Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   Zeng Guang <guang.zeng@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>, kvm@vger.kernel.org,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Tony Luck <tony.luck@intel.com>,
        Kan Liang <kan.liang@linux.intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        "H. Peter Anvin" <hpa@zytor.com>,
        Kim Phillips <kim.phillips@amd.com>,
        Jarkko Sakkinen <jarkko@kernel.org>,
        Jethro Beekman <jethro@fortanix.com>,
        Kai Huang <kai.huang@intel.com>
Cc:     x86@kernel.org, linux-kernel@vger.kernel.org,
        Robert Hu <robert.hu@intel.com>, Gao Chao <chao.gao@intel.com>,
        Zeng Guang <guang.zeng@intel.com>
Subject: [PATCH v8 5/9] KVM: x86: Add support for vICR APIC-write VM-Exits in x2APIC mode
Date:   Mon, 11 Apr 2022 17:04:43 +0800
Message-Id: <20220411090447.5928-6-guang.zeng@intel.com>
In-Reply-To: <20220411090447.5928-1-guang.zeng@intel.com>
References: <20220411090447.5928-1-guang.zeng@intel.com>
Precedence: bulk

Upcoming Intel CPUs will support virtual x2APIC MSR writes to the vICR,
i.e. will trap and generate an APIC-write VM-Exit instead of intercepting
the WRMSR.  Add support for handling "nodecode" x2APIC writes, which
were previously impossible.

Note, x2APIC MSR writes are 64 bits wide.

Signed-off-by: Zeng Guang <guang.zeng@intel.com>
---
 arch/x86/kvm/lapic.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 66b0eb0bda94..137c3a2f5180 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -67,6 +67,7 @@ static bool lapic_timer_advance_dynamic __read_mostly;
 #define LAPIC_TIMER_ADVANCE_NS_MAX     5000
 /* step-by-step approximation to mitigate fluctuation */
 #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data);
 
 static inline void __kvm_lapic_set_reg(char *regs, int reg_off, u32 val)
 {
@@ -2230,10 +2231,27 @@ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 /* emulate APIC access in a trap manner */
 void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
 {
-	u32 val = kvm_lapic_get_reg(vcpu->arch.apic, offset);
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u64 val;
+
+	if (apic_x2apic_mode(apic)) {
+		/*
+		 * When guest APIC is in x2APIC mode and IPI virtualization
+		 * is enabled, accessing APIC_ICR may cause trap-like VM-exit
+		 * on Intel hardware. Other offsets are not possible.
+		 */
+		if (WARN_ON_ONCE(offset != APIC_ICR))
+			return;
 
-	/* TODO: optimize to just emulate side effect w/o one more write */
-	kvm_lapic_reg_write(vcpu->arch.apic, offset, val);
+		kvm_lapic_msr_read(apic, offset, &val);
+		kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32));
+		trace_kvm_apic_write(APIC_ICR, val);
+	} else {
+		val = kvm_lapic_get_reg(apic, offset);
+
+		/* TODO: optimize to just emulate side effect w/o one more write */
+		kvm_lapic_reg_write(apic, offset, (u32)val);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode);
 
-- 
2.27.0