linux-kernel - [PATCH 1/8] KVM: nSVM: Sync next_rip field from vmcb12 to vmcb02

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220402010903.727604-2-seanjc@google.com>
Date:   Sat,  2 Apr 2022 01:08:56 +0000
From:   Sean Christopherson <seanjc@...gle.com>
To:     Paolo Bonzini <pbonzini@...hat.com>
Cc:     Sean Christopherson <seanjc@...gle.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org,
        "Maciej S . Szmigiero" <maciej.szmigiero@...cle.com>
Subject: [PATCH 1/8] KVM: nSVM: Sync next_rip field from vmcb12 to vmcb02

From: Maciej S. Szmigiero <maciej.szmigiero@...cle.com>

The next_rip field of a VMCB is *not* an output-only field for a VMRUN.
This field value (instead of the saved guest RIP) in used by the CPU for
the return address pushed on stack when injecting a software interrupt or
INT3 or INTO exception.

Make sure this field gets synced from vmcb12 to vmcb02 when entering L2 or
loading a nested state and NRIPS is exposed to L1.  If NRIPS is supported
in hardware but not exposed to L1 (nrips=0 or hidden by userspace), stuff
vmcb02's next_rip from the new L2 RIP to emulate a !NRIPS CPU (which
saves RIP on the stack as-is).

Signed-off-by: Maciej S. Szmigiero <maciej.szmigiero@...cle.com>
Co-developed-by: Sean Christopherson <seanjc@...gle.com>
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/svm/nested.c | 22 +++++++++++++++++++---
 arch/x86/kvm/svm/svm.h    |  1 +
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 73b545278f5f..9a6dc2b38fcf 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -369,6 +369,7 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu,
 	to->nested_ctl          = from->nested_ctl;
 	to->event_inj           = from->event_inj;
 	to->event_inj_err       = from->event_inj_err;
+	to->next_rip            = from->next_rip;
 	to->nested_cr3          = from->nested_cr3;
 	to->virt_ext            = from->virt_ext;
 	to->pause_filter_count  = from->pause_filter_count;
@@ -606,7 +607,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 	}
 }
 
-static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
+static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
+					  unsigned long vmcb12_rip)
 {
 	u32 int_ctl_vmcb01_bits = V_INTR_MASKING_MASK;
 	u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK;
@@ -660,6 +662,19 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	vmcb02->control.event_inj           = svm->nested.ctl.event_inj;
 	vmcb02->control.event_inj_err       = svm->nested.ctl.event_inj_err;
 
+	/*
+	 * next_rip is consumed on VMRUN as the return address pushed on the
+	 * stack for injected soft exceptions/interrupts.  If nrips is exposed
+	 * to L1, take it verbatim from vmcb12.  If nrips is supported in
+	 * hardware but not exposed to L1, stuff the actual L2 RIP to emulate
+	 * what a nrips=0 CPU would do (L1 is responsible for advancing RIP
+	 * prior to injecting the event).
+	 */
+	if (svm->nrips_enabled)
+		vmcb02->control.next_rip    = svm->nested.ctl.next_rip;
+	else if (boot_cpu_has(X86_FEATURE_NRIPS))
+		vmcb02->control.next_rip    = vmcb12_rip;
+
 	vmcb02->control.virt_ext            = vmcb01->control.virt_ext &
 					      LBR_CTL_ENABLE_MASK;
 	if (svm->lbrv_enabled)
@@ -743,7 +758,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
 	nested_svm_copy_common_state(svm->vmcb01.ptr, svm->nested.vmcb02.ptr);
 
 	svm_switch_vmcb(svm, &svm->nested.vmcb02);
-	nested_vmcb02_prepare_control(svm);
+	nested_vmcb02_prepare_control(svm, vmcb12->save.rip);
 	nested_vmcb02_prepare_save(svm, vmcb12);
 
 	ret = nested_svm_load_cr3(&svm->vcpu, svm->nested.save.cr3,
@@ -1422,6 +1437,7 @@ static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst,
 	dst->nested_ctl           = from->nested_ctl;
 	dst->event_inj            = from->event_inj;
 	dst->event_inj_err        = from->event_inj_err;
+	dst->next_rip             = from->next_rip;
 	dst->nested_cr3           = from->nested_cr3;
 	dst->virt_ext              = from->virt_ext;
 	dst->pause_filter_count   = from->pause_filter_count;
@@ -1606,7 +1622,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	nested_copy_vmcb_control_to_cache(svm, ctl);
 
 	svm_switch_vmcb(svm, &svm->nested.vmcb02);
-	nested_vmcb02_prepare_control(svm);
+	nested_vmcb02_prepare_control(svm, save->rip);
 
 	/*
 	 * While the nested guest CR3 is already checked and set by
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e246793cbeae..47e7427d0395 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -139,6 +139,7 @@ struct vmcb_ctrl_area_cached {
 	u64 nested_ctl;
 	u32 event_inj;
 	u32 event_inj_err;
+	u64 next_rip;
 	u64 nested_cr3;
 	u64 virt_ext;
 	u32 clean;
-- 
2.35.1.1094.g7c7d902a7c-goog