[PATCH] KVM: x86: add HC_VMM_CUSTOM hypercall

[Peter Oskolkov <posk@xxxxxxxxxx>]

Allow kvm-based VMMs to request KVM to pass a custom vmcall
from the guest to the VMM in the host.

Quite often, operating systems research projects and/or specialized
paravirtualized workloads would benefit from a extra-low-overhead,
extra-low-latency guest-host communication channel.

With cloud-hypervisor modified to handle the new hypercall (simply
return the sum of the received arguments), the following function in
guest _userspace_ completes, on average, in 2.5 microseconds (walltime)
on a relatively modern Intel Xeon processor:

	uint64_t hypercall_custom_vmm(uint64_t a0, uint64_t a1,
					uint64_t a2, uint64_t a3)
	{
		uint64_t ret;

		asm(
			"movq   $13, %%rax \n\t"  // hypercall nr.
			"movq %[a0], %%rbx \n\t"  // a0
			"movq %[a1], %%rcx \n\t"  // a1
			"movq %[a2], %%rdx \n\t"  // a2
			"movq %[a3], %%rsi \n\t"  // a3
			"vmcall            \n\t"
			"movq %%rax, %[ret] \n\t" // ret
			: [ret] "=r"(ret)
			: [a0] "r"(a0), [a1] "r"(a1), [a2] "r"(a2), [a3] "r"(a3)
			: "rax", "rbx", "rcx", "rdx", "rsi"
		);

		return ret;
	}

Signed-off-by: Peter Oskolkov <posk@xxxxxxxxxx>
---
 arch/x86/kvm/x86.c            | 28 ++++++++++++++++++++++++++--
 include/uapi/linux/kvm_para.h |  1 +
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ab336f7c82e4..343971128da7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -108,7 +108,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 
 static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
 
-#define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE)
+#define KVM_EXIT_HYPERCALL_VALID_MASK  ((1 << KVM_HC_MAP_GPA_RANGE) | \
+					(1 << KVM_HC_VMM_CUSTOM))
 
 #define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE
 
@@ -9207,10 +9208,16 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
 	return kvm_skip_emulated_instruction(vcpu);
 }
 
+static int kvm_allow_hypercall_from_userspace(int nr)
+{
+	return nr == KVM_HC_VMM_CUSTOM;
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
 	int op_64_bit;
+	int cpl;
 
 	if (kvm_xen_hypercall_enabled(vcpu->kvm))
 		return kvm_xen_hypercall(vcpu);
@@ -9235,7 +9242,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		a3 &= 0xFFFFFFFF;
 	}
 
-	if (static_call(kvm_x86_get_cpl)(vcpu) != 0) {
+	cpl = static_call(kvm_x86_get_cpl)(vcpu);
+	if (cpl != 0 && !kvm_allow_hypercall_from_userspace(nr)) {
 		ret = -KVM_EPERM;
 		goto out;
 	}
@@ -9294,6 +9302,22 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		vcpu->arch.complete_userspace_io = complete_hypercall_exit;
 		return 0;
 	}
+	case KVM_HC_VMM_CUSTOM:
+		ret = -KVM_ENOSYS;
+		if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_VMM_CUSTOM)))
+			break;
+
+		vcpu->run->exit_reason        = KVM_EXIT_HYPERCALL;
+		vcpu->run->hypercall.nr       = KVM_HC_VMM_CUSTOM;
+		vcpu->run->hypercall.args[0]  = a0;
+		vcpu->run->hypercall.args[1]  = a1;
+		vcpu->run->hypercall.args[2]  = a2;
+		vcpu->run->hypercall.args[3]  = a3;
+		vcpu->run->hypercall.args[4]  = 0;
+		vcpu->run->hypercall.args[5]  = cpl;
+		vcpu->run->hypercall.longmode = op_64_bit;
+		vcpu->arch.complete_userspace_io = complete_hypercall_exit;
+		return 0;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index 960c7e93d1a9..8caab28c9025 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -30,6 +30,7 @@
 #define KVM_HC_SEND_IPI		10
 #define KVM_HC_SCHED_YIELD		11
 #define KVM_HC_MAP_GPA_RANGE		12
+#define KVM_HC_VMM_CUSTOM		13
 
 /*
  * hypercalls use architecture specific

base-commit: 150866cd0ec871c765181d145aa0912628289c8a
-- 
2.36.0.rc2.479.g8af0fa9b8e-goog