[PATCH v2 09/13] KVM: x86: More precisely identify NMI from guest when handling PMI

From: Sean Christopherson <seanjc@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Will Deacon <will@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Marc Zyngier <maz@kernel.org>, Guo Ren <guoren@kernel.org>,
	Nick Hu <nickhu@andestech.com>, Greentime Hu <green.hu@gmail.com>,
	Vincent Chen <deanbo422@gmail.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Thomas Gleixner <tglx@linutronix.de>,
	Borislav Petkov <bp@alien8.de>,
	x86@kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Juergen Gross <jgross@suse.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	James Morse <james.morse@arm.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	"H. Peter Anvin" <hpa@zytor.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>,
	Stefano Stabellini <sstabellini@kernel.org>,
	linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, linux-csky@vger.kernel.org,
	linux-riscv@lists.infradead.org, kvm@vger.kernel.org,
	xen-devel@lists.xenproject.org,
	Artem Kashkanov <artem.kashkanov@intel.com>,
	Like Xu <like.xu.linux@gmail.com>,
	Zhu Lingshan <lingshan.zhu@intel.com>
Subject: [PATCH v2 09/13] KVM: x86: More precisely identify NMI from guest when handling PMI
Date: Fri, 27 Aug 2021 17:35:54 -0700	[thread overview]
Message-ID: <20210828003558.713983-10-seanjc@google.com> (raw)
In-Reply-To: <20210828003558.713983-1-seanjc@google.com>

Differntiate between IRQ and NMI for KVM's PMC overflow callback, which
was originally invoked in response to an NMI that arrived while the guest
was running, but was inadvertantly changed to fire on IRQs as well when
support for perf without PMU/NMI was added to KVM.  In practice, this
should be a nop as the PMC overflow callback shouldn't be reached, but
it's a cheap and easy fix that also better documents the situation.

Note, this also doesn't completely prevent false positives if perf
somehow ends up calling into KVM, e.g. an NMI can arrive in host after
KVM sets its flag.

Fixes: dd60d217062f ("KVM: x86: Fix perf timer mode IP reporting")
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c |  2 +-
 arch/x86/kvm/vmx/vmx.c |  4 +++-
 arch/x86/kvm/x86.c     |  2 +-
 arch/x86/kvm/x86.h     | 13 ++++++++++---
 4 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 1a70e11f0487..0a0c01744b63 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3843,7 +3843,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
-		kvm_before_interrupt(vcpu);
+		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 
 	kvm_load_host_xsave_state(vcpu);
 	stgi();
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f19d72136f77..61a4f5ff2acd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6344,7 +6344,9 @@ void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
 static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
 					unsigned long entry)
 {
-	kvm_before_interrupt(vcpu);
+	bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist;
+
+	kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ);
 	vmx_do_interrupt_nmi_irqoff(entry);
 	kvm_after_interrupt(vcpu);
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6df300c55461..1427ac1fc1f2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9676,7 +9676,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 * interrupts on processors that implement an interrupt shadow, the
 	 * stat.exits increment will do nicely.
 	 */
-	kvm_before_interrupt(vcpu);
+	kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ);
 	local_irq_enable();
 	++vcpu->stat.exits;
 	local_irq_disable();
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a9c107e7c907..9b26f9b09d2a 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -387,9 +387,16 @@ static inline bool kvm_cstate_in_guest(struct kvm *kvm)
 	return kvm->arch.cstate_in_guest;
 }
 
-static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
+enum kvm_intr_type {
+	/* Values are arbitrary, but must be non-zero. */
+	KVM_HANDLING_IRQ = 1,
+	KVM_HANDLING_NMI,
+};
+
+static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu,
+					enum kvm_intr_type intr)
 {
-	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 1);
+	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, (u8)intr);
 }
 
 static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
@@ -399,7 +406,7 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
 
 static inline bool kvm_handling_nmi_from_guest(struct kvm_vcpu *vcpu)
 {
-	return !!vcpu->arch.handling_intr_from_guest;
+	return vcpu->arch.handling_intr_from_guest == KVM_HANDLING_NMI;
 }
 
 static inline bool kvm_pat_valid(u64 data)
-- 
2.33.0.259.gc128427fd7-goog

