From:   isaku.yamahata@intel.com
To:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
        Paolo Bonzini <pbonzini@redhat.com>, erdemaktas@google.com,
        Sean Christopherson <seanjc@google.com>,
        Sagi Shahar <sagis@google.com>,
        David Matlack <dmatlack@google.com>,
        Kai Huang <kai.huang@intel.com>,
        Zhi Wang <zhi.wang.linux@gmail.com>
Subject: [PATCH v12 012/106] KVM: x86/vmx, tdx: Allow VMX, TDX to override KVM_ENABLE_CAP
Date:   Mon, 27 Feb 2023 00:22:11 -0800
Message-Id: <b6867d9e8101fc464acfe76772c2cac8f078269f.1677484918.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1677484918.git.isaku.yamahata@intel.com>
References: <cover.1677484918.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Isaku Yamahata <isaku.yamahata@intel.com>

TDX has its own control of maximum number of vcpus. Not KVM_MAX_VCPUS.
Allow vmx, tdx to override KVM_CAP_MAX_CPUS so that it can specify its own
maximum number of cpus instead of KVM_MAX_VCPUS.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  1 +
 arch/x86/kvm/vmx/main.c            |  9 +++++++++
 arch/x86/kvm/vmx/tdx.c             | 30 ++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/tdx.h             |  3 +++
 arch/x86/kvm/vmx/x86_ops.h         |  2 ++
 arch/x86/kvm/x86.c                 |  2 ++
 7 files changed, 48 insertions(+)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 6914f1d61803..7522c193f2b4 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -22,6 +22,7 @@ KVM_X86_OP(has_emulated_msr)
 KVM_X86_OP(vcpu_after_set_cpuid)
 KVM_X86_OP(is_vm_type_supported)
 KVM_X86_OP_OPTIONAL(max_vcpus);
+KVM_X86_OP_OPTIONAL(vm_enable_cap)
 KVM_X86_OP(vm_init)
 KVM_X86_OP_OPTIONAL(vm_destroy)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_precreate)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1c761c9e1edb..bc9ecba514a9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1549,6 +1549,7 @@ struct kvm_x86_ops {
 	bool (*is_vm_type_supported)(unsigned long vm_type);
 	int (*max_vcpus)(struct kvm *kvm);
 	unsigned int vm_size;
+	int (*vm_enable_cap)(struct kvm *kvm, struct kvm_enable_cap *cap);
 	int (*vm_init)(struct kvm *kvm);
 	void (*vm_destroy)(struct kvm *kvm);
 
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 41c2e4a1b157..a090c029efd5 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -41,6 +41,14 @@ static __init int vt_hardware_setup(void)
 	return 0;
 }
 
+static int vt_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
+{
+	if (is_td(kvm))
+		return tdx_vm_enable_cap(kvm, cap);
+
+	return -EINVAL;
+}
+
 static int vt_vm_init(struct kvm *kvm)
 {
 	if (is_td(kvm))
@@ -82,6 +90,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.is_vm_type_supported = vt_is_vm_type_supported,
 	.max_vcpus = vt_max_vcpus,
 	.vm_size = sizeof(struct kvm_vmx),
+	.vm_enable_cap = vt_vm_enable_cap,
 	.vm_init = vt_vm_init,
 	.vm_destroy = vmx_vm_destroy,
 
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index cfedb2592725..16e207168dc1 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -16,6 +16,36 @@
 		offsetof(struct tdsysinfo_struct, cpuid_configs))	\
 		/ sizeof(struct tdx_cpuid_config))
 
+int tdx_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
+{
+	int r;
+
+	switch (cap->cap) {
+	case KVM_CAP_MAX_VCPUS: {
+		if (cap->flags || cap->args[0] == 0)
+			return -EINVAL;
+		if (cap->args[0] > KVM_MAX_VCPUS)
+			return -E2BIG;
+		if (cap->args[0] > TDX_MAX_VCPUS)
+			return -E2BIG;
+
+		mutex_lock(&kvm->lock);
+		if (kvm->created_vcpus)
+			r = -EBUSY;
+		else {
+			kvm->max_vcpus = cap->args[0];
+			r = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		break;
+	}
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
 int tdx_dev_ioctl(void __user *argp)
 {
 	struct kvm_tdx_capabilities __user *user_caps;
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index 2210c8c1e893..3860aa351bd9 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -3,6 +3,9 @@
 #define __KVM_X86_TDX_H
 
 #ifdef CONFIG_INTEL_TDX_HOST
+
+#include "tdx_ops.h"
+
 struct kvm_tdx {
 	struct kvm kvm;
 	/* TDX specific members follow. */
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 6598e16f8e9f..71f7dc9ca118 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -142,12 +142,14 @@ int __init tdx_hardware_setup(struct kvm_x86_ops *x86_ops);
 bool tdx_is_vm_type_supported(unsigned long type);
 int tdx_dev_ioctl(void __user *argp);
 
+int tdx_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap);
 int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
 #else
 static inline int tdx_hardware_setup(struct kvm_x86_ops *x86_ops) { return -ENOSYS; }
 static inline bool tdx_is_vm_type_supported(unsigned long type) { return false; }
 static inline int tdx_dev_ioctl(void __user *argp) { return -EOPNOTSUPP; };
 
+static inline int tdx_vm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { return -EINVAL; };
 static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
 #endif
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c54baa3973f2..318e36535aa6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6421,6 +6421,8 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		break;
 	default:
 		r = -EINVAL;
+		if (kvm_x86_ops.vm_enable_cap)
+			r = static_call(kvm_x86_vm_enable_cap)(kvm, cap);
 		break;
 	}
 	return r;
-- 
2.25.1