x86: irq: Define a global vector for nested posted interrupts

We are using the same vector for nested/non-nested posted
interrupts delivery, this may cause interrupts latency in
L1 since we can't kick the L2 vcpu out of vmx-nonroot mode.

This patch introduces a new vector which is only for nested
posted interrupts to solve the problems above.

Signed-off-by: Wincy Van <fanwenyi0529@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

7 files changed, 29 insertions, 1 deletions

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a9a8027a6c0e..d271fb79248f 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -705,6 +705,7 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR		x86_platform_ipi		smp_x86_platform_ipi
 #ifdef CONFIG_HAVE_KVM
 apicinterrupt3 POSTED_INTR_VECTOR		kvm_posted_intr_ipi		smp_kvm_posted_intr_ipi
 apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR	kvm_posted_intr_wakeup_ipi	smp_kvm_posted_intr_wakeup_ipi
+apicinterrupt3 POSTED_INTR_NESTED_VECTOR	kvm_posted_intr_nested_ipi	smp_kvm_posted_intr_nested_ipi
 #endif
 
 #ifdef CONFIG_X86_MCE_THRESHOLD
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index df002992d8fd..07b06955a05d 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -25,6 +25,8 @@ BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
 		 smp_kvm_posted_intr_ipi)
 BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
 		 smp_kvm_posted_intr_wakeup_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR,
+		 smp_kvm_posted_intr_nested_ipi)
 #endif
 
 /*
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 9b76cd331990..ad1ed531febc 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -15,6 +15,7 @@ typedef struct {
 #ifdef CONFIG_HAVE_KVM
 	unsigned int kvm_posted_intr_ipis;
 	unsigned int kvm_posted_intr_wakeup_ipis;
+	unsigned int kvm_posted_intr_nested_ipis;
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b90e1053049b..d6dbafbd4207 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -30,6 +30,7 @@ extern asmlinkage void apic_timer_interrupt(void);
 extern asmlinkage void x86_platform_ipi(void);
 extern asmlinkage void kvm_posted_intr_ipi(void);
 extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
+extern asmlinkage void kvm_posted_intr_nested_ipi(void);
 extern asmlinkage void error_interrupt(void);
 extern asmlinkage void irq_work_interrupt(void);
 
@@ -62,6 +63,7 @@ extern void trace_call_function_single_interrupt(void);
 #define trace_reboot_interrupt  reboot_interrupt
 #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
 #define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
+#define trace_kvm_posted_intr_nested_ipi kvm_posted_intr_nested_ipi
 #endif /* CONFIG_TRACING */
 
 #ifdef	CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 6ca9fd6234e1..aaf8d28b5d00 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -83,7 +83,6 @@
  */
 #define X86_PLATFORM_IPI_VECTOR		0xf7
 
-#define POSTED_INTR_WAKEUP_VECTOR	0xf1
 /*
  * IRQ work vector:
  */
@@ -98,6 +97,8 @@
 /* Vector for KVM to deliver posted interrupt IPI */
 #ifdef CONFIG_HAVE_KVM
 #define POSTED_INTR_VECTOR		0xf2
+#define POSTED_INTR_WAKEUP_VECTOR	0xf1
+#define POSTED_INTR_NESTED_VECTOR	0xf0
 #endif
 
 /*
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 4aa03c5a14c9..4ed0aba8dbc8 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -155,6 +155,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
 	seq_puts(p, "  Posted-interrupt notification event\n");
 
+	seq_printf(p, "%*s: ", prec, "NPI");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ",
+			   irq_stats(j)->kvm_posted_intr_nested_ipis);
+	seq_puts(p, "  Nested posted-interrupt event\n");
+
 	seq_printf(p, "%*s: ", prec, "PIW");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ",
@@ -313,6 +319,19 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
 	exiting_irq();
 	set_irq_regs(old_regs);
 }
+
+/*
+ * Handler for POSTED_INTERRUPT_NESTED_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	entering_ack_irq();
+	inc_irq_stat(kvm_posted_intr_nested_ipis);
+	exiting_irq();
+	set_irq_regs(old_regs);
+}
 #endif
 
 __visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs)
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 7468c6987547..c7fd18526c3e 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -150,6 +150,8 @@ static void __init apic_intr_init(void)
 	alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
 	/* IPI for KVM to deliver interrupt to wake up tasks */
 	alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
+	/* IPI for KVM to deliver nested posted interrupt */
+	alloc_intr_gate(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi);
 #endif
 
 	/* IPI vectors for APIC spurious and error interrupts */