commit 8764ed55c9705e426d889ff16c26f398bba70b9b upstream.

KVM's recent bug fix to update %rip after emulating I/O broke userspace
that relied on the previous behavior of incrementing %rip prior to
exiting to userspace.  When running a Windows XP guest on AMD hardware,
Qemu may patch "OUT 0x7E" instructions in reaction to the OUT itself.
Because KVM's old behavior was to increment %rip before exiting to
userspace to handle the I/O, Qemu manually adjusted %rip to account for
the OUT instruction.

Arguably this is a userspace bug as KVM requires userspace to re-enter
the kernel to complete instruction emulation before taking any other
actions.  That being said, this is a bit of a grey area and breaking
userspace that has worked for many years is bad.

Pre-increment %rip on OUT to port 0x7e before exiting to userspace to
hack around the issue.

Fixes: 45def77ebf79e ("KVM: x86: update %rip after emulating IO")
Reported-by: NSimon Becherer <simon@becherer.de>
Reported-and-tested-by: NIakov Karpov <srid@rkmail.ru>
Reported-by: NGabriele Balducci <balducci@units.it>
Reported-by: NAntti Antinoja <reader@fennosys.fi>
Cc: stable@vger.kernel.org
Cc: Takashi Iwai <tiwai@suse.com>
Cc: Jiri Slaby <jslaby@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 0cf9135b773bf32fba9dd8e6699c1b331ee4b749 upstream.

The CPUID flag ARCH_CAPABILITIES is unconditioinally exposed to host
userspace for all x86 hosts, i.e. KVM advertises ARCH_CAPABILITIES
regardless of hardware support under the pretense that KVM fully
emulates MSR_IA32_ARCH_CAPABILITIES.  Unfortunately, only VMX hosts
handle accesses to MSR_IA32_ARCH_CAPABILITIES (despite KVM_GET_MSRS
also reporting MSR_IA32_ARCH_CAPABILITIES for all hosts).

Move the MSR_IA32_ARCH_CAPABILITIES handling to common x86 code so
that it's emulated on AMD hosts.

Fixes: 1eaafe91 ("kvm: x86: IA32_ARCH_CAPABILITIES is always supported")
Cc: stable@vger.kernel.org
Reported-by: NXiaoyao Li <xiaoyao.li@linux.intel.com>
Cc: Jim Mattson <jmattson@google.com>
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 45def77ebf79e2e8942b89ed79294d97ce914fa0 upstream.

Most (all?) x86 platforms provide a port IO based reset mechanism, e.g.
OUT 92h or CF9h.  Userspace may emulate said mechanism, i.e. reset a
vCPU in response to KVM_EXIT_IO, without explicitly announcing to KVM
that it is doing a reset, e.g. Qemu jams vCPU state and resumes running.

To avoid corruping %rip after such a reset, commit 0967b7bf ("KVM:
Skip pio instruction when it is emulated, not executed") changed the
behavior of PIO handlers, i.e. today's "fast" PIO handling to skip the
instruction prior to exiting to userspace.  Full emulation doesn't need
such tricks becase re-emulating the instruction will naturally handle
%rip being changed to point at the reset vector.

Updating %rip prior to executing to userspace has several drawbacks:

  - Userspace sees the wrong %rip on the exit, e.g. if PIO emulation
    fails it will likely yell about the wrong address.
  - Single step exits to userspace for are effectively dropped as
    KVM_EXIT_DEBUG is overwritten with KVM_EXIT_IO.
  - Behavior of PIO emulation is different depending on whether it
    goes down the fast path or the slow path.

Rather than skip the PIO instruction before exiting to userspace,
snapshot the linear %rip and cancel PIO completion if the current
value does not match the snapshot.  For a 64-bit vCPU, i.e. the most
common scenario, the snapshot and comparison has negligible overhead
as VMCS.GUEST_RIP will be cached regardless, i.e. there is no extra
VMREAD in this case.

All other alternatives to snapshotting the linear %rip that don't
rely on an explicit reset announcenment suffer from one corner case
or another.  For example, canceling PIO completion on any write to
%rip fails if userspace does a save/restore of %rip, and attempting to
avoid that issue by canceling PIO only if %rip changed then fails if PIO
collides with the reset %rip.  Attempting to zero in on the exact reset
vector won't work for APs, which means adding more hooks such as the
vCPU's MP_STATE, and so on and so forth.

Checking for a linear %rip match technically suffers from corner cases,
e.g. userspace could theoretically rewrite the underlying code page and
expect a different instruction to execute, or the guest hardcodes a PIO
reset at 0xfffffff0, but those are far, far outside of what can be
considered normal operation.

Fixes: 432baf60 ("KVM: VMX: use kvm_fast_pio_in for handling IN I/O")
Cc: <stable@vger.kernel.org>
Reported-by: NJim Mattson <jmattson@google.com>
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 152482580a1b0accb60676063a1ac57b2d12daf6 upstream.

kvm_arch_memslots_updated() is at this point in time an x86-specific
hook for handling MMIO generation wraparound.  x86 stashes 19 bits of
the memslots generation number in its MMIO sptes in order to avoid
full page fault walks for repeat faults on emulated MMIO addresses.
Because only 19 bits are used, wrapping the MMIO generation number is
possible, if unlikely.  kvm_arch_memslots_updated() alerts x86 that
the generation has changed so that it can invalidate all MMIO sptes in
case the effective MMIO generation has wrapped so as to avoid using a
stale spte, e.g. a (very) old spte that was created with generation==0.

Given that the purpose of kvm_arch_memslots_updated() is to prevent
consuming stale entries, it needs to be called before the new generation
is propagated to memslots.  Invalidating the MMIO sptes after updating
memslots means that there is a window where a vCPU could dereference
the new memslots generation, e.g. 0, and incorrectly reuse an old MMIO
spte that was created with (pre-wrap) generation==0.

Fixes: e59dbe09 ("KVM: Introduce kvm_arch_memslots_updated()")
Cc: <stable@vger.kernel.org>
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 353c0956a618a07ba4bbe7ad00ff29fe70e8412a upstream.

Bugzilla: 1671930

Emulation of certain instructions (VMXON, VMCLEAR, VMPTRLD, VMWRITE with
memory operand, INVEPT, INVVPID) can incorrectly inject a page fault
when passed an operand that points to an MMIO address.  The page fault
will use uninitialized kernel stack memory as the CR2 and error code.

The right behavior would be to abort the VM with a KVM_EXIT_INTERNAL_ERROR
exit to userspace; however, it is not an easy fix, so for now just
ensure that the error code and CR2 are zero.

Embargoed until Feb 7th 2019.
Reported-by: NFelix Wilhelm <fwilhelm@google.com>
Cc: stable@kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 1ed199a41c70ad7bfaee8b14f78e791fcf43b278 upstream.

The recognition of the KVM_HC_SEND_IPI hypercall was unintentionally
wrapped in "#ifdef CONFIG_X86_64", causing 32-bit KVM hosts to reject
any and all PV IPI requests despite advertising the feature.  This
results in all KVM paravirtualized guests hanging during SMP boot due
to IPIs never being delivered.

Fixes: 4180bf1b ("KVM: X86: Implement "send IPI" hypercall")
Cc: stable@vger.kernel.org
Cc: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 5cc244a20b86090c087073c124284381cdf47234 upstream.

The single-step debugging of KVM guests on x86 is broken: if we run
gdb 'stepi' command at the breakpoint when the guest interrupts are
enabled, RIP always jumps to native_apic_mem_write(). Then other
nasty effects follow.

Long investigation showed that on Jun 7, 2017 the
commit c8401dda ("KVM: x86: fix singlestepping over syscall")
introduced the kvm_run.debug corruption: kvm_vcpu_do_singlestep() can
be called without X86_EFLAGS_TF set.

Let's fix it. Please consider that for -stable.
Signed-off-by: NAlexander Popov <alex.popov@linux.com>
Cc: stable@vger.kernel.org
Fixes: c8401dda ("KVM: x86: fix singlestepping over syscall")
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 0e1b869fff60c81b510c2d00602d778f8f59dd9a upstream.

Some guests OSes (including Windows 10) write to MSR 0xc001102c
on some cases (possibly while trying to apply a CPU errata).
Make KVM ignore reads and writes to that MSR, so the guest won't
crash.

The MSR is documented as "Execution Unit Configuration (EX_CFG)",
at AMD's "BIOS and Kernel Developer's Guide (BKDG) for AMD Family
15h Models 00h-0Fh Processors".

Cc: stable@vger.kernel.org
Signed-off-by: NEduardo Habkost <ehabkost@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit dcbd3e49 upstream.

Reported by syzkaller:

    CPU: 1 PID: 5962 Comm: syz-executor118 Not tainted 4.20.0-rc6+ #374
    Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
    RIP: 0010:kvm_apic_hw_enabled arch/x86/kvm/lapic.h:169 [inline]
    RIP: 0010:vcpu_scan_ioapic arch/x86/kvm/x86.c:7449 [inline]
    RIP: 0010:vcpu_enter_guest arch/x86/kvm/x86.c:7602 [inline]
    RIP: 0010:vcpu_run arch/x86/kvm/x86.c:7874 [inline]
    RIP: 0010:kvm_arch_vcpu_ioctl_run+0x5296/0x7320 arch/x86/kvm/x86.c:8074
    Call Trace:
	 kvm_vcpu_ioctl+0x5c8/0x1150 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2596
	 vfs_ioctl fs/ioctl.c:46 [inline]
	 file_ioctl fs/ioctl.c:509 [inline]
	 do_vfs_ioctl+0x1de/0x1790 fs/ioctl.c:696
	 ksys_ioctl+0xa9/0xd0 fs/ioctl.c:713
	 __do_sys_ioctl fs/ioctl.c:720 [inline]
	 __se_sys_ioctl fs/ioctl.c:718 [inline]
	 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718
	 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
	 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The reason is that the testcase writes hyperv synic HV_X64_MSR_SINT14 msr
and triggers scan ioapic logic to load synic vectors into EOI exit bitmap.
However, irqchip is not initialized by this simple testcase, ioapic/apic
objects should not be accessed.

This patch fixes it by also considering whether or not apic is present.

Reported-by: syzbot+39810e6c400efadfef71@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: NWanpeng Li <wanpengli@tencent.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit e97f852fd4561e77721bb9a4e0ea9d98305b1e93 upstream.

Reported by syzkaller:

 BUG: unable to handle kernel NULL pointer dereference at 00000000000001c8
 PGD 80000003ec4da067 P4D 80000003ec4da067 PUD 3f7bfa067 PMD 0
 Oops: 0000 [#1] PREEMPT SMP PTI
 CPU: 7 PID: 5059 Comm: debug Tainted: G           OE     4.19.0-rc5 #16
 RIP: 0010:__lock_acquire+0x1a6/0x1990
 Call Trace:
  lock_acquire+0xdb/0x210
  _raw_spin_lock+0x38/0x70
  kvm_ioapic_scan_entry+0x3e/0x110 [kvm]
  vcpu_enter_guest+0x167e/0x1910 [kvm]
  kvm_arch_vcpu_ioctl_run+0x35c/0x610 [kvm]
  kvm_vcpu_ioctl+0x3e9/0x6d0 [kvm]
  do_vfs_ioctl+0xa5/0x690
  ksys_ioctl+0x6d/0x80
  __x64_sys_ioctl+0x1a/0x20
  do_syscall_64+0x83/0x6e0
  entry_SYSCALL_64_after_hwframe+0x49/0xbe

The reason is that the testcase writes hyperv synic HV_X64_MSR_SINT6 msr
and triggers scan ioapic logic to load synic vectors into EOI exit bitmap.
However, irqchip is not initialized by this simple testcase, ioapic/apic
objects should not be accessed.
This can be triggered by the following program:

    #define _GNU_SOURCE

    #include <endian.h>
    #include <stdint.h>
    #include <stdio.h>
    #include <stdlib.h>
    #include <string.h>
    #include <sys/syscall.h>
    #include <sys/types.h>
    #include <unistd.h>

    uint64_t r[3] = {0xffffffffffffffff, 0xffffffffffffffff, 0xffffffffffffffff};

    int main(void)
    {
    	syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0);
    	long res = 0;
    	memcpy((void*)0x20000040, "/dev/kvm", 9);
    	res = syscall(__NR_openat, 0xffffffffffffff9c, 0x20000040, 0, 0);
    	if (res != -1)
    		r[0] = res;
    	res = syscall(__NR_ioctl, r[0], 0xae01, 0);
    	if (res != -1)
    		r[1] = res;
    	res = syscall(__NR_ioctl, r[1], 0xae41, 0);
    	if (res != -1)
    		r[2] = res;
    	memcpy(
    			(void*)0x20000080,
    			"\x01\x00\x00\x00\x00\x5b\x61\xbb\x96\x00\x00\x40\x00\x00\x00\x00\x01\x00"
    			"\x08\x00\x00\x00\x00\x00\x0b\x77\xd1\x78\x4d\xd8\x3a\xed\xb1\x5c\x2e\x43"
    			"\xaa\x43\x39\xd6\xff\xf5\xf0\xa8\x98\xf2\x3e\x37\x29\x89\xde\x88\xc6\x33"
    			"\xfc\x2a\xdb\xb7\xe1\x4c\xac\x28\x61\x7b\x9c\xa9\xbc\x0d\xa0\x63\xfe\xfe"
    			"\xe8\x75\xde\xdd\x19\x38\xdc\x34\xf5\xec\x05\xfd\xeb\x5d\xed\x2e\xaf\x22"
    			"\xfa\xab\xb7\xe4\x42\x67\xd0\xaf\x06\x1c\x6a\x35\x67\x10\x55\xcb",
    			106);
    	syscall(__NR_ioctl, r[2], 0x4008ae89, 0x20000080);
    	syscall(__NR_ioctl, r[2], 0xae80, 0);
    	return 0;
    }

This patch fixes it by bailing out scan ioapic if ioapic is not initialized in
kernel.
Reported-by: NWei Wu <ww9210@gmail.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Wei Wu <ww9210@gmail.com>
Signed-off-by: NWanpeng Li <wanpengli@tencent.com>
Cc: stable@vger.kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit bcbfbd8ec21096027f1ee13ce6c185e8175166f6 upstream.

kvm_pv_clock_pairing() allocates local var
"struct kvm_clock_pairing clock_pairing" on stack and initializes
all it's fields besides padding (clock_pairing.pad[]).

Because clock_pairing var is written completely (including padding)
to guest memory, failure to init struct padding results in kernel
info-leak.

Fix the issue by making sure to also init the padding with zeroes.

Fixes: 55dd00a7 ("KVM: x86: add KVM_HC_CLOCK_PAIRING hypercall")
Reported-by: syzbot+a8ef68d71211ba264f56@syzkaller.appspotmail.com
Reviewed-by: NMark Kanda <mark.kanda@oracle.com>
Signed-off-by: NLiran Alon <liran.alon@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

commit 326e742533bf0a23f0127d8ea62fb558ba665f08 upstream.

Since commit e79f245d ("X86/KVM: Properly update 'tsc_offset' to
represent the running guest"), vcpu->arch.tsc_offset meaning was
changed to always reflect the tsc_offset value set on active VMCS.
Regardless if vCPU is currently running L1 or L2.

However, above mentioned commit failed to also change
kvm_vcpu_write_tsc_offset() to set vcpu->arch.tsc_offset correctly.
This is because vmx_write_tsc_offset() could set the tsc_offset value
in active VMCS to given offset parameter *plus vmcs12->tsc_offset*.
However, kvm_vcpu_write_tsc_offset() just sets vcpu->arch.tsc_offset
to given offset parameter. Without taking into account the possible
addition of vmcs12->tsc_offset. (Same is true for SVM case).

Fix this issue by changing kvm_x86_ops->write_tsc_offset() to return
actually set tsc_offset in active VMCS and modify
kvm_vcpu_write_tsc_offset() to set returned value in
vcpu->arch.tsc_offset.
In addition, rename write_tsc_offset() callback to write_l1_tsc_offset()
to make it clear that it is meant to set L1 TSC offset.

Fixes: e79f245d ("X86/KVM: Properly update 'tsc_offset' to represent the running guest")
Reviewed-by: NLiran Alon <liran.alon@oracle.com>
Reviewed-by: NMihai Carabas <mihai.carabas@oracle.com>
Reviewed-by: NKrish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: NLeonid Shatz <leonid.shatz@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

Commit a87036ad ("KVM: x86: disable MPX if host did not enable
MPX XSAVE features") introduced kvm_mpx_supported() to return true
iff MPX is enabled in the host.

However, that commit seems to have missed replacing some calls to
kvm_x86_ops->mpx_supported() to kvm_mpx_supported().

Complete original commit by replacing remaining calls to
kvm_mpx_supported().

Fixes: a87036ad ("KVM: x86: disable MPX if host did not enable
MPX XSAVE features")
Suggested-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NLiran Alon <liran.alon@oracle.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The handlers of IOCTLs in kvm_arch_vcpu_ioctl() are expected to set
their return value in "r" local var and break out of switch block
when they encounter some error.
This is because vcpu_load() is called before the switch block which
have a proper cleanup of vcpu_put() afterwards.

However, KVM_{GET,SET}_NESTED_STATE IOCTLs handlers just return
immediately on error without performing above mentioned cleanup.

Thus, change these handlers to behave as expected.

Fixes: 8fcc4b59 ("kvm: nVMX: Introduce KVM_CAP_NESTED_STATE")
Reviewed-by: NMark Kanda <mark.kanda@oracle.com>
Reviewed-by: NPatrick Colp <patrick.colp@oracle.com>
Signed-off-by: NLiran Alon <liran.alon@oracle.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Add KVM_CAP_MSR_PLATFORM_INFO so that userspace can disable guest access
to reads of MSR_PLATFORM_INFO.

Disabling access to reads of this MSR gives userspace the control to "expose"
this platform-dependent information to guests in a clear way. As it exists
today, guests that read this MSR would get unpopulated information if userspace
hadn't already set it (and prior to this patch series, only the CPUID faulting
information could have been populated). This existing interface could be
confusing if guests don't handle the potential for incorrect/incomplete
information gracefully (e.g. zero reported for base frequency).
Signed-off-by: NDrew Schmitt <dasch@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Allow userspace to set turbo bits in MSR_PLATFORM_INFO. Previously, only
the CPUID faulting bit was settable. But now any bit in
MSR_PLATFORM_INFO would be settable. This can be used, for example, to
convey frequency information about the platform on which the guest is
running.
Signed-off-by: NDrew Schmitt <dasch@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

In case L1 do not intercept L2 HLT or enter L2 in HLT activity-state,
it is possible for a vCPU to be blocked while it is in guest-mode.

According to Intel SDM 26.6.5 Interrupt-Window Exiting and
Virtual-Interrupt Delivery: "These events wake the logical processor
if it just entered the HLT state because of a VM entry".
Therefore, if L1 enters L2 in HLT activity-state and L2 has a pending
deliverable interrupt in vmcs12->guest_intr_status.RVI, then the vCPU
should be waken from the HLT state and injected with the interrupt.

In addition, if while the vCPU is blocked (while it is in guest-mode),
it receives a nested posted-interrupt, then the vCPU should also be
waken and injected with the posted interrupt.

To handle these cases, this patch enhances kvm_vcpu_has_events() to also
check if there is a pending interrupt in L2 virtual APICv provided by
L1. That is, it evaluates if there is a pending virtual interrupt for L2
by checking RVI[7:4] > VPPR[7:4] as specified in Intel SDM 29.2.1
Evaluation of Pending Interrupts.

Note that this also handles the case of nested posted-interrupt by the
fact RVI is updated in vmx_complete_nested_posted_interrupt() which is
called from kvm_vcpu_check_block() -> kvm_arch_vcpu_runnable() ->
kvm_vcpu_running() -> vmx_check_nested_events() ->
vmx_complete_nested_posted_interrupt().
Reviewed-by: NNikita Leshenko <nikita.leshchenko@oracle.com>
Reviewed-by: NDarren Kenny <darren.kenny@oracle.com>
Signed-off-by: NLiran Alon <liran.alon@oracle.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The functions
	kvm_load_guest_fpu()
	kvm_put_guest_fpu()

are only used locally, make them static. This requires also that both
functions are moved because they are used before their implementation.
Those functions were exported (via EXPORT_SYMBOL) before commit
e5bb4025 ("KVM: Drop kvm_{load,put}_guest_fpu() exports").
Signed-off-by: NSebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

A VMX preemption timer value of '0' is guaranteed to cause a VMExit
prior to the CPU executing any instructions in the guest.  Use the
preemption timer (if it's supported) to trigger immediate VMExit
in place of the current method of sending a self-IPI.  This ensures
that pending VMExit injection to L1 occurs prior to executing any
instructions in the guest (regardless of nesting level).

When deferring VMExit injection, KVM generates an immediate VMExit
from the (possibly nested) guest by sending itself an IPI.  Because
hardware interrupts are blocked prior to VMEnter and are unblocked
(in hardware) after VMEnter, this results in taking a VMExit(INTR)
before any guest instruction is executed.  But, as this approach
relies on the IPI being received before VMEnter executes, it only
works as intended when KVM is running as L0.  Because there are no
architectural guarantees regarding when IPIs are delivered, when
running nested the INTR may "arrive" long after L2 is running e.g.
L0 KVM doesn't force an immediate switch to L1 to deliver an INTR.

For the most part, this unintended delay is not an issue since the
events being injected to L1 also do not have architectural guarantees
regarding their timing.  The notable exception is the VMX preemption
timer[1], which is architecturally guaranteed to cause a VMExit prior
to executing any instructions in the guest if the timer value is '0'
at VMEnter.  Specifically, the delay in injecting the VMExit causes
the preemption timer KVM unit test to fail when run in a nested guest.

Note: this approach is viable even on CPUs with a broken preemption
timer, as broken in this context only means the timer counts at the
wrong rate.  There are no known errata affecting timer value of '0'.

[1] I/O SMIs also have guarantees on when they arrive, but I have
    no idea if/how those are emulated in KVM.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
[Use a hook for SVM instead of leaving the default in x86.c - Paolo]
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

kvm should not attempt to read guest PDPTEs when CR0.PG = 0 and
CR4.PAE = 1.
Signed-off-by: NJunaid Shahid <junaids@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Allowing x86_emulate_instruction() to be called directly has led to
subtle bugs being introduced, e.g. not setting EMULTYPE_NO_REEXECUTE
in the emulation type.  While most of the blame lies on re-execute
being opt-out, exporting x86_emulate_instruction() also exposes its
cr2 parameter, which may have contributed to commit d391f120
("x86/kvm/vmx: do not use vm-exit instruction length for fast MMIO
when running nested") using x86_emulate_instruction() instead of
emulate_instruction() because "hey, I have a cr2!", which in turn
introduced its EMULTYPE_NO_REEXECUTE bug.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Lack of the kvm_ prefix gives the impression that it's a VMX or SVM
specific function, and there's no conflict that prevents adding the
kvm_ prefix.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Commit a6f177ef ("KVM: Reenter guest after emulation failure if
due to access to non-mmio address") added reexecute_instruction() to
handle the scenario where two (or more) vCPUS race to write a shadowed
page, i.e. reexecute_instruction() is intended to return true if and
only if the instruction being emulated was accessing a shadowed page.
As L0 is only explicitly shadowing L1 tables, an emulation failure of
a nested VM instruction cannot be due to a race to write a shadowed
page and so should never be re-executed.

This fixes an issue where an "MMIO" emulation failure[1] in L2 is all
but guaranteed to result in an infinite loop when TDP is enabled.
Because "cr2" is actually an L2 GPA when TDP is enabled, calling
kvm_mmu_gva_to_gpa_write() to translate cr2 in the non-direct mapped
case (L2 is never direct mapped) will almost always yield UNMAPPED_GVA
and cause reexecute_instruction() to immediately return true.  The
!mmio_info_in_cache() check in kvm_mmu_page_fault() doesn't catch this
case because mmio_info_in_cache() returns false for a nested MMU (the
MMIO caching currently handles L1 only, e.g. to cache nested guests'
GPAs we'd have to manually flush the cache when switching between
VMs and when L1 updated its page tables controlling the nested guest).

Way back when, commit 68be0803 ("KVM: x86: never re-execute
instruction with enabled tdp") changed reexecute_instruction() to
always return false when using TDP under the assumption that KVM would
only get into the emulator for MMIO.  Commit 95b3cf69 ("KVM: x86:
let reexecute_instruction work for tdp") effectively reverted that
behavior in order to handle the scenario where emulation failed due to
an access from L1 to the shadow page tables for L2, but it didn't
account for the case where emulation failed in L2 with TDP enabled.

All of the above logic also applies to retry_instruction(), added by
commit 1cb3f3ae ("KVM: x86: retry non-page-table writing
instructions").  An indefinite loop in retry_instruction() should be
impossible as it protects against retrying the same instruction over
and over, but it's still correct to not retry an L2 instruction in
the first place.

Fix the immediate issue by adding a check for a nested guest when
determining whether or not to allow retry in kvm_mmu_page_fault().
In addition to fixing the immediate bug, add WARN_ON_ONCE in the
retry functions since they are not designed to handle nested cases,
i.e. they need to be modified even if there is some scenario in the
future where we want to allow retrying a nested guest.

[1] This issue was encountered after commit 3a2936de ("kvm: mmu:
    Don't expose private memslots to L2") changed the page fault path
    to return KVM_PFN_NOSLOT when translating an L2 access to a
    prive memslot.  Returning KVM_PFN_NOSLOT is semantically correct
    when we want to hide a memslot from L2, i.e. there effectively is
    no defined memory region for L2, but it has the unfortunate side
    effect of making KVM think the GFN is a MMIO page, thus triggering
    emulation.  The failure occurred with in-development code that
    deliberately exposed a private memslot to L2, which L2 accessed
    with an instruction that is not emulated by KVM.

Fixes: 95b3cf69 ("KVM: x86: let reexecute_instruction work for tdp")
Fixes: 1cb3f3ae ("KVM: x86: retry non-page-table writing instructions")
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Cc: Jim Mattson <jmattson@google.com>
Cc: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@tencent.com>
Cc: stable@vger.kernel.org
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

retry_instruction() and reexecute_instruction() are a package deal,
i.e. there is no scenario where one is allowed and the other is not.
Merge their controlling emulation type flags to enforce this in code.
Name the combined flag EMULTYPE_ALLOW_RETRY to make it abundantly
clear that we are allowing re{try,execute} to occur, as opposed to
explicitly requesting retry of a previously failed instruction.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Re-execution of an instruction after emulation decode failure is
intended to be used only when emulating shadow page accesses.  Invert
the flag to make allowing re-execution opt-in since that behavior is
by far in the minority.
Signed-off-by: NSean Christopherson <sean.j.christopherson@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

There are several blockable mmu notifiers which might sleep in
mmu_notifier_invalidate_range_start and that is a problem for the
oom_reaper because it needs to guarantee a forward progress so it cannot
depend on any sleepable locks.

Currently we simply back off and mark an oom victim with blockable mmu
notifiers as done after a short sleep.  That can result in selecting a new
oom victim prematurely because the previous one still hasn't torn its
memory down yet.

We can do much better though.  Even if mmu notifiers use sleepable locks
there is no reason to automatically assume those locks are held.  Moreover
majority of notifiers only care about a portion of the address space and
there is absolutely zero reason to fail when we are unmapping an unrelated
range.  Many notifiers do really block and wait for HW which is harder to
handle and we have to bail out though.

This patch handles the low hanging fruit.
__mmu_notifier_invalidate_range_start gets a blockable flag and callbacks
are not allowed to sleep if the flag is set to false.  This is achieved by
using trylock instead of the sleepable lock for most callbacks and
continue as long as we do not block down the call chain.

I think we can improve that even further because there is a common pattern
to do a range lookup first and then do something about that.  The first
part can be done without a sleeping lock in most cases AFAICS.

The oom_reaper end then simply retries if there is at least one notifier
which couldn't make any progress in !blockable mode.  A retry loop is
already implemented to wait for the mmap_sem and this is basically the
same thing.

The simplest way for driver developers to test this code path is to wrap
userspace code which uses these notifiers into a memcg and set the hard
limit to hit the oom.  This can be done e.g.  after the test faults in all
the mmu notifier managed memory and set the hard limit to something really
small.  Then we are looking for a proper process tear down.

[akpm@linux-foundation.org: coding style fixes]
[akpm@linux-foundation.org: minor code simplification]
Link: http://lkml.kernel.org/r/20180716115058.5559-1-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Acked-by: Christian König <christian.koenig@amd.com> # AMD notifiers
Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx and umem_odp
Reported-by: NDavid Rientjes <rientjes@google.com>
Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Mike Marciniszyn <mike.marciniszyn@intel.com>
Cc: Dennis Dalessandro <dennis.dalessandro@intel.com>
Cc: Sudeep Dutt <sudeep.dutt@intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Removing one of the two accesses of the maxphyaddr variable led to
a harmless warning:

arch/x86/kvm/x86.c: In function 'kvm_set_mmio_spte_mask':
arch/x86/kvm/x86.c:6563:6: error: unused variable 'maxphyaddr' [-Werror=unused-variable]

Removing the #ifdef seems to be the nicest workaround, as it
makes the code look cleaner than adding another #ifdef.

Fixes: 28a1f3ac ("kvm: x86: Set highest physical address bits in non-present/reserved SPTEs")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org # L1TF
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Always set the 5 upper-most supported physical address bits to 1 for SPTEs
that are marked as non-present or reserved, to make them unusable for
L1TF attacks from the guest. Currently, this just applies to MMIO SPTEs.
(We do not need to mark PTEs that are completely 0 as physical page 0
is already reserved.)

This allows mitigation of L1TF without disabling hyper-threading by using
shadow paging mode instead of EPT.
Signed-off-by: NJunaid Shahid <junaids@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Using hypercall to send IPIs by one vmexit instead of one by one for
xAPIC/x2APIC physical mode and one vmexit per-cluster for x2APIC cluster
mode. Intel guest can enter x2apic cluster mode when interrupt remmaping
is enabled in qemu, however, latest AMD EPYC still just supports xapic
mode which can get great improvement by Exit-less IPIs. This patchset
lets a guest send multicast IPIs, with at most 128 destinations per
hypercall in 64-bit mode and 64 vCPUs per hypercall in 32-bit mode.

Hardware: Xeon Skylake 2.5GHz, 2 sockets, 40 cores, 80 threads, the VM
is 80 vCPUs, IPI microbenchmark(https://lkml.org/lkml/2017/12/19/141):

x2apic cluster mode, vanilla

 Dry-run:                         0,            2392199 ns
 Self-IPI:                  6907514,           15027589 ns
 Normal IPI:              223910476,          251301666 ns
 Broadcast IPI:                   0,         9282161150 ns
 Broadcast lock:                  0,         8812934104 ns

x2apic cluster mode, pv-ipi

 Dry-run:                         0,            2449341 ns
 Self-IPI:                  6720360,           15028732 ns
 Normal IPI:              228643307,          255708477 ns
 Broadcast IPI:                   0,         7572293590 ns  => 22% performance boost
 Broadcast lock:                  0,         8316124651 ns

x2apic physical mode, vanilla

 Dry-run:                         0,            3135933 ns
 Self-IPI:                  8572670,           17901757 ns
 Normal IPI:              226444334,          255421709 ns
 Broadcast IPI:                   0,        19845070887 ns
 Broadcast lock:                  0,        19827383656 ns

x2apic physical mode, pv-ipi

 Dry-run:                         0,            2446381 ns
 Self-IPI:                  6788217,           15021056 ns
 Normal IPI:              219454441,          249583458 ns
 Broadcast IPI:                   0,         7806540019 ns  => 154% performance boost
 Broadcast lock:                  0,         9143618799 ns

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: NWanpeng Li <wanpengli@tencent.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

X86_CR4_OSXSAVE check belongs to sregs check and so move into
kvm_valid_sregs().
Signed-off-by: NLan Tianyu <Tianyu.Lan@microsoft.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

It is a duplicate of X86_CR3_PCID_NOFLUSH. So just use that instead.
Signed-off-by: NJunaid Shahid <junaids@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

When the guest indicates that the TLB doesn't need to be flushed in a
CR3 switch, we can also skip resyncing the shadow page tables since an
out-of-sync shadow page table is equivalent to an out-of-sync TLB.
Signed-off-by: NJunaid Shahid <junaids@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

When PCIDs are enabled, the MSb of the source operand for a MOV-to-CR3
instruction indicates that the TLB doesn't need to be flushed.

This change enables this optimization for MOV-to-CR3s in the guest
that have been intercepted by KVM for shadow paging and are handled
within the fast CR3 switch path.
Signed-off-by: NJunaid Shahid <junaids@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The KVM_REQ_LOAD_CR3 request loads the hardware CR3 using the
current root_hpa.
Signed-off-by: NJunaid Shahid <junaids@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

When using shadow paging, a CR3 switch in the guest results in a VM Exit.
In the common case, that VM exit doesn't require much processing by KVM.
However, it does acquire the MMU lock, which can start showing signs of
contention under some workloads even on a 2 VCPU VM when the guest is
using KPTI. Therefore, we add a fast path that avoids acquiring the MMU
lock in the most common cases e.g. when switching back and forth between
the kernel and user mode CR3s used by KPTI with no guest page table
changes in between.

For now, this fast path is implemented only for 64-bit guests and hosts
to avoid the handling of PDPTEs, but it can be extended later to 32-bit
guests and/or hosts as well.
Signed-off-by: NJunaid Shahid <junaids@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

For nested virtualization L0 KVM is managing a bit of state for L2 guests,
this state can not be captured through the currently available IOCTLs. In
fact the state captured through all of these IOCTLs is usually a mix of L1
and L2 state. It is also dependent on whether the L2 guest was running at
the moment when the process was interrupted to save its state.

With this capability, there are two new vcpu ioctls: KVM_GET_NESTED_STATE
and KVM_SET_NESTED_STATE. These can be used for saving and restoring a VM
that is in VMX operation.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: x86@kernel.org
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NJim Mattson <jmattson@google.com>
[karahmed@ - rename structs and functions and make them ready for AMD and
             address previous comments.
           - handle nested.smm state.
           - rebase & a bit of refactoring.
           - Merge 7/8 and 8/8 into one patch. ]
Signed-off-by: NKarimAllah Ahmed <karahmed@amazon.de>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

If the vCPU enters system management mode while running a nested guest,
RSM starts processing the vmentry while still in SMM.  In that case,
however, the pages pointed to by the vmcs12 might be incorrectly
loaded from SMRAM.  To avoid this, delay the handling of the pages
until just before the next vmentry.  This is done with a new request
and a new entry in kvm_x86_ops, which we will be able to reuse for
nested VMX state migration.

Extracted from a patch by Jim Mattson and KarimAllah Ahmed.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Some of the MSRs returned by GET_MSR_INDEX_LIST currently cannot be sent back
to KVM_GET_MSR and/or KVM_SET_MSR; either they can never be sent back, or you
they are only accepted under special conditions.  This makes the API a pain to
use.

To avoid this pain, this patch makes it so that the result of the get-list
ioctl can always be used for host-initiated get and set.  Since we don't have
a separate way to check for read-only MSRs, this means some Hyper-V MSRs are
ignored when written.  Arguably they should not even be in the result of
GET_MSR_INDEX_LIST, but I am leaving there in case userspace is using the
outcome of GET_MSR_INDEX_LIST to derive the support for the corresponding
Hyper-V feature.

Cc: stable@vger.kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

When nested virtualization is in use, VMENTER operations from the nested
hypervisor into the nested guest will always be processed by the bare metal
hypervisor, and KVM's "conditional cache flushes" mode in particular does a
flush on nested vmentry.  Therefore, include the "skip L1D flush on
vmentry" bit in KVM's suggested ARCH_CAPABILITIES setting.

Add the relevant Documentation.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

This lets userspace read the MSR_IA32_ARCH_CAPABILITIES and check that all
requested features are available on the host.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>