KVM: x86: Re-split x2APIC ICR into ICR+ICR2 for AMD (x2AVIC)

Re-introduce the "split" x2APIC ICR storage that KVM used prior to Intel's
IPI virtualization support, but only for AMD. While not stated anywhere
in the APM, despite stating the ICR is a single 64-bit register, AMD CPUs
store the 64-bit ICR as two separate 32-bit values in ICR and ICR2. When
IPI virtualization (IPIv on Intel, all AVIC flavors on AMD) is enabled,
KVM needs to match CPU behavior as some ICR ICR writes will be handled by
the CPU, not by KVM.

Add a kvm_x86_ops knob to control the underlying format used by the CPU to
store the x2APIC ICR, and tune it to AMD vs. Intel regardless of whether
or not x2AVIC is enabled. If KVM is handling all ICR writes, the storage
format for x2APIC mode doesn't matter, and having the behavior follow AMD
versus Intel will provide better test coverage and ease debugging.

Fixes: 4d1d7942e36a ("KVM: SVM: Introduce logic to (de)activate x2AVIC mode")
Cc: [e-mail]
Cc: Maxim Levitsky <[e-mail]>
Cc: Suravee Suthikulpanit <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Sean Christopherson <[e-mail]>

arch/x86/include/asm/kvm_host.h

···
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
+
+	const bool x2apic_icr_is_split;
 	const unsigned long required_apicv_inhibits;
 	bool allow_apicv_in_x2apic_without_x2apic_virtualization;
 	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);

arch/x86/kvm/lapic.c

···
 	data &= ~APIC_ICR_BUSY;
 
 	kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32));
-	kvm_lapic_set_reg64(apic, APIC_ICR, data);
+	if (kvm_x86_ops.x2apic_icr_is_split) {
+		kvm_lapic_set_reg(apic, APIC_ICR, data);
+		kvm_lapic_set_reg(apic, APIC_ICR2, data >> 32);
+	} else {
+		kvm_lapic_set_reg64(apic, APIC_ICR, data);
+	}
 	trace_kvm_apic_write(APIC_ICR, data);
 	return 0;
+}
+
+static u64 kvm_x2apic_icr_read(struct kvm_lapic *apic)
+{
+	if (kvm_x86_ops.x2apic_icr_is_split)
+		return (u64)kvm_lapic_get_reg(apic, APIC_ICR) |
+		       (u64)kvm_lapic_get_reg(apic, APIC_ICR2) << 32;
+
+	return kvm_lapic_get_reg64(apic, APIC_ICR);
 }
 
 /* emulate APIC access in a trap manner */
···
 	 * maybe-unecessary write, and both are in the noise anyways.
 	 */
 	if (apic_x2apic_mode(apic) && offset == APIC_ICR)
-		WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)));
+		WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_x2apic_icr_read(apic)));
 	else
 		kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset));
 }
···
 
 		/*
 		 * In x2APIC mode, the LDR is fixed and based on the id.  And
-		 * ICR is internally a single 64-bit register, but needs to be
-		 * split to ICR+ICR2 in userspace for backwards compatibility.
+		 * if the ICR is _not_ split, ICR is internally a single 64-bit
+		 * register, but needs to be split to ICR+ICR2 in userspace for
+		 * backwards compatibility.
 		 */
-		if (set) {
+		if (set)
 			*ldr = kvm_apic_calc_x2apic_ldr(x2apic_id);
 
-			icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
-			      (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
-			__kvm_lapic_set_reg64(s->regs, APIC_ICR, icr);
-		} else {
-			icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
-			__kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
+		if (!kvm_x86_ops.x2apic_icr_is_split) {
+			if (set) {
+				icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
+				      (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
+				__kvm_lapic_set_reg64(s->regs, APIC_ICR, icr);
+			} else {
+				icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
+				__kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
+			}
 		}
 	}
 
···
 	u32 low;
 
 	if (reg == APIC_ICR) {
-		*data = kvm_lapic_get_reg64(apic, APIC_ICR);
+		*data = kvm_x2apic_icr_read(apic);
 		return 0;
 	}
 

arch/x86/kvm/svm/svm.c

···
 	.enable_nmi_window = svm_enable_nmi_window,
 	.enable_irq_window = svm_enable_irq_window,
 	.update_cr8_intercept = svm_update_cr8_intercept,
+
+	.x2apic_icr_is_split = true,
 	.set_virtual_apic_mode = avic_refresh_virtual_apic_mode,
 	.refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl,
 	.apicv_post_state_restore = avic_apicv_post_state_restore,

arch/x86/kvm/vmx/main.c

···
 	.enable_nmi_window = vmx_enable_nmi_window,
 	.enable_irq_window = vmx_enable_irq_window,
 	.update_cr8_intercept = vmx_update_cr8_intercept,
+
+	.x2apic_icr_is_split = false,
 	.set_virtual_apic_mode = vmx_set_virtual_apic_mode,
 	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
 	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,