All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sean Christopherson <sean.j.christopherson@intel.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2 3/7] KVM: nVMX: Allow L1 to use 5-level page walks for nested EPT
Date: Fri,  7 Feb 2020 09:37:43 -0800	[thread overview]
Message-ID: <20200207173747.6243-4-sean.j.christopherson@intel.com> (raw)
In-Reply-To: <20200207173747.6243-1-sean.j.christopherson@intel.com>

Add support for 5-level nested EPT, and advertise said support in the
EPT capabilities MSR.  KVM's MMU can already handle 5-level legacy page
tables, there's no reason to force an L1 VMM to use shadow paging if it
wants to employ 5-level page tables.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
---
 arch/x86/include/asm/vmx.h     | 12 ++++++++++++
 arch/x86/kvm/mmu/mmu.c         | 11 ++++++-----
 arch/x86/kvm/mmu/paging_tmpl.h |  2 +-
 arch/x86/kvm/vmx/nested.c      | 21 +++++++++++++++++----
 arch/x86/kvm/vmx/vmx.c         |  3 +--
 5 files changed, 37 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 2a85287b3685..bcd93fe07991 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -500,6 +500,18 @@ enum vmcs_field {
 						 VMX_EPT_EXECUTABLE_MASK)
 #define VMX_EPT_MT_MASK				(7ull << VMX_EPT_MT_EPTE_SHIFT)
 
+static inline u8 vmx_eptp_page_walk_level(u64 eptp)
+{
+	u64 encoded_level = eptp & VMX_EPTP_PWL_MASK;
+
+	if (encoded_level == VMX_EPTP_PWL_5)
+		return 5;
+
+	/* @eptp must be pre-validated by the caller. */
+	WARN_ON_ONCE(encoded_level != VMX_EPTP_PWL_4);
+	return 4;
+}
+
 /* The mask to use to trigger an EPT Misconfiguration in order to track MMIO */
 #define VMX_EPT_MISCONFIG_WX_VALUE		(VMX_EPT_WRITABLE_MASK |       \
 						 VMX_EPT_EXECUTABLE_MASK)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7011a4e54866..70f67bcab7db 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5012,14 +5012,14 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
 static union kvm_mmu_role
 kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
-				   bool execonly)
+				   bool execonly, u8 level)
 {
 	union kvm_mmu_role role = {0};
 
 	/* SMM flag is inherited from root_mmu */
 	role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;
 
-	role.base.level = PT64_ROOT_4LEVEL;
+	role.base.level = level;
 	role.base.gpte_is_8_bytes = true;
 	role.base.direct = false;
 	role.base.ad_disabled = !accessed_dirty;
@@ -5043,9 +5043,10 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty, gpa_t new_eptp)
 {
 	struct kvm_mmu *context = vcpu->arch.mmu;
+	u8 level = vmx_eptp_page_walk_level(new_eptp);
 	union kvm_mmu_role new_role =
 		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
-						   execonly);
+						   execonly, level);
 
 	__kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false);
 
@@ -5053,7 +5054,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	if (new_role.as_u64 == context->mmu_role.as_u64)
 		return;
 
-	context->shadow_root_level = PT64_ROOT_4LEVEL;
+	context->shadow_root_level = level;
 
 	context->nx = true;
 	context->ept_ad = accessed_dirty;
@@ -5062,7 +5063,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->sync_page = ept_sync_page;
 	context->invlpg = ept_invlpg;
 	context->update_pte = ept_update_pte;
-	context->root_level = PT64_ROOT_4LEVEL;
+	context->root_level = level;
 	context->direct_map = false;
 	context->mmu_role.as_u64 = new_role.as_u64;
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index e4c8a4cbf407..6b15b58f3ecc 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -66,7 +66,7 @@
 	#define PT_GUEST_ACCESSED_SHIFT 8
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad)
 	#define CMPXCHG cmpxchg64
-	#define PT_MAX_FULL_LEVELS 4
+	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
 #else
 	#error Invalid PTTYPE value
 #endif
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 657c2eda357c..d5fc4bfea0e2 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2581,9 +2581,19 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
 		return false;
 	}
 
-	/* only 4 levels page-walk length are valid */
-	if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4))
+	/* Page-walk levels validity. */
+	switch (address & VMX_EPTP_PWL_MASK) {
+	case VMX_EPTP_PWL_5:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT)))
+			return false;
+		break;
+	case VMX_EPTP_PWL_4:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT)))
+			return false;
+		break;
+	default:
 		return false;
+	}
 
 	/* Reserved bits should not be set */
 	if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f)))
@@ -6057,8 +6067,11 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 		/* nested EPT: emulate EPT also to L1 */
 		msrs->secondary_ctls_high |=
 			SECONDARY_EXEC_ENABLE_EPT;
-		msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
-			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+		msrs->ept_caps =
+			VMX_EPT_PAGE_WALK_4_BIT |
+			VMX_EPT_PAGE_WALK_5_BIT |
+			VMX_EPTP_WB_BIT |
+			VMX_EPT_INVEPT_BIT;
 		if (cpu_has_vmx_ept_execute_only())
 			msrs->ept_caps |=
 				VMX_EPT_EXECUTE_ONLY_BIT;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ed1d41f5f505..e6d5c9277ba5 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2947,9 +2947,8 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
-	/* Nested EPT currently only supports 4-level walks. */
 	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
-		return 4;
+		return vmx_eptp_page_walk_level(nested_ept_get_cr3(vcpu));
 	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
 		return 5;
 	return 4;
-- 
2.24.1


  parent reply	other threads:[~2020-02-07 17:38 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-07 17:37 [PATCH v2 0/7] KVM: x86/mmu: nVMX: 5-level paging fixes and enabling Sean Christopherson
2020-02-07 17:37 ` [PATCH v2 1/7] KVM: nVMX: Use correct root level for nested EPT shadow page tables Sean Christopherson
2020-02-07 17:37 ` [PATCH v2 2/7] KVM: x86/mmu: Fix struct guest_walker arrays for 5-level paging Sean Christopherson
2020-02-07 17:37 ` Sean Christopherson [this message]
2020-02-07 17:37 ` [PATCH v2 4/7] KVM: nVMX: Rename nested_ept_get_cr3() to nested_ept_get_eptp() Sean Christopherson
2020-02-07 17:37 ` [PATCH v2 5/7] KVM: nVMX: Rename EPTP validity helper and associated variables Sean Christopherson
2020-02-07 17:37 ` [PATCH v2 6/7] KVM: x86/mmu: Rename kvm_mmu->get_cr3() to ->get_guest_cr3_or_eptp() Sean Christopherson
2020-02-12 12:00   ` Paolo Bonzini
2020-02-12 16:28     ` Sean Christopherson
2020-02-12 16:42       ` Paolo Bonzini
2020-03-01 17:49         ` Sean Christopherson
2020-02-07 17:37 ` [PATCH v2 7/7] KVM: nVMX: Drop unnecessary check on ept caps for execute-only Sean Christopherson
2020-02-12 12:03 ` [PATCH v2 0/7] KVM: x86/mmu: nVMX: 5-level paging fixes and enabling Paolo Bonzini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200207173747.6243-4-sean.j.christopherson@intel.com \
    --to=sean.j.christopherson@intel.com \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.