On 4/1/2022 7:07 AM, Sean Christopherson wrote:
On Fri, Mar 04, 2022, Zeng Guang wrote:
Upcoming Intel CPUs will support virtual x2APIC MSR writes to the vICR,
i.e. will trap and generate an APIC-write VM-Exit instead of intercepting
the WRMSR. Add support for handling "nodecode" x2APIC writes, which
were previously impossible.
Note, x2APIC MSR writes are 64 bits wide.
Signed-off-by: Zeng Guang <guang.zeng@xxxxxxxxx>
---
arch/x86/kvm/lapic.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 629c116b0d3e..22929b5b3f9b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -67,6 +67,7 @@ static bool lapic_timer_advance_dynamic __read_mostly;
#define LAPIC_TIMER_ADVANCE_NS_MAX 5000
/* step-by-step approximation to mitigate fluctuation */
#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data);
static inline void __kvm_lapic_set_reg(char *regs, int reg_off, u32 val)
{
@@ -2227,10 +2228,25 @@ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
/* emulate APIC access in a trap manner */
void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
{
- u32 val = kvm_lapic_get_reg(vcpu->arch.apic, offset);
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u64 val;
+
+ if (apic_x2apic_mode(apic)) {
+ /*
+ * When guest APIC is in x2APIC mode and IPI virtualization
+ * is enabled, accessing APIC_ICR may cause trap-like VM-exit
+ * on Intel hardware. Other offsets are not possible.
+ */
+ if (WARN_ON_ONCE(offset != APIC_ICR))
+ return;
- /* TODO: optimize to just emulate side effect w/o one more write */
- kvm_lapic_reg_write(vcpu->arch.apic, offset, val);
+ kvm_lapic_msr_read(apic, offset, &val);
+ kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32));
This needs to clear the APIC_ICR_BUSY bit. It'd also be nice to trace this write.
The easiest thing is to use kvm_x2apic_icr_write(). Kinda silly as it'll generate
an extra write, but on the plus side the TODO comment doesn't have to move :-D
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c4c3155d98db..58bf296ee313 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2230,6 +2230,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
struct kvm_lapic *apic = vcpu->arch.apic;
u64 val;
+ /* TODO: optimize to just emulate side effect w/o one more write */
if (apic_x2apic_mode(apic)) {
/*
* When guest APIC is in x2APIC mode and IPI virtualization
@@ -2240,10 +2241,9 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
return;
kvm_lapic_msr_read(apic, offset, &val);
- kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32));
+ kvm_x2apic_icr_write(apic, val);
As SDM section 10.12.9 "ICR Operation in X2APIC mode" says "Delivery status
bit is removed since it is not needed in x2APIC mode" , so that's not
necessary
to clear the APIC_ICR_BUSY bit here. Alternatively we can add trace to
this write
by hardware.
} else {
val = kvm_lapic_get_reg(apic, offset);
- /* TODO: optimize to just emulate side effect w/o one more write */
kvm_lapic_reg_write(apic, offset, (u32)val);
}
}
+ } else {
+ val = kvm_lapic_get_reg(apic, offset);
+ /* TODO: optimize to just emulate side effect w/o one more write */
+ kvm_lapic_reg_write(apic, offset, (u32)val);
+ }
}
EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode);
--
2.27.0
