Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Vitaly Kuznetsov <vkuznets@redhat.com>
To:     kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>
Cc:     Sean Christopherson <sean.j.christopherson@intel.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        "Dr . David Alan Gilbert" <dgilbert@redhat.com>,
        Wei Huang <whuang2@amd.com>, linux-kernel@vger.kernel.org
Subject: [PATCH RFC 1/2] KVM: x86: allocate vcpu->arch.cpuid_entries dynamically
Date:   Tue, 15 Sep 2020 17:43:05 +0200
Message-Id: <20200915154306.724953-2-vkuznets@redhat.com>
In-Reply-To: <20200915154306.724953-1-vkuznets@redhat.com>
References: <20200915154306.724953-1-vkuznets@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

The current limit for guest CPUID leaves (KVM_MAX_CPUID_ENTRIES, 80)
is reported to be insufficient but before we bump it let's switch to
allocating vcpu->arch.cpuid_entries dynamically. Currenly,
'struct kvm_cpuid_entry2' is 40 bytes so vcpu->arch.cpuid_entries is
3200 bytes which accounts for 1/4 of the whole 'struct kvm_vcpu_arch'
but having it pre-allocated (for all vCPUs which we also pre-allocate)
gives us no benefits.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kvm/cpuid.c            | 55 ++++++++++++++++++++++++---------
 arch/x86/kvm/x86.c              |  1 +
 3 files changed, 42 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5303dbc5c9bc..0c5f2ca3e838 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -636,7 +636,7 @@ struct kvm_vcpu_arch {
 	int halt_request; /* real mode on Intel only */
 
 	int cpuid_nent;
-	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
+	struct kvm_cpuid_entry2 *cpuid_entries;
 
 	int maxphyaddr;
 	int max_tdp_level;
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 3fd6eec202d7..0ce943a8a39a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -195,6 +195,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 {
 	int r, i;
 	struct kvm_cpuid_entry *cpuid_entries = NULL;
+	struct kvm_cpuid_entry2 *cpuid_entries2 = NULL;
 
 	r = -E2BIG;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
@@ -207,31 +208,42 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			r = PTR_ERR(cpuid_entries);
 			goto out;
 		}
+		cpuid_entries2 = kvmalloc_array(cpuid->nent, sizeof(cpuid_entries2[0]),
+						GFP_KERNEL_ACCOUNT);
+		if (!cpuid_entries2) {
+			r = -ENOMEM;
+			goto out_free_cpuid;
+		}
 	}
 	for (i = 0; i < cpuid->nent; i++) {
-		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
-		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
-		vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
-		vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
-		vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
-		vcpu->arch.cpuid_entries[i].index = 0;
-		vcpu->arch.cpuid_entries[i].flags = 0;
-		vcpu->arch.cpuid_entries[i].padding[0] = 0;
-		vcpu->arch.cpuid_entries[i].padding[1] = 0;
-		vcpu->arch.cpuid_entries[i].padding[2] = 0;
+		cpuid_entries2[i].function = cpuid_entries[i].function;
+		cpuid_entries2[i].eax = cpuid_entries[i].eax;
+		cpuid_entries2[i].ebx = cpuid_entries[i].ebx;
+		cpuid_entries2[i].ecx = cpuid_entries[i].ecx;
+		cpuid_entries2[i].edx = cpuid_entries[i].edx;
+		cpuid_entries2[i].index = 0;
+		cpuid_entries2[i].flags = 0;
+		cpuid_entries2[i].padding[0] = 0;
+		cpuid_entries2[i].padding[1] = 0;
+		cpuid_entries2[i].padding[2] = 0;
 	}
+	kvfree(vcpu->arch.cpuid_entries);
+	vcpu->arch.cpuid_entries = cpuid_entries2;
 	vcpu->arch.cpuid_nent = cpuid->nent;
+
 	r = kvm_check_cpuid(vcpu);
 	if (r) {
+		kvfree(vcpu->arch.cpuid_entries);
+		vcpu->arch.cpuid_entries = NULL;
 		vcpu->arch.cpuid_nent = 0;
-		kvfree(cpuid_entries);
-		goto out;
+		goto out_free_cpuid;
 	}
 
 	cpuid_fix_nx_cap(vcpu);
 	kvm_update_cpuid_runtime(vcpu);
 	kvm_vcpu_after_set_cpuid(vcpu);
 
+out_free_cpuid:
 	kvfree(cpuid_entries);
 out:
 	return r;
@@ -241,18 +253,31 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 			      struct kvm_cpuid2 *cpuid,
 			      struct kvm_cpuid_entry2 __user *entries)
 {
+	struct kvm_cpuid_entry2 *cpuid_entries2 = NULL;
 	int r;
 
 	r = -E2BIG;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		goto out;
 	r = -EFAULT;
-	if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
-			   cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
-		goto out;
+
+	if (cpuid->nent) {
+		cpuid_entries2 = vmemdup_user(entries,
+					      array_size(sizeof(cpuid_entries2[0]),
+							 cpuid->nent));
+		if (IS_ERR(cpuid_entries2)) {
+			r = PTR_ERR(cpuid_entries2);
+			goto out;
+		}
+	}
+	kvfree(vcpu->arch.cpuid_entries);
+	vcpu->arch.cpuid_entries = cpuid_entries2;
 	vcpu->arch.cpuid_nent = cpuid->nent;
+
 	r = kvm_check_cpuid(vcpu);
 	if (r) {
+		kvfree(vcpu->arch.cpuid_entries);
+		vcpu->arch.cpuid_entries = NULL;
 		vcpu->arch.cpuid_nent = 0;
 		goto out;
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1994602a0851..42259a6ec1d8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9610,6 +9610,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_destroy(vcpu);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	free_page((unsigned long)vcpu->arch.pio_data);
+	kvfree(vcpu->arch.cpuid_entries);
 	if (!lapic_in_kernel(vcpu))
 		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
-- 
2.25.4