The VMX preemption timer can be used to virtualize the TSC deadline timer.
The VMX preemption timer is armed when the vCPU is running, and a VMExit
will happen if the virtual TSC deadline timer expires.

When the vCPU thread is blocked because of HLT, KVM will switch to use
an hrtimer, and then go back to the VMX preemption timer when the vCPU
thread is unblocked.

This solution avoids the complex OS's hrtimer system, and the host
timer interrupt handling cost, replacing them with a little math
(for guest->host TSC and host TSC->preemption timer conversion)
and a cheaper VMexit.  This benefits latency for isolated pCPUs.

[A word about performance... Yunhong reported a 30% reduction in average
 latency from cyclictest.  I made a similar test with tscdeadline_latency
 from kvm-unit-tests, and measured

 - ~20 clock cycles loss (out of ~3200, so less than 1% but still
   statistically significant) in the worst case where the test halts
   just after programming the TSC deadline timer

 - ~800 clock cycles gain (25% reduction in latency) in the best case
   where the test busy waits.

 I removed the VMX bits from Yunhong's patch, to concentrate them in the
 next patch - Paolo]
Signed-off-by: NYunhong Jiang <yunhong.jiang@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The function to start the tsc deadline timer virtualization will be used
also by the pre_block hook when we use the preemption timer; change it
to a separate function. No logic changes.
Signed-off-by: NYunhong Jiang <yunhong.jiang@intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The new created_vcpus field makes it possible to avoid the race between
irqchip and VCPU creation in a much nicer way; just check under kvm->lock
whether a VCPU has already been created.

We can then remove KVM_APIC_ARCHITECTURE too, because at this point the
symbol is only governing the default definition of kvm_vcpu_compatible.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Signed-off-by: NAndrea Gelmini <andrea.gelmini@gelma.net>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/iommu.c includes <linux/intel-iommu.h> and <linux/dmar.h>, which
both are unnecessary, in fact incorrect to be here as they are intel specific.

Building kvm on x86 passed after removing above inclusion.
Signed-off-by: NKai Huang <kai.huang@linux.intel.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

The syzkaller folks reported a NULL pointer dereference that seems
to be cause by a race between KVM_CREATE_IRQCHIP and KVM_CREATE_PIT2.
The former takes kvm->lock (except when registering the devices,
which needs kvm->slots_lock); the latter takes kvm->slots_lock only.
Change KVM_CREATE_PIT2 to follow the same model as KVM_CREATE_IRQCHIP.

Testcase:

    #include <pthread.h>
    #include <linux/kvm.h>
    #include <fcntl.h>
    #include <sys/ioctl.h>
    #include <stdint.h>
    #include <string.h>
    #include <stdlib.h>
    #include <sys/syscall.h>
    #include <unistd.h>

    long r[23];

    void* thr1(void* arg)
    {
        struct kvm_pit_config pitcfg = { .flags = 4 };
        switch ((long)arg) {
        case 0: r[2]  = open("/dev/kvm", O_RDONLY|O_ASYNC);    break;
        case 1: r[3]  = ioctl(r[2], KVM_CREATE_VM, 0);         break;
        case 2: r[4]  = ioctl(r[3], KVM_CREATE_IRQCHIP, 0);    break;
        case 3: r[22] = ioctl(r[3], KVM_CREATE_PIT2, &pitcfg); break;
        }
        return 0;
    }

    int main(int argc, char **argv)
    {
        long i;
        pthread_t th[4];

        memset(r, -1, sizeof(r));
        for (i = 0; i < 4; i++) {
            pthread_create(&th[i], 0, thr, (void*)i);
            if (argc > 1 && rand()%2) usleep(rand()%1000);
        }
        usleep(20000);
        return 0;
    }
Reported-by: NDmitry Vyukov <dvyukov@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Make the function names more similar between KVM_REQ_NMI and KVM_REQ_SMI.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

If the processor exits to KVM while delivering an interrupt,
the hypervisor then requeues the interrupt for the next vmentry.
Trying to enter SMM in this same window causes to enter non-root
mode in emulated SMM (i.e. with IF=0) and with a request to
inject an IRQ (i.e. with a valid VM-entry interrupt info field).
This is invalid guest state (SDM 26.3.1.4 "Check on Guest RIP
and RFLAGS") and the processor fails vmentry.

The fix is to defer the injection from KVM_REQ_SMI to KVM_REQ_EVENT,
like we already do for e.g. NMIs.  This patch doesn't change the
name of the process_smi function so that it can be applied to
stable releases.  The next patch will modify the names so that
process_nmi and process_smi handle respectively KVM_REQ_NMI and
KVM_REQ_SMI.

This is especially common with Windows, probably due to the
self-IPI trick that it uses to deliver deferred procedure
calls (DPCs).
Reported-by: NLaszlo Ersek <lersek@redhat.com>
Reported-by: NMichał Zegan <webczat_200@poczta.onet.pl>
Fixes: 64d60670
Cc: stable@vger.kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

MOV to DR6 or DR7 causes a #GP if an attempt is made to write a 1 to
any of bits 63:32.  However, this is not detected at KVM_SET_DEBUGREGS
time, and the next KVM_RUN oopses:

   general protection fault: 0000 [#1] SMP
   CPU: 2 PID: 14987 Comm: a.out Not tainted 4.4.9-300.fc23.x86_64 #1
   Hardware name: LENOVO 2325F51/2325F51, BIOS G2ET32WW (1.12 ) 05/30/2012
   [...]
   Call Trace:
    [<ffffffffa072c93d>] kvm_arch_vcpu_ioctl_run+0x141d/0x14e0 [kvm]
    [<ffffffffa071405d>] kvm_vcpu_ioctl+0x33d/0x620 [kvm]
    [<ffffffff81241648>] do_vfs_ioctl+0x298/0x480
    [<ffffffff812418a9>] SyS_ioctl+0x79/0x90
    [<ffffffff817a0f2e>] entry_SYSCALL_64_fastpath+0x12/0x71
   Code: 55 83 ff 07 48 89 e5 77 27 89 ff ff 24 fd 90 87 80 81 0f 23 fe 5d c3 0f 23 c6 5d c3 0f 23 ce 5d c3 0f 23 d6 5d c3 0f 23 de 5d c3 <0f> 23 f6 5d c3 0f 0b 66 66 66 66 66 2e 0f 1f 84 00 00 00 00 00
   RIP  [<ffffffff810639eb>] native_set_debugreg+0x2b/0x40
    RSP <ffff88005836bd50>

Testcase (beautified/reduced from syzkaller output):

    #include <unistd.h>
    #include <sys/syscall.h>
    #include <string.h>
    #include <stdint.h>
    #include <linux/kvm.h>
    #include <fcntl.h>
    #include <sys/ioctl.h>

    long r[8];

    int main()
    {
        struct kvm_debugregs dr = { 0 };

        r[2] = open("/dev/kvm", O_RDONLY);
        r[3] = ioctl(r[2], KVM_CREATE_VM, 0);
        r[4] = ioctl(r[3], KVM_CREATE_VCPU, 7);

        memcpy(&dr,
               "\x5d\x6a\x6b\xe8\x57\x3b\x4b\x7e\xcf\x0d\xa1\x72"
               "\xa3\x4a\x29\x0c\xfc\x6d\x44\x00\xa7\x52\xc7\xd8"
               "\x00\xdb\x89\x9d\x78\xb5\x54\x6b\x6b\x13\x1c\xe9"
               "\x5e\xd3\x0e\x40\x6f\xb4\x66\xf7\x5b\xe3\x36\xcb",
               48);
        r[7] = ioctl(r[4], KVM_SET_DEBUGREGS, &dr);
        r[6] = ioctl(r[4], KVM_RUN, 0);
    }
Reported-by: NDmitry Vyukov <dvyukov@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

This cannot be returned by KVM_GET_VCPU_EVENTS, so it is okay to return
EINVAL.  It causes a WARN from exception_type:

    WARNING: CPU: 3 PID: 16732 at arch/x86/kvm/x86.c:345 exception_type+0x49/0x50 [kvm]()
    CPU: 3 PID: 16732 Comm: a.out Tainted: G        W       4.4.6-300.fc23.x86_64 #1
    Hardware name: LENOVO 2325F51/2325F51, BIOS G2ET32WW (1.12 ) 05/30/2012
     0000000000000286 000000006308a48b ffff8800bec7fcf8 ffffffff813b542e
     0000000000000000 ffffffffa0966496 ffff8800bec7fd30 ffffffff810a40f2
     ffff8800552a8000 0000000000000000 00000000002c267c 0000000000000001
    Call Trace:
     [<ffffffff813b542e>] dump_stack+0x63/0x85
     [<ffffffff810a40f2>] warn_slowpath_common+0x82/0xc0
     [<ffffffff810a423a>] warn_slowpath_null+0x1a/0x20
     [<ffffffffa0924809>] exception_type+0x49/0x50 [kvm]
     [<ffffffffa0934622>] kvm_arch_vcpu_ioctl_run+0x10a2/0x14e0 [kvm]
     [<ffffffffa091c04d>] kvm_vcpu_ioctl+0x33d/0x620 [kvm]
     [<ffffffff81241248>] do_vfs_ioctl+0x298/0x480
     [<ffffffff812414a9>] SyS_ioctl+0x79/0x90
     [<ffffffff817a04ee>] entry_SYSCALL_64_fastpath+0x12/0x71
    ---[ end trace b1a0391266848f50 ]---

Testcase (beautified/reduced from syzkaller output):

    #include <unistd.h>
    #include <sys/syscall.h>
    #include <string.h>
    #include <stdint.h>
    #include <fcntl.h>
    #include <sys/ioctl.h>
    #include <linux/kvm.h>

    long r[31];

    int main()
    {
        memset(r, -1, sizeof(r));
        r[2] = open("/dev/kvm", O_RDONLY);
        r[3] = ioctl(r[2], KVM_CREATE_VM, 0);
        r[7] = ioctl(r[3], KVM_CREATE_VCPU, 0);

        struct kvm_vcpu_events ve = {
                .exception.injected = 1,
                .exception.nr = 0xd4
        };
        r[27] = ioctl(r[7], KVM_SET_VCPU_EVENTS, &ve);
        r[30] = ioctl(r[7], KVM_RUN, 0);
        return 0;
    }
Reported-by: NDmitry Vyukov <dvyukov@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

This causes an ugly dmesg splat.  Beautified syzkaller testcase:

    #include <unistd.h>
    #include <sys/syscall.h>
    #include <sys/ioctl.h>
    #include <fcntl.h>
    #include <linux/kvm.h>

    long r[8];

    int main()
    {
        struct kvm_cpuid2 c = { 0 };
        r[2] = open("/dev/kvm", O_RDWR);
        r[3] = ioctl(r[2], KVM_CREATE_VM, 0);
        r[4] = ioctl(r[3], KVM_CREATE_VCPU, 0x8);
        r[7] = ioctl(r[4], KVM_SET_CPUID, &c);
        return 0;
    }
Reported-by: NDmitry Vyukov <dvyukov@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Found by syzkaller:

    WARNING: CPU: 3 PID: 15175 at arch/x86/kvm/x86.c:7705 __x86_set_memory_region+0x1dc/0x1f0 [kvm]()
    CPU: 3 PID: 15175 Comm: a.out Tainted: G        W       4.4.6-300.fc23.x86_64 #1
    Hardware name: LENOVO 2325F51/2325F51, BIOS G2ET32WW (1.12 ) 05/30/2012
     0000000000000286 00000000950899a7 ffff88011ab3fbf0 ffffffff813b542e
     0000000000000000 ffffffffa0966496 ffff88011ab3fc28 ffffffff810a40f2
     00000000000001fd 0000000000003000 ffff88014fc50000 0000000000000000
    Call Trace:
     [<ffffffff813b542e>] dump_stack+0x63/0x85
     [<ffffffff810a40f2>] warn_slowpath_common+0x82/0xc0
     [<ffffffff810a423a>] warn_slowpath_null+0x1a/0x20
     [<ffffffffa09251cc>] __x86_set_memory_region+0x1dc/0x1f0 [kvm]
     [<ffffffffa092521b>] x86_set_memory_region+0x3b/0x60 [kvm]
     [<ffffffffa09bb61c>] vmx_set_tss_addr+0x3c/0x150 [kvm_intel]
     [<ffffffffa092f4d4>] kvm_arch_vm_ioctl+0x654/0xbc0 [kvm]
     [<ffffffffa091d31a>] kvm_vm_ioctl+0x9a/0x6f0 [kvm]
     [<ffffffff81241248>] do_vfs_ioctl+0x298/0x480
     [<ffffffff812414a9>] SyS_ioctl+0x79/0x90
     [<ffffffff817a04ee>] entry_SYSCALL_64_fastpath+0x12/0x71

Testcase:

    #include <unistd.h>
    #include <sys/ioctl.h>
    #include <fcntl.h>
    #include <string.h>
    #include <linux/kvm.h>

    long r[8];

    int main()
    {
        memset(r, -1, sizeof(r));
	r[2] = open("/dev/kvm", O_RDONLY|O_TRUNC);
        r[3] = ioctl(r[2], KVM_CREATE_VM, 0x0ul);
        r[5] = ioctl(r[3], KVM_SET_TSS_ADDR, 0x20000000ul);
        r[7] = ioctl(r[3], KVM_SET_TSS_ADDR, 0x20000000ul);
        return 0;
    }
Reported-by: NDmitry Vyukov <dvyukov@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Intel CPUs having Turbo Boost feature implement an MSR to provide a
control interface via rdmsr/wrmsr instructions. One could detect the
presence of this feature by issuing one of these instructions and
handling the #GP exception which is generated in case the referenced MSR
is not implemented by the CPU.

KVM's vCPU model behaves exactly as a real CPU in this case by injecting
a fault when MSR_IA32_PERF_CTL is called (which KVM does not support).
However, some operating systems use this register during an early boot
stage in which their kernel is not capable of handling #GP correctly,
causing #DP and finally a triple fault effectively resetting the vCPU.

This patch implements a dummy handler for MSR_IA32_PERF_CTL to avoid the
crashes.
Signed-off-by: NDmitry Bilunov <kmeaw@yandex-team.ru>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

In theory, nothing prevents the compiler from write-tearing PTEs, or
split PTE writes. These partially-modified PTEs can be fetched by other
cores and cause mayhem. I have not really encountered such case in
real-life, but it does seem possible.

For example, the compiler may try to do something creative for
kvm_set_pte_rmapp() and perform multiple writes to the PTE.
Signed-off-by: NNadav Amit <nadav.amit@gmail.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

The function to update APICv on/off state (in particular, to deactivate
it when enabling Hyper-V SynIC) is incomplete: it doesn't adjust
APICv-related fields among secondary processor-based VM-execution
controls.  As a result, Windows 2012 guests get stuck when SynIC-based
auto-EOI interrupt intersected with e.g. an IPI in the guest.

In addition, the MSR intercept bitmap isn't updated every time "virtualize
x2APIC mode" is toggled.  This path can only be triggered by a malicious
guest, because Windows didn't use x2APIC but rather their own synthetic
APIC access MSRs; however a guest running in a SynIC-enabled VM could
switch to x2APIC and thus obtain direct access to host APIC MSRs
(CVE-2016-4440).

The patch fixes those omissions.
Signed-off-by: NRoman Kagan <rkagan@virtuozzo.com>
Reported-by: NSteve Rutherford <srutherford@google.com>
Reported-by: NYang Zhang <yang.zhang.wz@gmail.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

These were supposed to be a bitwise operation but there is a typo.
The result is mostly harmless, but sparse correctly complains.

Fixes: 44a95dae ('KVM: x86: Detect and Initialize AVIC support')
Fixes: 18f40c53 ('svm: Add VMEXIT handlers for AVIC')
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

MSR 0x2f8 accessed the 124th Variable Range MTRR ever since MTRR support
was introduced by 9ba075a6 ("KVM: MTRR support").

0x2f8 became harmful when 910a6aae ("KVM: MTRR: exactly define the
size of variable MTRRs") shrinked the array of VR MTRRs from 256 to 8,
which made access to index 124 out of bounds.  The surrounding code only
WARNs in this situation, thus the guest gained a limited read/write
access to struct kvm_arch_vcpu.

0x2f8 is not a valid VR MTRR MSR, because KVM has/advertises only 16 VR
MTRR MSRs, 0x200-0x20f.  Every VR MTRR is set up using two MSRs, 0x2f8
was treated as a PHYSBASE and 0x2f9 would be its PHYSMASK, but 0x2f9 was
not implemented in KVM, therefore 0x2f8 could never do anything useful
and getting rid of it is safe.

This fixes CVE-2016-3713.

Fixes: 910a6aae ("KVM: MTRR: exactly define the size of variable MTRRs")
Cc: stable@vger.kernel.org
Reported-by: NDavid Matlack <dmatlack@google.com>
Signed-off-by: NAndy Honig <ahonig@google.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Neither APICv nor AVIC actually need the first argument of
hwapic_isr_update, but the vCPU makes more sense than passing the
pointer to the whole virtual machine!  In fact in the APICv case it's
just happening that the vCPU is used implicitly, through the loaded VMCS.

The second argument instead is named differently, make it consistent.
Reviewed-by: NRadim Krčmář <rkrcmar@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

When a vcpu is loaded/unloaded to a physical core, we need to update
host physical APIC ID information in the Physical APIC-ID table
accordingly.

Also, when vCPU is blocking/un-blocking (due to halt instruction),
we need to make sure that the is-running bit in set accordingly in the
physical APIC-ID table.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: NRadim Krčmář <rkrcmar@redhat.com>
[Return void from new functions, add WARN_ON when they returned negative
 errno; split load and put into separate function as they have almost
 nothing in common. - Paolo]
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

When enable AVIC:
    * Do not intercept CR8 since this should be handled by AVIC HW.
    * Also, we don't need to sync cr8/V_TPR and APIC backing page.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
[Rename svm_in_nested_interrupt_shadow to svm_nested_virtualize_tpr. - Paolo]
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Since AVIC only virtualizes xAPIC hardware for the guest, this patch
disable x2APIC support in guest CPUID.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Adding kvm_x86_ops hooks to allow APICv to do post state restore.
This is required to support VM save and restore feature.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

This patch introduces VMEXIT handlers, avic_incomplete_ipi_interception()
and avic_unaccelerated_access_interception() along with two trace points
(trace_kvm_avic_incomplete_ipi and trace_kvm_avic_unaccelerated_access).
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

This patch introduces a new mechanism to inject interrupt using AVIC.
Since VINTR is not supported when enable AVIC, we need to inject
interrupt via APIC backing page instead.

This patch also adds support for AVIC doorbell, which is used by
KVM to signal a running vcpu to check IRR for injected interrupts.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

This patch introduces AVIC-related data structure, and AVIC
initialization code.

There are three main data structures for AVIC:
    * Virtual APIC (vAPIC) backing page (per-VCPU)
    * Physical APIC ID table (per-VM)
    * Logical APIC ID table (per-VM)

Currently, AVIC is disabled by default. Users can manually
enable AVIC via kernel boot option kvm-amd.avic=1 or during
kvm-amd module loading with parameter avic=1.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
[Avoid extra indentation (Boris). - Paolo]
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Adding function pointers in struct kvm_x86_ops for processor-specific
layer to provide hooks for when KVM initialize and destroy VM.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Rename kvm_apic_get_reg to kvm_lapic_get_reg to be consistent with
the existing kvm_lapic_set_reg counterpart.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Exporting LAPIC utility functions and macros for re-use in SVM code.
Signed-off-by: NSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: NRadim Krčmář <rkrcmar@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Some wakeups should not be considered a sucessful poll. For example on
s390 I/O interrupts are usually floating, which means that _ALL_ CPUs
would be considered runnable - letting all vCPUs poll all the time for
transactional like workload, even if one vCPU would be enough.
This can result in huge CPU usage for large guests.
This patch lets architectures provide a way to qualify wakeups if they
should be considered a good/bad wakeups in regard to polls.

For s390 the implementation will fence of halt polling for anything but
known good, single vCPU events. The s390 implementation for floating
interrupts does a wakeup for one vCPU, but the interrupt will be delivered
by whatever CPU checks first for a pending interrupt. We prefer the
woken up CPU by marking the poll of this CPU as "good" poll.
This code will also mark several other wakeup reasons like IPI or
expired timers as "good". This will of course also mark some events as
not sucessful. As  KVM on z runs always as a 2nd level hypervisor,
we prefer to not poll, unless we are really sure, though.

This patch successfully limits the CPU usage for cases like uperf 1byte
transactional ping pong workload or wakeup heavy workload like OLTP
while still providing a proper speedup.

This also introduced a new vcpu stat "halt_poll_no_tuning" that marks
wakeups that are considered not good for polling.
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Radim Krčmář <rkrcmar@redhat.com> (for an earlier version)
Cc: David Matlack <dmatlack@google.com>
Cc: Wanpeng Li <kernellwp@gmail.com>
[Rename config symbol. - Paolo]
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

If we don't support a mechanism for bypassing IRQs, don't register as
a consumer.  This eliminates meaningless dev_info()s when the connect
fails between producer and consumer, such as on AMD systems where
kvm_x86_ops->update_pi_irte is not implemented
Signed-off-by: NAlex Williamson <alex.williamson@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The kbuild test robot reported this objtool warning [1]:

  arch/x86/kvm/emulate.o: warning: objtool: fastop()+0x69: call without frame pointer save/setup

The issue seems to be caused by CONFIG_PROFILE_ALL_BRANCHES.  With that
option, for some reason gcc decides not to create a stack frame in
fastop() before doing the inline asm call, which can result in a bad
stack trace.

Force a stack frame to be created if CONFIG_FRAME_POINTER is enabled by
listing the stack pointer as an output operand for the inline asm
statement.

This change has no effect for !CONFIG_PROFILE_ALL_BRANCHES.

[1] https://lists.01.org/pipermail/kbuild-all/2016-March/018249.htmlReported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NJosh Poimboeuf <jpoimboe@redhat.com>
Acked-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

After the THP refcounting change, obtaining a compound pages from
get_user_pages() no longer allows us to assume the entire compound page
is immediately mappable from a secondary MMU.

A secondary MMU doesn't want to call get_user_pages() more than once for
each compound page, in order to know if it can map the whole compound
page.  So a secondary MMU needs to know from a single get_user_pages()
invocation when it can map immediately the entire compound page to avoid
a flood of unnecessary secondary MMU faults and spurious
atomic_inc()/atomic_dec() (pages don't have to be pinned by MMU notifier
users).

Ideally instead of the page->_mapcount < 1 check, get_user_pages()
should return the granularity of the "page" mapping in the "mm" passed
to get_user_pages().  However it's non trivial change to pass the "pmd"
status belonging to the "mm" walked by get_user_pages up the stack (up
to the caller of get_user_pages).  So the fix just checks if there is
not a single pte mapping on the page returned by get_user_pages, and in
turn if the caller can assume that the whole compound page is mapped in
the current "mm" (in a pmd_trans_huge()).  In such case the entire
compound page is safe to map into the secondary MMU without additional
get_user_pages() calls on the surrounding tail/head pages.  In addition
of being faster, not having to run other get_user_pages() calls also
reduces the memory footprint of the secondary MMU fault in case the pmd
split happened as result of memory pressure.

Without this fix after a MADV_DONTNEED (like invoked by QEMU during
postcopy live migration or balloning) or after generic swapping (with a
failure in split_huge_page() that would only result in pmd splitting and
not a physical page split), KVM would map the whole compound page into
the shadow pagetables, despite regular faults or userfaults (like
UFFDIO_COPY) may map regular pages into the primary MMU as result of the
pte faults, leading to the guest mode and userland mode going out of
sync and not working on the same memory at all times.

Any other secondary MMU notifier manager (KVM is just one of the many
MMU notifier users) will need the same information if it doesn't want to
run a flood of get_user_pages_fast and it can support multiple
granularity in the secondary MMU mappings, so I think it is justified to
be exposed not just to KVM.

The other option would be to move transparent_hugepage_adjust to
mm/huge_memory.c but that currently has all kind of KVM data structures
in it, so it's definitely not a cut-and-paste work, so I couldn't do a
fix as cleaner as this one for 4.6.
Signed-off-by: NAndrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: "Li, Liang Z" <liang.z.li@intel.com>
Cc: Amit Shah <amit.shah@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Guest should only trust data to be valid when version haven't changed
before and after reads of steal time. Besides not changing, it has to
be an even number. Hypervisor may write an odd number to version field
to indicate that an update is in progress.

kvm_steal_clock() in guest has already done the read side, make write
side in hypervisor more robust by following the above rule.
Reviewed-by: NWincy Van <fanwenyi0529@gmail.com>
Signed-off-by: NWanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Commit d28bc9dd reversed the order of two lines which initialize cr0,
allowing the current (old) cr0 value to mess up vcpu initialization.
This was observed in the checks for cr0 X86_CR0_WP bit in the context of
kvm_mmu_reset_context(). Besides, setting vcpu->arch.cr0 after vmx_set_cr0()
is completely redundant. Change the order back to ensure proper vcpu
initialization.

The combination of booting with ovmf firmware when guest vcpus > 1 and kvm's
ept=N option being set results in a VM-entry failure. This patch fixes that.

Fixes: d28bc9dd ("KVM: x86: INIT and reset sequences are different")
Cc: stable@vger.kernel.org
Signed-off-by: NBruce Rogers <brogers@suse.com>
Signed-off-by: NRadim Krčmář <rkrcmar@redhat.com>

Unlike ds and es, these are base addresses, not selectors.  Rename
them so their meaning is more obvious.

On x86_32, the field is still called fs.  Fixing that could make sense
as a future cleanup.
Signed-off-by: NAndy Lutomirski <luto@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/69a18a51c4cba0ce29a241e570fc618ad721d908.1461698311.git.luto@kernel.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>

Some versions of Intel PT do not support tracing across VMXON, more
specifically, VMXON will clear TraceEn control bit and any attempt to
set it before VMXOFF will throw a #GP, which in the current state of
things will crash the kernel. Namely:

  $ perf record -e intel_pt// kvm -nographic

on such a machine will kill it.

To avoid this, notify the intel_pt driver before VMXON and after
VMXOFF so that it knows when not to enable itself.
Signed-off-by: NAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: hpa@zytor.com
Link: http://lkml.kernel.org/r/87oa9dwrfk.fsf@ashishki-desk.ger.corp.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

kvm_make_request and kvm_check_request imply a producer-consumer
relationship; add implicit memory barriers to them.  There was indeed
already a place that was adding an explicit smp_mb() to order between
kvm_check_request and the processing of the request.  That memory
barrier can be removed (as an added benefit, kvm_check_request can use
smp_mb__after_atomic which is free on x86).
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

The obsolete sp should not be used on current vCPUs and should not hurt
vCPU's running, so skip it from for_each_gfn_sp() and
for_each_gfn_indirect_valid_sp()

The side effort is we will double check role.invalid in kvm_mmu_get_page()
but i think it is okay as role is well cached
Signed-off-by: NXiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Since accumulate_steal_time is now only called in record_steal_time, it
doesn't quite make sense to put the delta calculation in a separate
function. The function could be called thousands of times before guest
enables the steal time MSR (though the compiler may optimize out this
function call). And after it's enabled, the MSR enable bit is tested twice
every time. Removing the accumulate_steal_time function also avoids the
necessity of having the accum_steal field.
Signed-off-by: NLiang Chen <liangchen.linux@gmail.com>
Signed-off-by: NGavin Guo <gavin.guo@canonical.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

This patch fix spelling typos found in printk
within various part of the kernel sources.
Signed-off-by: NMasanari Iida <standby24x7@gmail.com>
Acked-by: NRandy Dunlap <rdunlap@infradead.org>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>