[PATCH v2] KVM: nVMX: Fix trying to cancel vmlauch/vmresume
From: Wanpeng Li
Date: Fri Aug 18 2017 - 10:11:39 EST
From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
------------[ cut here ]------------
WARNING: CPU: 7 PID: 3861 at /home/kernel/ssd/kvm/arch/x86/kvm//vmx.c:11299 nested_vmx_vmexit+0x176e/0x1980 [kvm_intel]
CPU: 7 PID: 3861 Comm: qemu-system-x86 Tainted: G W OE 4.13.0-rc4+ #11
RIP: 0010:nested_vmx_vmexit+0x176e/0x1980 [kvm_intel]
Call Trace:
? kvm_multiple_exception+0x149/0x170 [kvm]
? handle_emulation_failure+0x79/0x230 [kvm]
? load_vmcs12_host_state+0xa80/0xa80 [kvm_intel]
? check_chain_key+0x137/0x1e0
? reexecute_instruction.part.168+0x130/0x130 [kvm]
nested_vmx_inject_exception_vmexit+0xb7/0x100 [kvm_intel]
? nested_vmx_inject_exception_vmexit+0xb7/0x100 [kvm_intel]
vmx_queue_exception+0x197/0x300 [kvm_intel]
kvm_arch_vcpu_ioctl_run+0x1b0c/0x2c90 [kvm]
? kvm_arch_vcpu_runnable+0x220/0x220 [kvm]
? preempt_count_sub+0x18/0xc0
? restart_apic_timer+0x17d/0x300 [kvm]
? kvm_lapic_restart_hv_timer+0x37/0x50 [kvm]
? kvm_arch_vcpu_load+0x1d8/0x350 [kvm]
kvm_vcpu_ioctl+0x4e4/0x910 [kvm]
? kvm_vcpu_ioctl+0x4e4/0x910 [kvm]
? kvm_dev_ioctl+0xbe0/0xbe0 [kvm]
The flag "nested_run_pending", which can override the decision of which should run
next, L1 or L2. nested_run_pending=1 means that we *must* run L2 next, not L1. This
is necessary in particular when L1 did a VMLAUNCH of L2 and therefore expects L2 to
be run (and perhaps be injected with an event it specified, etc.). Nested_run_pending
is especially intended to avoid switching to L1 in the injection decision-point.
I catch this in the queue exception path, this patch fixes it by requesting
an immediate VM exit from L2 and keeping the exception for L1 pending for a
subsequent nested VM exit.
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/svm.c | 6 ++++--
arch/x86/kvm/vmx.c | 15 ++++++++++-----
arch/x86/kvm/x86.c | 4 ++--
4 files changed, 17 insertions(+), 10 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6db0ed9..e1e6f00 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -962,7 +962,7 @@ struct kvm_x86_ops {
unsigned char *hypercall_addr);
void (*set_irq)(struct kvm_vcpu *vcpu);
void (*set_nmi)(struct kvm_vcpu *vcpu);
- void (*queue_exception)(struct kvm_vcpu *vcpu);
+ int (*queue_exception)(struct kvm_vcpu *vcpu);
void (*cancel_injection)(struct kvm_vcpu *vcpu);
int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
int (*nmi_allowed)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c21b49b..bee1937 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -632,7 +632,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
svm_set_interrupt_shadow(vcpu, 0);
}
-static void svm_queue_exception(struct kvm_vcpu *vcpu)
+static int svm_queue_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
unsigned nr = vcpu->arch.exception.nr;
@@ -646,7 +646,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu)
*/
if (!reinject &&
nested_svm_check_exception(svm, nr, has_error_code, error_code))
- return;
+ return 0;
if (nr == BP_VECTOR && !static_cpu_has(X86_FEATURE_NRIPS)) {
unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
@@ -669,6 +669,8 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu)
| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
| SVM_EVTINJ_TYPE_EXEPT;
svm->vmcb->control.event_inj_err = error_code;
+
+ return 0;
}
static void svm_init_erratum_383(void)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e398946..cd0ab5d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2500,7 +2500,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
return 0;
}
-static void vmx_queue_exception(struct kvm_vcpu *vcpu)
+static int vmx_queue_exception(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned nr = vcpu->arch.exception.nr;
@@ -2509,9 +2509,12 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
u32 error_code = vcpu->arch.exception.error_code;
u32 intr_info = nr | INTR_INFO_VALID_MASK;
- if (!reinject && is_guest_mode(vcpu) &&
- nested_vmx_check_exception(vcpu))
- return;
+ if (!reinject && is_guest_mode(vcpu)) {
+ if (vmx->nested.nested_run_pending)
+ return -EBUSY;
+ if (nested_vmx_check_exception(vcpu))
+ return 0;
+ }
if (has_error_code) {
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
@@ -2524,7 +2527,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
inc_eip = vcpu->arch.event_exit_inst_len;
if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE)
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
- return;
+ return 0;
}
if (kvm_exception_is_soft(nr)) {
@@ -2535,6 +2538,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
intr_info |= INTR_TYPE_HARD_EXCEPTION;
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
+
+ return 0;
}
static bool vmx_rdtscp_supported(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 008a0b1..8e53de2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6356,8 +6356,8 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
kvm_update_dr7(vcpu);
}
- kvm_x86_ops->queue_exception(vcpu);
- return 0;
+ r = kvm_x86_ops->queue_exception(vcpu);
+ return r;
}
if (vcpu->arch.nmi_injected) {
--
2.7.4