All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chenyi Qiang <chenyi.qiang@intel.com>
To: Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Xiaoyao Li <xiaoyao.li@intel.com>
Cc: Chenyi Qiang <chenyi.qiang@intel.com>,
	kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v6 7/7] KVM: VMX: Enable PKS for nested VM
Date: Mon, 21 Feb 2022 16:08:40 +0800	[thread overview]
Message-ID: <20220221080840.7369-8-chenyi.qiang@intel.com> (raw)
In-Reply-To: <20220221080840.7369-1-chenyi.qiang@intel.com>

PKS MSR passes through guest directly. Configure the MSR to match the
L0/L1 settings so that nested VM runs PKS properly.

Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
---
 arch/x86/kvm/vmx/nested.c | 38 ++++++++++++++++++++++++++++++++++++--
 arch/x86/kvm/vmx/vmcs12.c |  2 ++
 arch/x86/kvm/vmx/vmcs12.h |  4 ++++
 arch/x86/kvm/vmx/vmx.c    |  1 +
 arch/x86/kvm/vmx/vmx.h    |  2 ++
 5 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f235f77cbc03..c42a1df385ef 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -252,6 +252,10 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 	dest->ds_sel = src->ds_sel;
 	dest->es_sel = src->es_sel;
 #endif
+	if (unlikely(src->pkrs != dest->pkrs)) {
+		vmcs_write64(HOST_IA32_PKRS, src->pkrs);
+		dest->pkrs = src->pkrs;
+	}
 }
 
 static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
@@ -685,6 +689,9 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
 					 MSR_IA32_PRED_CMD, MSR_TYPE_W);
 
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_PKRS, MSR_TYPE_RW);
+
 	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
 
 	vmx->nested.force_msr_bitmap_recalc = false;
@@ -2433,6 +2440,10 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		if (kvm_mpx_supported() && vmx->nested.nested_run_pending &&
 		    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
 			vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+
+		if (vmx->nested.nested_run_pending &&
+		    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS))
+			vmcs_write64(GUEST_IA32_PKRS, vmcs12->guest_ia32_pkrs);
 	}
 
 	if (nested_cpu_has_xsaves(vmcs12))
@@ -2521,6 +2532,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
 		vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+	if (kvm_cpu_cap_has(X86_FEATURE_PKS) &&
+	    (!vmx->nested.nested_run_pending ||
+	     !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS)))
+		vmcs_write64(GUEST_IA32_PKRS, vmx->nested.vmcs01_guest_pkrs);
+
 	vmx_set_rflags(vcpu, vmcs12->guest_rflags);
 
 	/* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
@@ -2897,6 +2913,10 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 					   vmcs12->host_ia32_perf_global_ctrl)))
 		return -EINVAL;
 
+	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PKRS) &&
+		CC(!kvm_pkrs_valid(vmcs12->host_ia32_pkrs)))
+		return -EINVAL;
+
 #ifdef CONFIG_X86_64
 	ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
 #else
@@ -3049,6 +3069,10 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	if (nested_check_guest_non_reg_state(vmcs12))
 		return -EINVAL;
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS) &&
+	    CC(!kvm_pkrs_valid(vmcs12->guest_ia32_pkrs)))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -3377,6 +3401,9 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	if (kvm_mpx_supported() &&
 		!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
 		vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
+	if (kvm_cpu_cap_has(X86_FEATURE_PKS) &&
+	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS))
+		vmx->nested.vmcs01_guest_pkrs = vmcs_read64(GUEST_IA32_PKRS);
 
 	/*
 	 * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and*
@@ -4022,6 +4049,7 @@ static bool is_vmcs12_ext_field(unsigned long field)
 	case GUEST_IDTR_BASE:
 	case GUEST_PENDING_DBG_EXCEPTIONS:
 	case GUEST_BNDCFGS:
+	case GUEST_IA32_PKRS:
 		return true;
 	default:
 		break;
@@ -4073,6 +4101,8 @@ static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
 		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
 	if (kvm_mpx_supported())
 		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
+	if (guest_cpuid_has(vcpu, X86_FEATURE_PKS))
+		vmcs12->guest_ia32_pkrs = vmcs_read64(GUEST_IA32_PKRS);
 
 	vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false;
 }
@@ -4310,6 +4340,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
 					 vmcs12->host_ia32_perf_global_ctrl));
 
+	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PKRS)
+		vmcs_write64(GUEST_IA32_PKRS, vmcs12->host_ia32_pkrs);
+
 	/* Set L1 segment info according to Intel SDM
 	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
 	seg = (struct kvm_segment) {
@@ -6527,7 +6560,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
 		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
-		VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+		VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |
+		VM_EXIT_LOAD_IA32_PKRS;
 	msrs->exit_ctls_high |=
 		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
@@ -6547,7 +6581,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 		VM_ENTRY_IA32E_MODE |
 #endif
 		VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS |
-		VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | VM_ENTRY_LOAD_IA32_PKRS;
 	msrs->entry_ctls_high |=
 		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
 
diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c
index cab6ba7a5005..f3b964e1496c 100644
--- a/arch/x86/kvm/vmx/vmcs12.c
+++ b/arch/x86/kvm/vmx/vmcs12.c
@@ -62,9 +62,11 @@ const unsigned short vmcs_field_to_offset_table[] = {
 	FIELD64(GUEST_PDPTR2, guest_pdptr2),
 	FIELD64(GUEST_PDPTR3, guest_pdptr3),
 	FIELD64(GUEST_BNDCFGS, guest_bndcfgs),
+	FIELD64(GUEST_IA32_PKRS, guest_ia32_pkrs),
 	FIELD64(HOST_IA32_PAT, host_ia32_pat),
 	FIELD64(HOST_IA32_EFER, host_ia32_efer),
 	FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
+	FIELD64(HOST_IA32_PKRS, host_ia32_pkrs),
 	FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control),
 	FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control),
 	FIELD(EXCEPTION_BITMAP, exception_bitmap),
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 2a45f026ee11..42cb4a2b806a 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -185,6 +185,8 @@ struct __packed vmcs12 {
 	u16 host_gs_selector;
 	u16 host_tr_selector;
 	u16 guest_pml_index;
+	u64 host_ia32_pkrs;
+	u64 guest_ia32_pkrs;
 };
 
 /*
@@ -359,6 +361,8 @@ static inline void vmx_check_vmcs12_offsets(void)
 	CHECK_OFFSET(host_gs_selector, 992);
 	CHECK_OFFSET(host_tr_selector, 994);
 	CHECK_OFFSET(guest_pml_index, 996);
+	CHECK_OFFSET(host_ia32_pkrs, 998);
+	CHECK_OFFSET(guest_ia32_pkrs, 1006);
 }
 
 extern const unsigned short vmcs_field_to_offset_table[];
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6fc70ddeff5a..978f4a61771f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7248,6 +7248,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_PKE,        ecx, feature_bit(PKU));
 	cr4_fixed1_update(X86_CR4_UMIP,       ecx, feature_bit(UMIP));
 	cr4_fixed1_update(X86_CR4_LA57,       ecx, feature_bit(LA57));
+	cr4_fixed1_update(X86_CR4_PKS,        ecx, feature_bit(PKS));
 
 #undef cr4_fixed1_update
 }
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index d704ba3a4af7..78bca3d14ed4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -222,6 +222,8 @@ struct nested_vmx {
 	u64 vmcs01_debugctl;
 	u64 vmcs01_guest_bndcfgs;
 
+	u64 vmcs01_guest_pkrs;
+
 	/* to migrate it to L1 if L2 writes to L1's CR8 directly */
 	int l1_tpr_threshold;
 
-- 
2.17.1


  parent reply	other threads:[~2022-02-21  8:06 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-21  8:08 [PATCH v6 0/7] KVM: PKS Virtualization support Chenyi Qiang
2022-02-21  8:08 ` [PATCH v6 1/7] KVM: VMX: Introduce PKS VMCS fields Chenyi Qiang
2022-03-30 20:05   ` Sean Christopherson
2022-02-21  8:08 ` [PATCH v6 2/7] KVM: VMX: Add proper cache tracking for PKRS Chenyi Qiang
2022-03-30 20:42   ` Sean Christopherson
2022-03-31  5:39     ` Chenyi Qiang
2022-02-21  8:08 ` [PATCH v6 3/7] KVM: X86: Expose IA32_PKRS MSR Chenyi Qiang
2022-02-21  8:08 ` [PATCH v6 4/7] KVM: MMU: Rename the pkru to pkr Chenyi Qiang
2022-02-21  8:08 ` [PATCH v6 5/7] KVM: MMU: Add support for PKS emulation Chenyi Qiang
2022-03-30 21:27   ` Sean Christopherson
2022-03-31  5:43     ` Chenyi Qiang
2022-02-21  8:08 ` [PATCH v6 6/7] KVM: VMX: Expose PKS to guest Chenyi Qiang
2022-03-30 21:30   ` Sean Christopherson
2022-02-21  8:08 ` Chenyi Qiang [this message]
2022-03-30 21:47   ` [PATCH v6 7/7] KVM: VMX: Enable PKS for nested VM Sean Christopherson
2022-03-31  6:08     ` Chenyi Qiang
2022-03-07  6:09 ` [PATCH v6 0/7] KVM: PKS Virtualization support Chenyi Qiang

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=20220221080840.7369-8-chenyi.qiang@intel.com \
    --to=chenyi.qiang@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=seanjc@google.com \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    --cc=xiaoyao.li@intel.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.