[PATCH v4 1/3] KVM: nVMX: Add nested msr load/restore algorithm

[Eugene Korenevsky <ekorenevsky@gmail.com>]

Several hypervisors need MSR auto load/restore feature.
We read MSRs from VM-entry MSR load area which specified by L1,
and load them via kvm_set_msr in the nested entry.
When nested exit occurs, we get MSRs via kvm_get_msr, writing
them to L1`s MSR store area. After this, we read MSRs from VM-exit
MSR load area, and load them via kvm_set_msr.

Signed-off-by: Wincy Van <fanwenyi0529@gmail.com>
---
 arch/x86/include/uapi/asm/vmx.h |  5 +++
 arch/x86/kvm/vmx.c              | 68 +++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c              |  1 +
 virt/kvm/kvm_main.c             |  1 +
 4 files changed, 75 insertions(+)

diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index b813bf9..ff2b8e2 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -56,6 +56,7 @@
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_INVALID_STATE       33
+#define EXIT_REASON_MSR_LOAD_FAIL       34
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
 #define EXIT_REASON_MONITOR_INSTRUCTION 39
 #define EXIT_REASON_PAUSE_INSTRUCTION   40
@@ -116,10 +117,14 @@
 	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
 	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
 	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
+	{ EXIT_REASON_MSR_LOAD_FAIL,         "MSR_LOAD_FAIL" }, \
 	{ EXIT_REASON_INVD,                  "INVD" }, \
 	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
 
+#define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
+#define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
+
 #endif /* _UAPIVMX_H */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9bcc871..b49d198 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6143,6 +6143,13 @@ static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
 	 */
 }
 
+static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
+{
+	/* TODO: not to reset guest simply here. */
+	kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	pr_warn("kvm: nested vmx abort, indicator %d\n", indicator);
+}
+
 static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
 {
 	struct vcpu_vmx *vmx =
@@ -8286,6 +8293,67 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
 		      ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
 }
 
+static inline int nested_vmx_msr_check_common(struct vmx_msr_entry *e)
+{
+	if (e->index >> 8 == 0x8 || e->reserved != 0)
+		return -EINVAL;
+	return 0;
+}
+
+static inline int nested_vmx_load_msr_check(struct vmx_msr_entry *e)
+{
+	if (e->index == MSR_FS_BASE ||
+	    e->index == MSR_GS_BASE ||
+		nested_vmx_msr_check_common(e))
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * Load guest's/host's msr at nested entry/exit.
+ * return 0 for success, entry index for failure.
+ */
+static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
+{
+	u32 i;
+	struct vmx_msr_entry e;
+	struct msr_data msr;
+
+	msr.host_initiated = false;
+	for (i = 0; i < count; i++) {
+		kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e), &e, sizeof(e));
+		if (nested_vmx_load_msr_check(&e))
+			goto fail;
+		msr.index = e.index;
+		msr.data = e.value;
+		if (kvm_set_msr(vcpu, &msr))
+			goto fail;
+	}
+	return 0;
+fail:
+	return i + 1;
+}
+
+static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
+{
+	u32 i;
+	struct vmx_msr_entry e;
+
+	for (i = 0; i < count; i++) {
+		kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e),
+				&e, 2 * sizeof(u32));
+		if (nested_vmx_msr_check_common(&e))
+			return -EINVAL;
+		if (kvm_get_msr(vcpu, e.index, &e.value))
+			return -EINVAL;
+		kvm_write_guest(vcpu->kvm,
+				gpa + i * sizeof(e) +
+					offsetof(struct vmx_msr_entry, value),
+				&e.value, sizeof(e.value));
+	}
+	return 0;
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c259814..af9faed 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2324,6 +2324,7 @@ int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 {
 	return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
 }
+EXPORT_SYMBOL_GPL(kvm_get_msr);
 
 static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c5c186a..77179c5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1579,6 +1579,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvm_write_guest);
 
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len)
-- 
2.0.4