On 08/06/2017 11:30, Wanpeng Li wrote:
> However, I found that "nr == PF_VECTOR && vmx->apf_reason != 0" never be true
> in nested_vmx_check_exception(). SVM depends on the similar stuff in
> nested_svm_intercept() which makes me confusing how it can works. In addition,
> vmx/svm->apf_reason should be got in L1 since apf_reason.reason will make sense
> just in pv guest. So vmx/svm->apf_reason should always be 0 on L0.
I agree. My suggestion is a series like this:
1) remove all arguments except the first in
kvm_x86_ops->queue_exception: they can extract the arguments from
vcpu->arch.exception themselves
2) do the same in nested_{vmx,svm}_check_exception
3) add an async_page_fault member to vcpu->arch.exception
> I change the
> condition to "nr == PF_VECTOR && error_code == 0" to intercept async_pf, however,
> the below bug will be splatted:
Right, because error_code == 0 is a valid error code.
For stable releases, this should be enough:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ac7810513d0e..c5f0023bac2d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3689,6 +3689,9 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu)
kvm_event_needs_reinjection(vcpu)))
return false;
+ if (is_guest_mode(vcpu))
+ return false;
+
return kvm_x86_ops->interrupt_allowed(vcpu);
}
For proper nested async page fault support, you have to be careful,
because old KVM as L1 you might crash due to the BUG(enable_ept); my
suggestion is to add another flag bit to MSR_KVM_ASYNC_PF_EN.
If bit 2 is 1, async page faults are delivered to L1 as #PF vmexits; if
bit 2 is 0, can_do_async_pf returns 0 if in guest mode. When bit 2 is
1, async page fault exceptions override the usual exception/intercept
bitmaps, i.e. they always cause #PF vmexits. What do you think?
Thanks,
Paolo
> BUG: unable to handle kernel paging request at ffffe305770a87e0
> IP: kfree+0x6f/0x300
> PGD 0
> P4D 0
>
> Oops: 0000 [#1] PREEMPT SMP
> CPU: 3 PID: 2187 Comm: transhuge-stres Tainted: G OE 4.12.0-rc4+ #9
> task: ffff8a9214b58000 task.stack: ffffb46bc34e4000
> RIP: 0010:kfree+0x6f/0x300
> RSP: 0000:ffffb46bc34e7b28 EFLAGS: 00010086
> RAX: ffffe305770a87c0 RBX: ffffb46bc2a1fe70 RCX: 0000000000000001
> RDX: 0000757180000000 RSI: 00000000ffffffff RDI: 0000000000000096
> RBP: ffffb46bc34e7b50 R08: 0000000000000000 R09: 0000000000000001
> R10: ffffb46bc34e7ac8 R11: 68b9962a00000000 R12: 000000a7770a87c0
> R13: ffffffff90059b75 R14: ffffffff913466c0 R15: ffffe25e06f18000
> FS: 00007f1904ae7700(0000) GS:ffff8a921a800000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: ffffe305770a87e0 CR3: 000000040eb5c000 CR4: 00000000001426e0
> Call Trace:
> kvm_async_pf_task_wait+0xd5/0x280
> ? __this_cpu_preempt_check+0x13/0x20
> do_async_page_fault+0x77/0xb0
> ? do_async_page_fault+0x77/0xb0
> async_page_fault+0x28/0x30
>
> In additon, if svm->apf_reason doen't make sense on L0, then maybe it also will not
> work in the function nested_svm_exit_special().
>
> The patch below is uncompleted, and your inputs to improve it is a great appreciated.
The patch makes sense. Let's try to make more code common to VMX and
SVM too once the above is clarified.
Paolo
> Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx>
> Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
> ---
> arch/x86/kvm/vmx.c | 41 ++++++++++++++++++++++++++++++++---------
> 1 file changed, 32 insertions(+), 9 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index ca5d2b9..21a1b44 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -616,6 +616,7 @@ struct vcpu_vmx {
> bool emulation_required;
>
> u32 exit_reason;
> + u32 apf_reason;
>
> /* Posted interrupt descriptor */
> struct pi_desc pi_desc;
> @@ -2418,11 +2419,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
> * KVM wants to inject page-faults which it got to the guest. This function
> * checks whether in a nested guest, we need to inject them to L1 or L2.
> */
> -static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
> +static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
> {
> struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
>
> - if (!(vmcs12->exception_bitmap & (1u << nr)))
> + if (!((vmcs12->exception_bitmap & (1u << nr)) ||
> + (nr == PF_VECTOR && error_code == 0)))
> return 0;
>
> nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
> @@ -2439,7 +2441,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
> u32 intr_info = nr | INTR_INFO_VALID_MASK;
>
> if (!reinject && is_guest_mode(vcpu) &&
> - nested_vmx_check_exception(vcpu, nr))
> + nested_vmx_check_exception(vcpu, nr, error_code))
> return;
>
> if (has_error_code) {
> @@ -5646,14 +5648,31 @@ static int handle_exception(struct kvm_vcpu *vcpu)
> }
>
> if (is_page_fault(intr_info)) {
> - /* EPT won't cause page fault directly */
> - BUG_ON(enable_ept);
> cr2 = vmcs_readl(EXIT_QUALIFICATION);
> - trace_kvm_page_fault(cr2, error_code);
> + switch (vmx->apf_reason) {
> + default:
> + /* EPT won't cause page fault directly */
> + BUG_ON(enable_ept);
> + trace_kvm_page_fault(cr2, error_code);
>
> - if (kvm_event_needs_reinjection(vcpu))
> - kvm_mmu_unprotect_page_virt(vcpu, cr2);
> - return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
> + if (kvm_event_needs_reinjection(vcpu))
> + kvm_mmu_unprotect_page_virt(vcpu, cr2);
> + return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
> + break;
> + case KVM_PV_REASON_PAGE_NOT_PRESENT:
> + vmx->apf_reason = 0;
> + local_irq_disable();
> + kvm_async_pf_task_wait(cr2);
> + local_irq_enable();
> + break;
> + case KVM_PV_REASON_PAGE_READY:
> + vmx->apf_reason = 0;
> + local_irq_disable();
> + kvm_async_pf_task_wake(cr2);
> + local_irq_enable();
> + break;
> + }
> + return 0;
> }
>
> ex_no = intr_info & INTR_INFO_VECTOR_MASK;
> @@ -8600,6 +8619,10 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
> vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
> exit_intr_info = vmx->exit_intr_info;
>
> + /* if exit due to PF check for async PF */
> + if (is_page_fault(exit_intr_info))
> + vmx->apf_reason = kvm_read_and_reset_pf_reason();
> +
> /* Handle machine checks before interrupts are enabled */
> if (is_machine_check(exit_intr_info))
> kvm_machine_check();
>
