From: Wanpeng Li <[email protected]>
Reported by syzkaller:
WARNING: CPU: 1 PID: 27742 at arch/x86/kvm/vmx.c:11029
nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
CPU: 1 PID: 27742 Comm: a.out Not tainted 4.10.0+ #229
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:15 [inline]
dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
panic+0x1fb/0x412 kernel/panic.c:179
__warn+0x1c4/0x1e0 kernel/panic.c:540
warn_slowpath_null+0x2c/0x40 kernel/panic.c:583
nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
vmx_leave_nested arch/x86/kvm/vmx.c:11136 [inline]
vmx_set_msr+0x1565/0x1910 arch/x86/kvm/vmx.c:3324
kvm_set_msr+0xd4/0x170 arch/x86/kvm/x86.c:1099
do_set_msr+0x11e/0x190 arch/x86/kvm/x86.c:1128
__msr_io arch/x86/kvm/x86.c:2577 [inline]
msr_io+0x24b/0x450 arch/x86/kvm/x86.c:2614
kvm_arch_vcpu_ioctl+0x35b/0x46a0 arch/x86/kvm/x86.c:3497
kvm_vcpu_ioctl+0x232/0x1120 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2721
vfs_ioctl fs/ioctl.c:43 [inline]
do_vfs_ioctl+0x1bf/0x1790 fs/ioctl.c:683
SYSC_ioctl fs/ioctl.c:698 [inline]
SyS_ioctl+0x8f/0xc0 fs/ioctl.c:689
entry_SYSCALL_64_fastpath+0x1f/0xc2
The syzkaller folks reported a nested_run_pending warning during userspace
clear VMX capability which is exposed to L1 before.
The warning gets thrown while doing
(*(uint32_t*)0x20aecfe8 = (uint32_t)0x1);
(*(uint32_t*)0x20aecfec = (uint32_t)0x0);
(*(uint32_t*)0x20aecff0 = (uint32_t)0x3a);
(*(uint32_t*)0x20aecff4 = (uint32_t)0x0);
(*(uint64_t*)0x20aecff8 = (uint64_t)0x0);
r[29] = syscall(__NR_ioctl, r[4], 0x4008ae89ul,
0x20aecfe8ul, 0, 0, 0, 0, 0, 0);
i.e. KVM_SET_MSR ioctl with
struct kvm_msrs {
.nmsrs = 1,
.pad = 0,
.entries = {
{.index = MSR_IA32_FEATURE_CONTROL,
.reserved = 0,
.data = 0}
}
}
The VMLANCH/VMRESUME emulation should be stopped since the CPU is going to
reset here. This patch resets the nested_run_pending since the CPU is going
to be reset hence there should be nothing pending.
Reported-by: Dmitry Vyukov <[email protected]>
Suggested-by: Radim Krčmář <[email protected]>
Cc: Paolo Bonzini <[email protected]>
Cc: Radim Krčmář <[email protected]>
Cc: Dmitry Vyukov <[email protected]>
Cc: David Hildenbrand <[email protected]>
Signed-off-by: Wanpeng Li <[email protected]>
---
v2 -> v3:
* move the reset to vmx_leave_nested()
v1 -> v2:
* cleanup comments format
arch/x86/kvm/vmx.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3b626d6..ab33858 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11107,8 +11107,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
*/
static void vmx_leave_nested(struct kvm_vcpu *vcpu)
{
- if (is_guest_mode(vcpu))
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.nested_run_pending = 0;
nested_vmx_vmexit(vcpu, -1, 0, 0);
+ }
free_nested(to_vmx(vcpu));
}
--
2.7.4
Am 06.03.2017 um 13:03 schrieb Wanpeng Li:
> From: Wanpeng Li <[email protected]>
>
> Reported by syzkaller:
>
> WARNING: CPU: 1 PID: 27742 at arch/x86/kvm/vmx.c:11029
> nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
> CPU: 1 PID: 27742 Comm: a.out Not tainted 4.10.0+ #229
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:15 [inline]
> dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
> panic+0x1fb/0x412 kernel/panic.c:179
> __warn+0x1c4/0x1e0 kernel/panic.c:540
> warn_slowpath_null+0x2c/0x40 kernel/panic.c:583
> nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
> vmx_leave_nested arch/x86/kvm/vmx.c:11136 [inline]
> vmx_set_msr+0x1565/0x1910 arch/x86/kvm/vmx.c:3324
> kvm_set_msr+0xd4/0x170 arch/x86/kvm/x86.c:1099
> do_set_msr+0x11e/0x190 arch/x86/kvm/x86.c:1128
> __msr_io arch/x86/kvm/x86.c:2577 [inline]
> msr_io+0x24b/0x450 arch/x86/kvm/x86.c:2614
> kvm_arch_vcpu_ioctl+0x35b/0x46a0 arch/x86/kvm/x86.c:3497
> kvm_vcpu_ioctl+0x232/0x1120 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2721
> vfs_ioctl fs/ioctl.c:43 [inline]
> do_vfs_ioctl+0x1bf/0x1790 fs/ioctl.c:683
> SYSC_ioctl fs/ioctl.c:698 [inline]
> SyS_ioctl+0x8f/0xc0 fs/ioctl.c:689
> entry_SYSCALL_64_fastpath+0x1f/0xc2
>
> The syzkaller folks reported a nested_run_pending warning during userspace
> clear VMX capability which is exposed to L1 before.
>
> The warning gets thrown while doing
>
> (*(uint32_t*)0x20aecfe8 = (uint32_t)0x1);
> (*(uint32_t*)0x20aecfec = (uint32_t)0x0);
> (*(uint32_t*)0x20aecff0 = (uint32_t)0x3a);
> (*(uint32_t*)0x20aecff4 = (uint32_t)0x0);
> (*(uint64_t*)0x20aecff8 = (uint64_t)0x0);
> r[29] = syscall(__NR_ioctl, r[4], 0x4008ae89ul,
> 0x20aecfe8ul, 0, 0, 0, 0, 0, 0);
>
> i.e. KVM_SET_MSR ioctl with
>
> struct kvm_msrs {
> .nmsrs = 1,
> .pad = 0,
> .entries = {
> {.index = MSR_IA32_FEATURE_CONTROL,
> .reserved = 0,
> .data = 0}
> }
> }
>
> The VMLANCH/VMRESUME emulation should be stopped since the CPU is going to
> reset here. This patch resets the nested_run_pending since the CPU is going
> to be reset hence there should be nothing pending.
>
> Reported-by: Dmitry Vyukov <[email protected]>
> Suggested-by: Radim Krčmář <[email protected]>
> Cc: Paolo Bonzini <[email protected]>
> Cc: Radim Krčmář <[email protected]>
> Cc: Dmitry Vyukov <[email protected]>
> Cc: David Hildenbrand <[email protected]>
> Signed-off-by: Wanpeng Li <[email protected]>
> ---
> v2 -> v3:
> * move the reset to vmx_leave_nested()
> v1 -> v2:
> * cleanup comments format
>
> arch/x86/kvm/vmx.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 3b626d6..ab33858 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -11107,8 +11107,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
> */
> static void vmx_leave_nested(struct kvm_vcpu *vcpu)
> {
> - if (is_guest_mode(vcpu))
> + if (is_guest_mode(vcpu)) {
> + to_vmx(vcpu)->nested.nested_run_pending = 0;
> nested_vmx_vmexit(vcpu, -1, 0, 0);
> + }
> free_nested(to_vmx(vcpu));
> }
>
>
Reviewed-by: David Hildenbrand <[email protected]>
--
Thanks,
David
On Mon, Mar 6, 2017 at 4:33 AM, David Hildenbrand <[email protected]> wrote:
> Am 06.03.2017 um 13:03 schrieb Wanpeng Li:
>> From: Wanpeng Li <[email protected]>
>>
>> Reported by syzkaller:
>>
>> WARNING: CPU: 1 PID: 27742 at arch/x86/kvm/vmx.c:11029
>> nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
>> CPU: 1 PID: 27742 Comm: a.out Not tainted 4.10.0+ #229
>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>> Call Trace:
>> __dump_stack lib/dump_stack.c:15 [inline]
>> dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
>> panic+0x1fb/0x412 kernel/panic.c:179
>> __warn+0x1c4/0x1e0 kernel/panic.c:540
>> warn_slowpath_null+0x2c/0x40 kernel/panic.c:583
>> nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
>> vmx_leave_nested arch/x86/kvm/vmx.c:11136 [inline]
>> vmx_set_msr+0x1565/0x1910 arch/x86/kvm/vmx.c:3324
>> kvm_set_msr+0xd4/0x170 arch/x86/kvm/x86.c:1099
>> do_set_msr+0x11e/0x190 arch/x86/kvm/x86.c:1128
>> __msr_io arch/x86/kvm/x86.c:2577 [inline]
>> msr_io+0x24b/0x450 arch/x86/kvm/x86.c:2614
>> kvm_arch_vcpu_ioctl+0x35b/0x46a0 arch/x86/kvm/x86.c:3497
>> kvm_vcpu_ioctl+0x232/0x1120 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2721
>> vfs_ioctl fs/ioctl.c:43 [inline]
>> do_vfs_ioctl+0x1bf/0x1790 fs/ioctl.c:683
>> SYSC_ioctl fs/ioctl.c:698 [inline]
>> SyS_ioctl+0x8f/0xc0 fs/ioctl.c:689
>> entry_SYSCALL_64_fastpath+0x1f/0xc2
>>
>> The syzkaller folks reported a nested_run_pending warning during userspace
>> clear VMX capability which is exposed to L1 before.
>>
>> The warning gets thrown while doing
>>
>> (*(uint32_t*)0x20aecfe8 = (uint32_t)0x1);
>> (*(uint32_t*)0x20aecfec = (uint32_t)0x0);
>> (*(uint32_t*)0x20aecff0 = (uint32_t)0x3a);
>> (*(uint32_t*)0x20aecff4 = (uint32_t)0x0);
>> (*(uint64_t*)0x20aecff8 = (uint64_t)0x0);
>> r[29] = syscall(__NR_ioctl, r[4], 0x4008ae89ul,
>> 0x20aecfe8ul, 0, 0, 0, 0, 0, 0);
>>
>> i.e. KVM_SET_MSR ioctl with
>>
>> struct kvm_msrs {
>> .nmsrs = 1,
>> .pad = 0,
>> .entries = {
>> {.index = MSR_IA32_FEATURE_CONTROL,
>> .reserved = 0,
>> .data = 0}
>> }
>> }
>>
>> The VMLANCH/VMRESUME emulation should be stopped since the CPU is going to
>> reset here. This patch resets the nested_run_pending since the CPU is going
>> to be reset hence there should be nothing pending.
>>
>> Reported-by: Dmitry Vyukov <[email protected]>
>> Suggested-by: Radim Krčmář <[email protected]>
>> Cc: Paolo Bonzini <[email protected]>
>> Cc: Radim Krčmář <[email protected]>
>> Cc: Dmitry Vyukov <[email protected]>
>> Cc: David Hildenbrand <[email protected]>
>> Signed-off-by: Wanpeng Li <[email protected]>
>> ---
>> v2 -> v3:
>> * move the reset to vmx_leave_nested()
>> v1 -> v2:
>> * cleanup comments format
>>
>> arch/x86/kvm/vmx.c | 4 +++-
>> 1 file changed, 3 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
>> index 3b626d6..ab33858 100644
>> --- a/arch/x86/kvm/vmx.c
>> +++ b/arch/x86/kvm/vmx.c
>> @@ -11107,8 +11107,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
>> */
>> static void vmx_leave_nested(struct kvm_vcpu *vcpu)
>> {
>> - if (is_guest_mode(vcpu))
>> + if (is_guest_mode(vcpu)) {
>> + to_vmx(vcpu)->nested.nested_run_pending = 0;
>> nested_vmx_vmexit(vcpu, -1, 0, 0);
>> + }
>> free_nested(to_vmx(vcpu));
>> }
>>
>>
>
> Reviewed-by: David Hildenbrand <[email protected]>
>
> --
> Thanks,
>
> David
This seems reasonable to me, and it should fix the issue exposed by
syzkaller--though I was never able to reproduce it.
Reviewed-by: Jim Mattson <[email protected]>
2017-03-06 04:03-0800, Wanpeng Li:
> From: Wanpeng Li <[email protected]>
>
> Reported by syzkaller:
>
> WARNING: CPU: 1 PID: 27742 at arch/x86/kvm/vmx.c:11029
> nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
> CPU: 1 PID: 27742 Comm: a.out Not tainted 4.10.0+ #229
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> Call Trace:
> __dump_stack lib/dump_stack.c:15 [inline]
> dump_stack+0x2ee/0x3ef lib/dump_stack.c:51
> panic+0x1fb/0x412 kernel/panic.c:179
> __warn+0x1c4/0x1e0 kernel/panic.c:540
> warn_slowpath_null+0x2c/0x40 kernel/panic.c:583
> nested_vmx_vmexit+0x5c35/0x74d0 arch/x86/kvm/vmx.c:11029
> vmx_leave_nested arch/x86/kvm/vmx.c:11136 [inline]
> vmx_set_msr+0x1565/0x1910 arch/x86/kvm/vmx.c:3324
> kvm_set_msr+0xd4/0x170 arch/x86/kvm/x86.c:1099
> do_set_msr+0x11e/0x190 arch/x86/kvm/x86.c:1128
> __msr_io arch/x86/kvm/x86.c:2577 [inline]
> msr_io+0x24b/0x450 arch/x86/kvm/x86.c:2614
> kvm_arch_vcpu_ioctl+0x35b/0x46a0 arch/x86/kvm/x86.c:3497
> kvm_vcpu_ioctl+0x232/0x1120 arch/x86/kvm/../../../virt/kvm/kvm_main.c:2721
> vfs_ioctl fs/ioctl.c:43 [inline]
> do_vfs_ioctl+0x1bf/0x1790 fs/ioctl.c:683
> SYSC_ioctl fs/ioctl.c:698 [inline]
> SyS_ioctl+0x8f/0xc0 fs/ioctl.c:689
> entry_SYSCALL_64_fastpath+0x1f/0xc2
>
> The syzkaller folks reported a nested_run_pending warning during userspace
> clear VMX capability which is exposed to L1 before.
>
> The warning gets thrown while doing
>
> (*(uint32_t*)0x20aecfe8 = (uint32_t)0x1);
> (*(uint32_t*)0x20aecfec = (uint32_t)0x0);
> (*(uint32_t*)0x20aecff0 = (uint32_t)0x3a);
> (*(uint32_t*)0x20aecff4 = (uint32_t)0x0);
> (*(uint64_t*)0x20aecff8 = (uint64_t)0x0);
> r[29] = syscall(__NR_ioctl, r[4], 0x4008ae89ul,
> 0x20aecfe8ul, 0, 0, 0, 0, 0, 0);
>
> i.e. KVM_SET_MSR ioctl with
>
> struct kvm_msrs {
> .nmsrs = 1,
> .pad = 0,
> .entries = {
> {.index = MSR_IA32_FEATURE_CONTROL,
> .reserved = 0,
> .data = 0}
> }
> }
>
> The VMLANCH/VMRESUME emulation should be stopped since the CPU is going to
> reset here. This patch resets the nested_run_pending since the CPU is going
> to be reset hence there should be nothing pending.
>
> Reported-by: Dmitry Vyukov <[email protected]>
> Suggested-by: Radim Krčmář <[email protected]>
> Cc: Paolo Bonzini <[email protected]>
> Cc: Radim Krčmář <[email protected]>
> Cc: Dmitry Vyukov <[email protected]>
> Cc: David Hildenbrand <[email protected]>
> Signed-off-by: Wanpeng Li <[email protected]>
> ---
Queued for 4.11-rc2, thanks.
> v2 -> v3:
> * move the reset to vmx_leave_nested()
> v1 -> v2:
> * cleanup comments format
>
> arch/x86/kvm/vmx.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 3b626d6..ab33858 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -11107,8 +11107,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
> */
> static void vmx_leave_nested(struct kvm_vcpu *vcpu)
> {
> - if (is_guest_mode(vcpu))
> + if (is_guest_mode(vcpu)) {
> + to_vmx(vcpu)->nested.nested_run_pending = 0;
> nested_vmx_vmexit(vcpu, -1, 0, 0);
> + }
> free_nested(to_vmx(vcpu));
> }
>
> --
> 2.7.4
>