5 KVM: x86 emulator: mix decode bits from opcode and group decode tables
Allow bits that are common to all members of a group to be specified in the
opcode table instead of the group table.  This allows some simplification
of the decode tables.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:58 +02:00
Avi Kivity
047a481809 KVM: x86 emulator: add Undefined decode flag
Add a decode flag to indicate the instruction is invalid.  Will come in useful
later, when we mix decode bits from the opcode and group table.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:57 +02:00
Avi Kivity
2ce495365f KVM: x86 emulator: Make group storage bits separate from operand bits
Currently group bits are stored in bits 0:7, where operand bits are stored.

Make group bits be 0:3, and move the existing bits 0:3 to 16:19, so we can
mix group and operand bits.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:55 +02:00
Avi Kivity
880a188378 KVM: x86 emulator: consolidate Jcc rel32 decoding
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:55 +02:00
Avi Kivity
be8eacddbd KVM: x86 emulator: consolidate CMOVcc decoding
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:53 +02:00
Avi Kivity
b6e6153885 KVM: x86 emulator: consolidate MOV reg, imm decoding
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:52 +02:00
Avi Kivity
b3ab3405fe KVM: x86 emulator: consolidate Jcc rel8 decoding
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:51 +02:00
Avi Kivity
3849186c38 KVM: x86 emulator: consolidate push/pop reg decoding
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:49 +02:00
Avi Kivity
749358a6b4 KVM: x86 emulator: consolidate inc/dec reg decoding
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:48 +02:00
Avi Kivity
83babbca46 KVM: x86 emulator: add macros for repetitive instructions
Some instructions are repetitive in the opcode space, add macros for
consolidating them.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:48 +02:00
Avi Kivity
91269b8f94 KVM: x86 emulator: fix handling for unemulated instructions
If an instruction is present in the decode tables but not in the execution
switch, it will be emulated as a NOP.  An example is IRET (0xcf).

Fix by adding default: labels to the execution switches.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-24 10:49:47 +02:00
Linus Torvalds
d60a2793ba Merge branch 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Remove stale pmtimer_64.c
  x86, cleanups: Use clear_page/copy_page rather than memset/memcpy
  x86: Remove unnecessary #ifdef ACPI/X86_IO_ACPI
  x86, cleanup: Remove obsolete boot_cpu_id variable
2010-10-21 13:18:06 -07:00
Linus Torvalds
2f0384e5fc Merge branch 'x86-amd-nb-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-amd-nb-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, amd_nb: Enable GART support for AMD family 0x15 CPUs
  x86, amd: Use compute unit information to determine thread siblings
  x86, amd: Extract compute unit information for AMD CPUs
  x86, amd: Add support for CPUID topology extension of AMD CPUs
  x86, nmi: Support NMI watchdog on newer AMD CPU families
  x86, mtrr: Assume SYS_CFG[Tom2ForceMemTypeWB] exists on all future AMD CPUs
  x86, k8: Rename k8.[ch] to amd_nb.[ch] and CONFIG_K8_NB to CONFIG_AMD_NB
  x86, k8-gart: Decouple handling of garts and northbridges
  x86, cacheinfo: Fix dependency of AMD L3 CID
  x86, kvm: add new AMD SVM feature bits
  x86, cpu: Fix allowed CPUID bits for KVM guests
  x86, cpu: Update AMD CPUID feature bits
  x86, cpu: Fix renamed, not-yet-shipping AMD CPUID feature bit
  x86, AMD: Remove needless CPU family check (for L3 cache info)
  x86, tsc: Remove CPU frequency calibration on AMD
2010-10-21 13:01:08 -07:00
Avi Kivity
9581d442b9 KVM: Fix fs/gs reload oops with invalid ldt
kvm reloads the host's fs and gs blindly, however the underlying segment
descriptors may be invalid due to the user modifying the ldt after loading
them.

Fix by using the safe accessors (loadsegment() and load_gs_index()) instead
of home grown unsafe versions.

This is CVE-2010-3698.

KVM-Stable-Tag.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-19 14:21:45 -02:00
Zachary Amsden
47008cd887 KVM: x86: Move TSC reset out of vmcb_init
The VMCB is reset whenever we receive a startup IPI, so Linux is setting
TSC back to zero happens very late in the boot process and destabilizing
the TSC.  Instead, just set TSC to zero once at VCPU creation time.

Why the separate patch?  So git-bisect is your friend.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-11 12:36:07 +02:00
Zachary Amsden
58877679fd KVM: x86: Fix SVM VMCB reset
On reset, VMCB TSC should be set to zero.  Instead, code was setting
tsc_offset to zero, which passes through the underlying TSC.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-10-11 12:36:07 +02:00
H. Peter Anvin
86ffb08519 Merge remote branch 'origin/x86/cpu' into x86/amd-nb 2010-10-01 16:18:11 -07:00
Jan Beulich
234bb549ee x86, cleanups: Use clear_page/copy_page rather than memset/memcpy
When operating on whole pages, use clear_page() and copy_page() in
favor of memset() and memcpy(); after all that's what they are
intended for.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
LKML-Reference: <4C7FB8CA0200007800013F51@vpn.id2.novell.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-09-22 15:36:49 -07:00
Andre Przywara
6d886fd042 x86, cpu: Fix allowed CPUID bits for KVM guests
The AMD extensions to AVX (FMA4, XOP) work on the same YMM register set
as AVX, so they are safe for guests to use, as long as AVX itself
is allowed. Add F16C and AES on the way for the same reasons.

Signed-off-by: Andre Przywara <andre.przywara@amd.com>
LKML-Reference: <1283778860-26843-4-git-send-email-andre.przywara@amd.com>
Acked-by: Avi Kivity <avi@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-09-08 13:34:15 -07:00
Andre Przywara
7ef8aa72ab x86, cpu: Fix renamed, not-yet-shipping AMD CPUID feature bit
The AMD SSE5 feature set as-it has been replaced by some extensions
to the AVX instruction set. Thus the bit formerly advertised as SSE5
is re-used for one of these extensions (XOP).
Although this changes the /proc/cpuinfo output, it is not user visible, as
there are no CPUs (yet) having this feature.
To avoid confusion this should be added to the stable series, too.

Cc: stable@kernel.org [.32.x .34.x, .35.x]
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
LKML-Reference: <1283778860-26843-2-git-send-email-andre.przywara@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-09-08 13:32:55 -07:00
Gleb Natapov
eebb5f31b8 KVM: i8259: fix migration
Top of kvm_kpic_state structure should have the same memory layout as
kvm_pic_state since it is copied by memcpy.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-09-08 14:50:58 -03:00
Avi Kivity
ae0635b358 KVM: fix i8259 oops when no vcpus are online
If there are no vcpus, found will be NULL.  Check before doing anything with
it.

Signed-off-by: Avi Kivity <avi@redhat.com>
2010-09-08 14:50:56 -03:00
Avi Kivity
16518d5ada KVM: x86 emulator: fix regression with cmpxchg8b on i386 hosts
operand::val and operand::orig_val are 32-bit on i386, whereas cmpxchg8b
operands are 64-bit.

Fix by adding val64 and orig_val64 union members to struct operand, and
using them where needed.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-09-08 14:50:55 -03:00
Linus Torvalds
3dc8d7f07e Merge branch 'kvm-updates/2.6.36' of git://git.kernel.org/pub/scm/virt/kvm/kvm
* 'kvm-updates/2.6.36' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: PIT: free irq source id in handling error path
  KVM: destroy workqueue on kvm_create_pit() failures
  KVM: fix poison overwritten caused by using wrong xstate size
2010-08-22 11:27:36 -07:00
Xiao Guangrong
6b5d7a9f6f KVM: PIT: free irq source id in handling error path
Free irq source id if create pit workqueue fail

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-17 12:04:23 +03:00
Xiaotian Feng
3185bf8c23 KVM: destroy workqueue on kvm_create_pit() failures
kernel needs to destroy workqueue if kvm_create_pit() fails, otherwise
after pit is freed, the workqueue is leaked.

Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-15 14:17:35 +03:00
Xiaotian Feng
f45755b834 KVM: fix poison overwritten caused by using wrong xstate size
fpu.state is allocated from task_xstate_cachep, the size of task_xstate_cachep
is xstate_size. xstate_size is set from cpuid instruction, which is often
smaller than sizeof(struct xsave_struct). kvm is using sizeof(struct xsave_struct)
to fill in/out fpu.state.xsave, as what we allocated for fpu.state is
xstate_size, kernel will write out of memory and caused poison/redzone/padding
overwritten warnings.

Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
Reviewed-by: Sheng Yang <sheng@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Sheng Yang <sheng@linux.intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-15 14:10:15 +03:00
H. Peter Anvin
7645e43204 x86, kvm: Remove cast obsoleted by set_64bit() prototype cleanup
KVM ended up having to put a pretty ugly wrapper around set_64bit()
in order to get the type right.  Now set_64bit() takes the expected
u64 type, and this wrapper can be cleaned up.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Avi Kivity <avi@redhat.com>
LKML-Reference: <4C5C4E7A.8040603@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-08-06 13:07:19 -07:00
Linus Torvalds
d9a73c0016 Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  um, x86: Cast to (u64 *) inside set_64bit()
  x86-32, asm: Directly access per-cpu GDT
  x86-64, asm: Directly access per-cpu IST
  x86, asm: Merge cmpxchg_486_u64() and cmpxchg8b_emu()
  x86, asm: Move cmpxchg emulation code to arch/x86/lib
  x86, asm: Clean up and simplify <asm/cmpxchg.h>
  x86, asm: Clean up and simplify set_64bit()
  x86: Add memory modify constraints to xchg() and cmpxchg()
  x86-64: Simplify loading initial_gs
  x86: Use symbolic MSR names
  x86: Remove redundant K6 MSRs
2010-08-06 10:07:34 -07:00
Linus Torvalds
0f477dd085 Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Fix keeping track of AMD C1E
  x86, cpu: Package Level Thermal Control, Power Limit Notification definitions
  x86, cpu: Export AMD errata definitions
  x86, cpu: Use AMD errata checking framework for erratum 383
  x86, cpu: Clean up AMD erratum 400 workaround
  x86, cpu: AMD errata checking framework
  x86, cpu: Split addon_cpuid_features.c
  x86, cpu: Clean up formatting in cpufeature.h, remove override
  x86, cpu: Enumerate xsaveopt
  x86, cpu: Add xsaveopt cpufeature
  x86, cpu: Make init_scattered_cpuid_features() consider cpuid subleaves
  x86, cpu: Support the features flags in new CPUID leaf 7
  x86, cpu: Add CPU flags for F16C and RDRND
  x86: Look for IA32_ENERGY_PERF_BIAS support
  x86, AMD: Extend support to future families
  x86, cacheinfo: Carve out L3 cache slot accessors
  x86, xsave: Cleanup return codes in check_for_xstate()
2010-08-06 10:02:36 -07:00
Avi Kivity
3444d7da18 KVM: VMX: Fix host GDT.LIMIT corruption
vmx does not restore GDT.LIMIT to the host value, instead it sets it to 64KB.
This means host userspace can learn a few bits of host memory.

Fix by reloading GDTR when we load other host state.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 08:10:18 +03:00
Xiao Guangrong
9a3aad7057 KVM: MMU: using __xchg_spte more smarter
Sometimes, atomically set spte is not needed, this patch call __xchg_spte()
more smartly

Note: if the old mapping's access bit is already set, we no need atomic operation
since the access bit is not lost

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-02 06:41:01 +03:00
Xiao Guangrong
e4b502ead2 KVM: MMU: cleanup spte set and accssed/dirty tracking
Introduce set_spte_track_bits() to cleanup current code

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-02 06:41:00 +03:00
Xiao Guangrong
be233d49ea KVM: MMU: don't atomicly set spte if it's not present
If the old mapping is not present, the spte.a is not lost, so no need
atomic operation to set it

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-02 06:40:59 +03:00
Xiao Guangrong
9ed5520dd3 KVM: MMU: fix page dirty tracking lost while sync page
In sync-page path, if spte.writable is changed, it will lose page dirty
tracking, for example:

assume spte.writable = 0 in a unsync-page, when it's synced, it map spte
to writable(that is spte.writable = 1), later guest write spte.gfn, it means
spte.gfn is dirty, then guest changed this mapping to read-only, after it's
synced,  spte.writable = 0

So, when host release the spte, it detect spte.writable = 0 and not mark page
dirty

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-02 06:40:58 +03:00
Xiao Guangrong
daa3db693c KVM: MMU: fix broken page accessed tracking with ept enabled
In current code, if ept is enabled(shadow_accessed_mask = 0), the page
accessed tracking is lost.

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-02 06:40:57 +03:00
Xiao Guangrong
fa1de2bfc0 KVM: MMU: add missing reserved bits check in speculative path
In the speculative path, we should check guest pte's reserved bits just as
the real processor does

Reported-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-02 06:40:56 +03:00
Andrea Arcangeli
6e3e243c3b KVM: MMU: fix mmu notifier invalidate handler for huge spte
The index wasn't calculated correctly (off by one) for huge spte so KVM guest
was unstable with transparent hugepages.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2010-08-02 06:40:54 +03:00
Wei Yongjun
c19b8bd60e KVM: x86 emulator: fix xchg instruction emulation
If the destination is a memory operand and the memory cannot
map to a valid page, the xchg instruction emulation and locked
instruction will not work on io regions and stuck in endless
loop. We should emulate exchange as write to fix it.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Acked-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:53 +03:00
Gleb Natapov
9195c4da26 KVM: x86: Call mask notifiers from pic
If pit delivers interrupt while pic is masking it OS will never do EOI
and ack notifier will not be called so when pit will be unmasked no pit
interrupts will be delivered any more. Calling mask notifiers solves this
issue.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:52 +03:00
Gleb Natapov
68be080345 KVM: x86: never re-execute instruction with enabled tdp
With tdp enabled we should get into emulator only when emulating io, so
reexecution will always bring us back into emulator.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:51 +03:00
Gleb Natapov
c0e0608cb9 KVM: x86: emulator: inc/dec can have lock prefix
Mark inc (0xfe/0 0xff/0) and dec (0xfe/1 0xff/1) as lock prefix capable.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:49 +03:00
Avi Kivity
24157aaf83 KVM: MMU: Eliminate redundant temporaries in FNAME(fetch)
'level' and 'sptep' are aliases for 'interator.level' and 'iterator.sptep', no
need for them.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:48 +03:00
Avi Kivity
5991b33237 KVM: MMU: Validate all gptes during fetch, not just those used for new pages
Currently, when we fetch an spte, we only verify that gptes match those that
the walker saw if we build new shadow pages for them.

However, this misses the following race:

  vcpu1            vcpu2

  walk
                  change gpte
                  walk
                  instantiate sp

  fetch existing sp

Fix by validating every gpte, regardless of whether it is used for building
a new sp or not.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:47 +03:00
Avi Kivity
0b3c933302 KVM: MMU: Simplify spte fetch() function
Partition the function into three sections:

- fetching indirect shadow pages (host_level > guest_level)
- fetching direct shadow pages (page_level < host_level <= guest_level)
- the final spte (page_level == host_level)

Instead of the current spaghetti.

A slight change from the original code is that we call validate_direct_spte()
more often: previously we called it only for gw->level, now we also call it for
lower levels.  The change should have no effect.

[xiao: fix regression caused by validate_direct_spte() called too late]

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:45 +03:00
Avi Kivity
39c8c672a1 KVM: MMU: Add gpte_valid() helper
Move the code to check whether a gpte has changed since we fetched it into
a helper.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:44 +03:00
Avi Kivity
a357bd229c KVM: MMU: Add validate_direct_spte() helper
Add a helper to verify that a direct shadow page is valid wrt the required
access permissions; drop the page if it is not valid.

Reviewed-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:43 +03:00
Avi Kivity
a3aa51cfaa KVM: MMU: Add drop_large_spte() helper
To clarify spte fetching code, move large spte handling into a helper.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:42 +03:00
Avi Kivity
121eee97a7 KVM: MMU: Use __set_spte to link shadow pages
To avoid split accesses to 64 bit sptes on i386, use __set_spte() to link
shadow pages together.

(not technically required since shadow pages are __GFP_KERNEL, so upper 32
bits are always clear)

Reviewed-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:41 +03:00
Avi Kivity
32ef26a359 KVM: MMU: Add link_shadow_page() helper
To simplify the process of fetching an spte, add a helper that links
a shadow page to an spte.

Reviewed-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:40 +03:00
Avi Kivity
908e75f3e7 KVM: Expose MCE control MSRs to userspace
Userspace needs to reset and save/restore these MSRs.

The MCE banks are not exposed since their number varies from vcpu to vcpu.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:36 +03:00
Xiao Guangrong
aea924f606 KVM: PIT: stop vpit before freeing irq_routing
Fix:
general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
......
Call Trace:
 [<ffffffffa0159bd1>] ? kvm_set_irq+0xdd/0x24b [kvm]
 [<ffffffff8106ea8b>] ? trace_hardirqs_off_caller+0x1f/0x10e
 [<ffffffff813ad17f>] ? sub_preempt_count+0xe/0xb6
 [<ffffffff8106d273>] ? put_lock_stats+0xe/0x27
...
RIP  [<ffffffffa0159c72>] kvm_set_irq+0x17e/0x24b [kvm]

This bug is triggered when guest is shutdown, is because we freed
irq_routing before pit thread stopped

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-08-02 06:40:35 +03:00