From: Sean Christopherson <seanjc@google.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: 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>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Reiji Watanabe <reijiw@google.com>
Subject: [PATCH v3 4/4] KVM: SVM: Delay restoration of host MSR_TSC_AUX until return to userspace
Date: Fri, 23 Apr 2021 15:34:04 -0700 [thread overview]
Message-ID: <20210423223404.3860547-5-seanjc@google.com> (raw)
In-Reply-To: <20210423223404.3860547-1-seanjc@google.com>
Use KVM's "user return MSRs" framework to defer restoring the host's
MSR_TSC_AUX until the CPU returns to userspace. Add/improve comments to
clarify why MSR_TSC_AUX is intercepted on both RDMSR and WRMSR, and why
it's safe for KVM to keep the guest's value loaded even if KVM is
scheduled out.
Cc: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/svm/svm.c | 52 +++++++++++++++++++-----------------------
arch/x86/kvm/svm/svm.h | 7 ------
2 files changed, 23 insertions(+), 36 deletions(-)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 4c7604fca009..a4bd7cb19755 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -213,6 +213,15 @@ struct kvm_ldttss_desc {
DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
+/*
+ * Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via
+ * the VMCB, and the SYSCALL/SYSENTER MSRs are handled by VMLOAD/VMSAVE.
+ *
+ * RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to
+ * defer the restoration of TSC_AUX until the CPU returns to userspace.
+ */
+#define TSC_AUX_URET_SLOT 0
+
static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
@@ -958,6 +967,9 @@ static __init int svm_hardware_setup(void)
kvm_tsc_scaling_ratio_frac_bits = 32;
}
+ if (boot_cpu_has(X86_FEATURE_RDTSCP))
+ kvm_define_user_return_msr(TSC_AUX_URET_SLOT, MSR_TSC_AUX);
+
/* Check for pause filtering support */
if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
pause_filter_count = 0;
@@ -1423,19 +1435,10 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
- unsigned int i;
if (svm->guest_state_loaded)
return;
- /*
- * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save
- * area (non-sev-es). Save ones that aren't so we can restore them
- * individually later.
- */
- for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
- rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
-
/*
* Save additional host state that will be restored on VMEXIT (sev-es)
* or subsequent vmload of host save area.
@@ -1454,29 +1457,15 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
}
}
- /* This assumes that the kernel never uses MSR_TSC_AUX */
if (static_cpu_has(X86_FEATURE_RDTSCP))
- wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
+ kvm_set_user_return_msr(TSC_AUX_URET_SLOT, svm->tsc_aux, -1ull);
svm->guest_state_loaded = true;
}
static void svm_prepare_host_switch(struct kvm_vcpu *vcpu)
{
- struct vcpu_svm *svm = to_svm(vcpu);
- unsigned int i;
-
- if (!svm->guest_state_loaded)
- return;
-
- /*
- * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save
- * area (non-sev-es). Restore the ones that weren't.
- */
- for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
- wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
-
- svm->guest_state_loaded = false;
+ to_svm(vcpu)->guest_state_loaded = false;
}
static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -2785,6 +2774,7 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ int r;
u32 ecx = msr->index;
u64 data = msr->data;
@@ -2888,11 +2878,15 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
case MSR_TSC_AUX:
/*
- * This is rare, so we update the MSR here instead of using
- * direct_access_msrs. Doing that would require a rdmsr in
- * svm_vcpu_put.
+ * TSC_AUX is usually changed only during boot and never read
+ * directly. Intercept TSC_AUX instead of exposing it to the
+ * guest via direct_access_msrs, and switch it via user return.
*/
- wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
+ preempt_disable();
+ r = kvm_set_user_return_msr(TSC_AUX_URET_SLOT, data, -1ull);
+ preempt_enable();
+ if (r)
+ return 1;
svm->tsc_aux = data;
break;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index d6206196eec1..5d8027e9c1c5 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -23,11 +23,6 @@
#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
-static const u32 host_save_user_msrs[] = {
- MSR_TSC_AUX,
-};
-#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
-
#define IOPM_SIZE PAGE_SIZE * 3
#define MSRPM_SIZE PAGE_SIZE * 2
@@ -129,8 +124,6 @@ struct vcpu_svm {
u64 next_rip;
- u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
-
u64 spec_ctrl;
/*
* Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be
--
2.31.1.498.g6c1eba8ee3d-goog
next prev parent reply other threads:[~2021-04-23 22:34 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-23 22:34 [PATCH v3 0/4] KVM: x86: MSR_TSC_AUX fixes and improvements Sean Christopherson
2021-04-23 22:34 ` [PATCH v3 1/4] KVM: SVM: Inject #GP on guest MSR_TSC_AUX accesses if RDTSCP unsupported Sean Christopherson
2021-04-26 8:49 ` Vitaly Kuznetsov
2021-04-23 22:34 ` [PATCH v3 2/4] KVM: SVM: Clear MSR_TSC_AUX[63:32] on write Sean Christopherson
2021-04-26 8:57 ` Vitaly Kuznetsov
2021-04-26 19:18 ` Sean Christopherson
2021-04-26 19:44 ` Sean Christopherson
2021-04-23 22:34 ` [PATCH v3 3/4] KVM: x86: Tie Intel and AMD behavior for MSR_TSC_AUX to guest CPU model Sean Christopherson
2021-04-24 7:19 ` Reiji Watanabe
2021-04-26 19:38 ` Sean Christopherson
2021-04-27 4:42 ` Reiji Watanabe
2021-04-27 21:58 ` Sean Christopherson
2021-04-23 22:34 ` Sean Christopherson [this message]
2021-04-26 9:26 ` [PATCH v3 0/4] KVM: x86: MSR_TSC_AUX fixes and improvements 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=20210423223404.3860547-5-seanjc@google.com \
--to=seanjc@google.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=reijiw@google.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).