When exception payloads are enabled by userspace (which is not yet
possible) and a #DB is raised in L2, defer the setting of DR6 until
later. Under VMX, this allows the L1 hypervisor to intercept the fault
before DR6 is modified. Under SVM, DR6 is modified before L1 can
intercept the fault (as has always been the case with DR7).
Note that the payload associated with a #DB exception includes only
the "new DR6 bits." When the payload is delievered, DR6.B0-B3 will be
cleared and DR6.RTM will be set prior to merging in the new DR6 bits.
Also note that bit 16 in the "new DR6 bits" is set to indicate that a
debug exception (#DB) or a breakpoint exception (#BP) occurred inside
an RTM region while advanced debugging of RTM transactional regions
was enabled. Though the reverse of DR6.RTM, this makes the #DB payload
field compatible with both the pending debug exceptions field under
VMX and the exit qualification for #DB exceptions under VMX.
Reported-by: Jim Mattson <jmattson@google.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When exception payloads are enabled by userspace (which is not yet
possible) and a #PF is raised in L2, defer the setting of CR2 until
the #PF is delivered. This allows the L1 hypervisor to intercept the
fault before CR2 is modified.
For backwards compatibility, when exception payloads are not enabled
by userspace, kvm_multiple_exception modifies CR2 when the #PF
exception is raised.
Reported-by: Jim Mattson <jmattson@google.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_multiple_exception now takes two additional operands: has_payload
and payload, so that updates to CR2 (and DR6 under VMX) can be delayed
until the exception is delivered. This is necessary to properly
emulate VMX or SVM hardware behavior for nested virtualization.
The new behavior is triggered by
vcpu->kvm->arch.exception_payload_enabled, which will (later) be set
by a new per-VM capability, KVM_CAP_EXCEPTION_PAYLOAD.
Reported-by: Jim Mattson <jmattson@google.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The per-VM capability KVM_CAP_EXCEPTION_PAYLOAD (to be introduced in a
later commit) adds the following fields to struct kvm_vcpu_events:
exception_has_payload, exception_payload, and exception.pending.
With this capability set, all of the details of vcpu->arch.exception,
including the payload for a pending exception, are reported to
userspace in response to KVM_GET_VCPU_EVENTS.
With this capability clear, the original ABI is preserved, and the
exception.injected field is set for either pending or injected
exceptions.
When userspace calls KVM_SET_VCPU_EVENTS with
KVM_CAP_EXCEPTION_PAYLOAD clear, exception.injected is no longer
translated to exception.pending. KVM_SET_VCPU_EVENTS can now only
establish a pending exception when KVM_CAP_EXCEPTION_PAYLOAD is set.
Reported-by: Jim Mattson <jmattson@google.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch adds the necessary code to patch a running kernel at runtime
to improve performance.
The current implementation offers a few optimizations variants:
- When running a SMP kernel on a single UP processor, unwanted assembler
statements like locking functions are overwritten with NOPs. When
multiple instructions shall be skipped, one branch instruction is used
instead of multiple nop instructions.
- In the UP case, some pdtlb and pitlb instructions are patched to
become pdtlb,l and pitlb,l which only flushes the CPU-local tlb
entries instead of broadcasting the flush to other CPUs in the system
and thus may improve performance.
- fic and fdc instructions are skipped if no I- or D-caches are
installed. This should speed up qemu emulation and cacheless systems.
- If no cache coherence is needed for IO operations, the relevant fdc
and sync instructions in the sba and ccio drivers are replaced by
nops.
- On systems which share I- and D-TLBs and thus don't have a seperate
instruction TLB, the pitlb instruction is replaced by a nop.
Live-patching is done early in the boot process, just after having run
the system inventory. No drivers are running and thus no external
interrupts should arrive. So the hope is that no TLB exceptions will
occur during the patching. If this turns out to be wrong we will
probably need to do the patching in real-mode.
Signed-off-by: Helge Deller <deller@gmx.de>
Helge writes:
"parisc fix:
Fix an unitialized variable usage in the parisc unwind code."
* 'parisc-4.19-3' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux:
parisc: Fix uninitialized variable usage in unwind.c
Booting an i486 with "no387 nofxsr" ends with with the following crash:
math_emulate: 0060:c101987d
Kernel panic - not syncing: Math emulation needed in kernel
on the first context switch in user land.
The reason is that copy_fpregs_to_fpstate() tries FNSAVE which does not work
as the FPU is turned off.
This bug was introduced in:
f1c8cd0176 ("x86/fpu: Change fpu->fpregs_active users to fpu->fpstate_active")
Add a check for X86_FEATURE_FPU before trying to save FPU registers (we
have such a check in switch_fpu_finish() already).
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Fixes: f1c8cd0176 ("x86/fpu: Change fpu->fpregs_active users to fpu->fpstate_active")
Link: http://lkml.kernel.org/r/20181016202525.29437-4-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Change the parisc vmlinuz boot code to include and process the real
compressed vmlinux.gz ELF file instead of a compressed memory dump.
This brings parisc in sync on how it's done on x86_64.
The benefit of this change is that, e.g. for debugging purposes, one can
then extract the vmlinux file out of the vmlinuz which was booted which
wasn't possible before. This can be archieved with the existing
scripts/extract-vmlinux script, which just needs a small tweak to prefer
to extract a compressed file before trying the existing given binary.
The downside of this approach is that due to the extra round of
decompression/ELF processing we need more physical memory installed to
be able to boot a kernel.
Signed-off-by: Helge Deller <deller@gmx.de>
In the C-code we need to put the physical address of the hpmc handler in
the interrupt vector table (IVA) in order to get HPMCs working. Since
on parisc64 function pointers are indirect (in fact they are function
descriptors) we instead export the address as variable and not as
function.
This reverts a small part of commit f39cce654f ("parisc: Add
cfi_startproc and cfi_endproc to assembly code").
Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org> [4.9+]
Fix a long-existing small nasty bug in the map_pages() implementation which
leads to overwriting already written pte entries with zero, *if* map_pages() is
called a second time with an end address which isn't aligned on a pmd boundry.
This happens for example if we want to remap only the text segment read/write
in order to run alternative patching on the code. Exiting the loop when we
reach the end address fixes this.
Cc: stable@vger.kernel.org
Signed-off-by: Helge Deller <deller@gmx.de>
This patch may resolve some races in TLB handling. Hopefully, TLB
inserts are accesses and protected by spin lock.
If not, we may need to IPI calls and do local purges on PA 2.0.
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
This patch updates the spin unlock code to use an ordered store with
release semanatics. All prior accesses are guaranteed to be performed
before an ordered store is performed.
Using an ordered store is significantly faster than using the sync
memory barrier.
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
On kernel crash, this is the current output:
Kernel Fault: Code=26 (Data memory access rights trap) regs=(ptrval) (Addr=00000004)
Drop the address of regs, it's of no use for debugging, and show the
faulty address without parenthesis.
Signed-off-by: Helge Deller <deller@gmx.de>
This change removes the PTE load and present check from the L2_ptep
macro. The load and check for kernel pages is now done in the tlb_lock
macro. This avoids a double load and check for user pages. The load
and check for user pages is now done inside the lock so the fault
handler can't be called while the entry is being updated. This version
uses an ordered store to release the lock when the page table entry
isn't present. It also corrects the check in the non SMP case.
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
On boot (mostly reboot), my c8000 sometimes crashes after it prints the
TLB flush threshold. The lockup is hard. The front LED flashes red and
the box must be unplugged to reset the error.
I noticed that when the crash occurs the TLB flush threshold is about
one quarter what it is on a successful boot. If I disabled the
calculation, the crash didn't occur. There also seemed to be a timing
dependency affecting the crash. I finally realized that the
flush_tlb_all() timing test runs just after the secondary CPUs are
started. There seems to be a problem with running flush_tlb_all() too
soon after the CPUs are started.
The timing for the range test always seemed okay. So, I reversed the
order of the two timing tests and I haven't had a crash at this point so
far.
I added a couple of information messages which I have left to help with
diagnosis if the problem should appear on another machine.
This version reduces the minimum TLB flush threshold to 16 KiB.
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
Commit cafa0010cd ("Raise the minimum required gcc version to 4.6")
bumped the minimum GCC version to 4.6 for all architectures.
The version check in arch/parisc/Makefile is obsolete now.
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Helge Deller <deller@gmx.de>
The payload associated with a #PF exception is the linear address of
the fault to be loaded into CR2 when the fault is delivered. The
payload associated with a #DB exception is a mask of the DR6 bits to
be set (or in the case of DR6.RTM, cleared) when the fault is
delivered. Add fields has_payload and payload to kvm_queued_exception
to track payloads for pending exceptions.
The new fields are introduced here, but for now, they are just cleared.
Reported-by: Jim Mattson <jmattson@google.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently we hardcode a list of files for which we specify that the
toolchain has DSP ASE support when building for MIPSr2 only. This has a
number of problems:
1) It doesn't actually ensure that the toolchain supports the DSP ASE
at all.
2) It's fragile if we try to use DSP ASE macros in other files.
3) It makes no provision for MIPSr6 & later systems which also support
the DSP ASE & end up using the .word directive implementation of
the DSP macros.
Fix this by detecting assembler support for the DSP ASE globally, not
just for a small set of files, and not just for MIPSr2. This now exposes
use of toolchain DSP support to kernel builds targeting MIPSr1 and
older, so we add .set MIPS_ISA_LEVEL directives prior to all .set dsp
directives in order to prevent the assembler from complaining that the
DSP ASE is only supported with MIPSr2 & higher.
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20901/
Cc: linux-mips@linux-mips.org
Add support for get/set of nested state when Enlightened VMCS is in use.
A new KVM_STATE_NESTED_EVMCS flag to indicate eVMCS on the vCPU was enabled
is added.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
vcpu->arch.pv_eoi is accessible through both HV_X64_MSR_VP_ASSIST_PAGE and
MSR_KVM_PV_EOI_EN so on migration userspace may try to restore them in any
order. Values match, however, kvm_lapic_enable_pv_eoi() uses different
length: for Hyper-V case it's the whole struct hv_vp_assist_page, for KVM
native case it is 8. In case we restore KVM-native MSR last cache will
be reinitialized with len=8 so trying to access VP assist page beyond
8 bytes with kvm_read_guest_cached() will fail.
Check if we re-initializing cache for the same address and preserve length
in case it was greater.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
VP assist pages may hold valuable data which needs to be preserved across
migration. Clean PV EOI portion of the data on init, the guest is
responsible for making sure there's no garbage in the rest.
This will be used for nVMX migration, eVMCS address needs to be preserved.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When Enlightened VMCS is in use by L1 hypervisor we can avoid vmwriting
VMCS fields which did not change.
Our first goal is to achieve minimal impact on traditional VMCS case so
we're not wrapping each vmwrite() with an if-changed checker. We also can't
utilize static keys as Enlightened VMCS usage is per-guest.
This patch implements the simpliest solution: checking fields in groups.
We skip single vmwrite() statements as doing the check will cost us
something even in non-evmcs case and the win is tiny. Unfortunately, this
makes prepare_vmcs02_full{,_full}() code Enlightened VMCS-dependent (and
a bit ugly).
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Per Hyper-V TLFS 5.0b:
"The L1 hypervisor may choose to use enlightened VMCSs by writing 1 to
the corresponding field in the VP assist page (see section 7.8.7).
Another field in the VP assist page controls the currently active
enlightened VMCS. Each enlightened VMCS is exactly one page (4 KB) in
size and must be initially zeroed. No VMPTRLD instruction must be
executed to make an enlightened VMCS active or current.
After the L1 hypervisor performs a VM entry with an enlightened VMCS,
the VMCS is considered active on the processor. An enlightened VMCS
can only be active on a single processor at the same time. The L1
hypervisor can execute a VMCLEAR instruction to transition an
enlightened VMCS from the active to the non-active state. Any VMREAD
or VMWRITE instructions while an enlightened VMCS is active is
unsupported and can result in unexpected behavior."
Keep Enlightened VMCS structure for the current L2 guest permanently mapped
from struct nested_vmx instead of mapping it every time.
Suggested-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Adds hv_evmcs pointer and implement copy_enlightened_to_vmcs12() and
copy_enlightened_to_vmcs12().
prepare_vmcs02()/prepare_vmcs02_full() separation is not valid for
Enlightened VMCS, do full sync for now.
Suggested-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Enlightened VMCS is opt-in. The current version does not contain all
fields supported by nested VMX so we must not advertise the
corresponding VMX features if enlightened VMCS is enabled.
Userspace is given the enlightened VMCS version supported by KVM as
part of enabling KVM_CAP_HYPERV_ENLIGHTENED_VMCS. The version is to
be advertised to the nested hypervisor, currently done via a cpuid
leaf for Hyper-V.
Suggested-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Split off EVMCS1_UNSUPPORTED_* macros so we can re-use them when
enabling Enlightened VMCS for Hyper-V on KVM.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
rmap_remove() removes the sptep after locating the correct rmap_head but,
in several cases, the caller has already known the correct rmap_head.
This patch introduces a new pte_list_remove(); because it is known that
the spte is present (or it would not have an rmap_head), it is safe
to remove the tracking bits without any previous check.
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If ept table pointers are mismatched, flushing tlb for each vcpus via
hv flush interface still helps to reduce vmexits which are triggered
by IPI and INEPT emulation.
Signed-off-by: Lan Tianyu <Tianyu.Lan@microsoft.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
x86_64 zero-extends 32bit xor to a full 64bit register. Use %k asm
operand modifier to force 32bit register and save 268 bytes in kvm.o
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Recently the minimum required version of binutils was changed to 2.20,
which supports all VMX instruction mnemonics. The patch removes
all .byte #defines and uses real instruction mnemonics instead.
The compiler is now able to pass memory operand to the instruction,
so there is no need for memory clobber anymore. Also, the compiler
adds CC register clobber automatically to all extended asm clauses,
so the patch also removes explicit CC clobber.
The immediate benefit of the patch is removal of many unnecesary
register moves, resulting in 1434 saved bytes in vmx.o:
text data bss dec hex filename
151257 18246 8500 178003 2b753 vmx.o
152691 18246 8500 179437 2bced vmx-old.o
Some examples of improvement include removal of unneeded moves
of %rsp to %rax in front of invept and invvpid instructions:
a57e: b9 01 00 00 00 mov $0x1,%ecx
a583: 48 89 04 24 mov %rax,(%rsp)
a587: 48 89 e0 mov %rsp,%rax
a58a: 48 c7 44 24 08 00 00 movq $0x0,0x8(%rsp)
a591: 00 00
a593: 66 0f 38 80 08 invept (%rax),%rcx
to:
a45c: 48 89 04 24 mov %rax,(%rsp)
a460: b8 01 00 00 00 mov $0x1,%eax
a465: 48 c7 44 24 08 00 00 movq $0x0,0x8(%rsp)
a46c: 00 00
a46e: 66 0f 38 80 04 24 invept (%rsp),%rax
and the ability to use more optimal registers and memory operands
in the instruction:
8faa: 48 8b 44 24 28 mov 0x28(%rsp),%rax
8faf: 4c 89 c2 mov %r8,%rdx
8fb2: 0f 79 d0 vmwrite %rax,%rdx
to:
8e7c: 44 0f 79 44 24 28 vmwrite 0x28(%rsp),%r8
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Register operand size of invvpid and invept instruction in 64-bit mode
has always 64 bits. Adjust inline function argument type to reflect
correct size.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We don't use root page role for nested_mmu, however, optimizing out
re-initialization in case nothing changed is still valuable as this
is done for every nested vmentry.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
MMU reconfiguration in init_kvm_tdp_mmu()/kvm_init_shadow_mmu() can be
avoided if the source data used to configure it didn't change; enhance
MMU extended role with the required fields and consolidate common code in
kvm_calc_mmu_role_common().
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
MMU re-initialization is expensive, in particular,
update_permission_bitmask() and update_pkru_bitmask() are.
Cache the data used to setup shadow EPT MMU and avoid full re-init when
it is unchanged.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In preparation to MMU reconfiguration avoidance we need a space to
cache source data. As this partially intersects with kvm_mmu_page_role,
create 64bit sized union kvm_mmu_role holding both base and extended data.
No functional change.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When EPT is used for nested guest we need to re-init MMU as shadow
EPT MMU (nested_ept_init_mmu_context() does that). When we return back
from L2 to L1 kvm_mmu_reset_context() in nested_vmx_load_cr3() resets
MMU back to normal TDP mode. Add a special 'guest_mmu' so we can use
separate root caches; the improved hit rate is not very important for
single vCPU performance, but it avoids contention on the mmu_lock for
many vCPUs.
On the nested CPUID benchmark, with 16 vCPUs, an L2->L1->L2 vmexit
goes from 42k to 26k cycles.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add an option to specify which MMU root we want to free. This will
be used when nested and non-nested MMUs for L1 are split.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
kvm_init_shadow_ept_mmu() doesn't set get_pdptr() hook and is this
not a problem just because MMU context is already initialized and this
hook points to kvm_pdptr_read(). As we're intended to use a dedicated
MMU for shadow EPT MMU set this hook explicitly.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
