From: Paolo Bonzini <pbonzini@redhat.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc: guang.zeng@intel.com, jing2.liu@intel.com, kevin.tian@intel.com,
seanjc@google.com, tglx@linutronix.de, wei.w.wang@intel.com,
yang.zhong@intel.com
Subject: [PATCH v6 21/21] kvm: x86: Disable interception for IA32_XFD on demand
Date: Fri, 7 Jan 2022 13:55:12 -0500 [thread overview]
Message-ID: <20220107185512.25321-22-pbonzini@redhat.com> (raw)
In-Reply-To: <20220107185512.25321-1-pbonzini@redhat.com>
From: Kevin Tian <kevin.tian@intel.com>
Always intercepting IA32_XFD causes non-negligible overhead when this
register is updated frequently in the guest.
Disable r/w emulation after intercepting the first WRMSR(IA32_XFD)
with a non-zero value.
Disable WRMSR emulation implies that IA32_XFD becomes out-of-sync
with the software states in fpstate and the per-cpu xfd cache. This
leads to two additional changes accordingly:
- Call fpu_sync_guest_vmexit_xfd_state() after vm-exit to bring
software states back in-sync with the MSR, before handle_exit_irqoff()
is called.
- Always trap #NM once write interception is disabled for IA32_XFD.
The #NM exception is rare if the guest doesn't use dynamic
features. Otherwise, there is at most one exception per guest
task given a dynamic feature.
p.s. We have confirmed that SDM is being revised to say that
when setting IA32_XFD[18] the AMX register state is not guaranteed
to be preserved. This clarification avoids adding mess for a creative
guest which sets IA32_XFD[18]=1 before saving active AMX state to
its own storage.
Signed-off-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220105123532.12586-22-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/vmx/vmx.c | 24 +++++++++++++++++++-----
arch/x86/kvm/vmx/vmx.h | 2 +-
arch/x86/kvm/x86.c | 8 ++++++++
4 files changed, 29 insertions(+), 6 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6cbf97a2ebc4..89d1fdb39c46 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -647,6 +647,7 @@ struct kvm_vcpu_arch {
u64 smi_count;
bool tpr_access_reporting;
bool xsaves_enabled;
+ bool xfd_no_write_intercept;
u64 ia32_xss;
u64 microcode_version;
u64 arch_capabilities;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b8b7f5c7b3df..15e30602782b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -162,6 +162,7 @@ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
MSR_FS_BASE,
MSR_GS_BASE,
MSR_KERNEL_GS_BASE,
+ MSR_IA32_XFD,
MSR_IA32_XFD_ERR,
#endif
MSR_IA32_SYSENTER_CS,
@@ -764,10 +765,11 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
}
/*
- * Trap #NM if guest xfd contains a non-zero value so guest XFD_ERR
- * can be saved timely.
+ * Disabling xfd interception indicates that dynamic xfeatures
+ * might be used in the guest. Always trap #NM in this case
+ * to save guest xfd_err timely.
*/
- if (vcpu->arch.guest_fpu.fpstate->xfd)
+ if (vcpu->arch.xfd_no_write_intercept)
eb |= (1u << NM_VECTOR);
vmcs_write32(EXCEPTION_BITMAP, eb);
@@ -1978,9 +1980,21 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_XFD:
ret = kvm_set_msr_common(vcpu, msr_info);
- /* Update #NM interception according to guest xfd */
- if (!ret)
+ /*
+ * Always intercepting WRMSR could incur non-negligible
+ * overhead given xfd might be changed frequently in
+ * guest context switch. Disable write interception
+ * upon the first write with a non-zero value (indicating
+ * potential usage on dynamic xfeatures). Also update
+ * exception bitmap to trap #NM for proper virtualization
+ * of guest xfd_err.
+ */
+ if (!ret && data) {
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD,
+ MSR_TYPE_RW);
+ vcpu->arch.xfd_no_write_intercept = true;
vmx_update_exception_bitmap(vcpu);
+ }
break;
#endif
case MSR_IA32_SYSENTER_CS:
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 69dd2f85abdc..f8fc7441baea 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -349,7 +349,7 @@ struct vcpu_vmx {
struct lbr_desc lbr_desc;
/* Save desired MSR intercept (read: pass-through) state */
-#define MAX_POSSIBLE_PASSTHROUGH_MSRS 14
+#define MAX_POSSIBLE_PASSTHROUGH_MSRS 15
struct {
DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bde18ca657db..60da2331ec32 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10083,6 +10083,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
+ /*
+ * Sync xfd before calling handle_exit_irqoff() which may
+ * rely on the fact that guest_fpu::xfd is up-to-date (e.g.
+ * in #NM irqoff handler).
+ */
+ if (vcpu->arch.xfd_no_write_intercept)
+ fpu_sync_guest_vmexit_xfd_state();
+
static_call(kvm_x86_handle_exit_irqoff)(vcpu);
if (vcpu->arch.guest_fpu.xfd_err)
--
2.31.1
prev parent reply other threads:[~2022-01-07 18:56 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-07 18:54 [PATCH v6 00/21] AMX support for KVM Paolo Bonzini
2022-01-07 18:54 ` [PATCH v6 01/21] x86/fpu: Extend fpu_xstate_prctl() with guest permissions Paolo Bonzini
2022-01-07 18:54 ` [PATCH v6 02/21] x86/fpu: Prepare guest FPU for dynamically enabled FPU features Paolo Bonzini
2022-01-07 18:54 ` [PATCH v6 03/21] kvm: x86: Fix xstate_required_size() to follow XSTATE alignment rule Paolo Bonzini
2022-01-07 18:54 ` [PATCH v6 04/21] kvm: x86: Exclude unpermitted xfeatures at KVM_GET_SUPPORTED_CPUID Paolo Bonzini
2022-01-23 6:22 ` Like Xu
2022-01-24 7:18 ` Tian, Kevin
2022-01-07 18:54 ` [PATCH v6 05/21] x86/fpu: Make XFD initialization in __fpstate_reset() a function argument Paolo Bonzini
2022-01-07 19:43 ` Borislav Petkov
2022-01-10 5:15 ` Tian, Kevin
2022-01-10 8:52 ` Borislav Petkov
2022-01-10 14:18 ` Paolo Bonzini
2022-01-10 15:25 ` Borislav Petkov
2022-01-10 15:55 ` Paolo Bonzini
2022-01-10 18:18 ` Borislav Petkov
2022-01-11 1:45 ` Tian, Kevin
2022-01-07 18:54 ` [PATCH v6 06/21] x86/fpu: Add guest support to xfd_enable_feature() Paolo Bonzini
2022-01-07 18:54 ` [PATCH v6 07/21] x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM Paolo Bonzini
2022-01-10 5:25 ` Tian, Kevin
2022-01-07 18:54 ` [PATCH v6 08/21] kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2 Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 09/21] x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 10/21] kvm: x86: Add emulation for IA32_XFD Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 11/21] x86/fpu: Prepare xfd_err in struct fpu_guest Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 12/21] kvm: x86: Intercept #NM for saving IA32_XFD_ERR Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 13/21] kvm: x86: Emulate IA32_XFD_ERR for guest Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 14/21] kvm: x86: Disable RDMSR interception of IA32_XFD_ERR Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 15/21] kvm: x86: Add XCR0 support for Intel AMX Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 16/21] kvm: x86: Add CPUID " Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 17/21] x86/fpu: Add uabi_size to guest_fpu Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 18/21] kvm: x86: Add support for getting/setting expanded xstate buffer Paolo Bonzini
2022-01-07 18:55 ` [PATCH v6 19/21] kvm: selftests: Add support for KVM_CAP_XSAVE2 Paolo Bonzini
2022-01-17 16:51 ` Janis Schoetterl-Glausch
2022-01-18 2:06 ` Wang, Wei W
2022-01-07 18:55 ` [PATCH v6 20/21] x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state() Paolo Bonzini
2022-01-07 18:55 ` Paolo Bonzini [this message]
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=20220107185512.25321-22-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=guang.zeng@intel.com \
--cc=jing2.liu@intel.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=wei.w.wang@intel.com \
--cc=yang.zhong@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 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).