Hi Vitaly,
On 4/29/20 7:36 PM, Vitaly Kuznetsov wrote:
KVM now supports using interrupt for type 2 APF event delivery (page ready
notifications). Switch KVM guests to using it when the feature is present.
Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
arch/x86/entry/entry_32.S | 5 ++++
arch/x86/entry/entry_64.S | 5 ++++
arch/x86/include/asm/hardirq.h | 3 +++
arch/x86/include/asm/irq_vectors.h | 6 ++++-
arch/x86/include/asm/kvm_para.h | 6 +++++
arch/x86/kernel/irq.c | 9 +++++++
arch/x86/kernel/kvm.c | 42 ++++++++++++++++++++++++++++++
7 files changed, 75 insertions(+), 1 deletion(-)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index b67bae7091d7..d574dadcb2a1 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1475,6 +1475,11 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR,
#endif /* CONFIG_HYPERV */
+#ifdef CONFIG_KVM_GUEST
+BUILD_INTERRUPT3(kvm_async_pf_vector, KVM_ASYNC_PF_VECTOR,
+ kvm_async_pf_intr)
+#endif
+
SYM_CODE_START(page_fault)
ASM_CLAC
pushl $do_page_fault
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 0e9504fabe52..6f127c1a6547 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1190,6 +1190,11 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
acrn_hv_callback_vector acrn_hv_vector_handler
#endif
+#ifdef CONFIG_KVM_GUEST
+apicinterrupt3 KVM_ASYNC_PF_VECTOR \
+ kvm_async_pf_vector kvm_async_pf_intr
+#endif
+
idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET
idtentry int3 do_int3 has_error_code=0 create_gap=1
idtentry stack_segment do_stack_segment has_error_code=1
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 07533795b8d2..be0fbb15ad7f 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -44,6 +44,9 @@ typedef struct {
unsigned int irq_hv_reenlightenment_count;
unsigned int hyperv_stimer0_count;
#endif
+#ifdef CONFIG_KVM_GUEST
+ unsigned int kvm_async_pf_pageready_count;
+#endif
} ____cacheline_aligned irq_cpustat_t;
DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 889f8b1b5b7f..8879a9ecd908 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -104,7 +104,11 @@
#define HYPERV_STIMER0_VECTOR 0xed
#endif
-#define LOCAL_TIMER_VECTOR 0xec
+#ifdef CONFIG_KVM_GUEST
+#define KVM_ASYNC_PF_VECTOR 0xec
+#endif
+
+#define LOCAL_TIMER_VECTOR 0xeb
#define NR_VECTORS 256
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 9b4df6eaa11a..fde4f21607f9 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -4,6 +4,7 @@
#include <asm/processor.h>
#include <asm/alternative.h>
+#include <linux/interrupt.h>
#include <uapi/asm/kvm_para.h>
extern void kvmclock_init(void);
@@ -93,6 +94,11 @@ void kvm_async_pf_task_wake(u32 token);
u32 kvm_read_and_reset_pf_reason(void);
extern void kvm_disable_steal_time(void);
void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
+extern void kvm_async_pf_vector(void);
+#ifdef CONFIG_TRACING
+#define trace_kvm_async_pf_vector kvm_async_pf_vector
+#endif
+__visible void __irq_entry kvm_async_pf_intr(struct pt_regs *regs);
#ifdef CONFIG_PARAVIRT_SPINLOCKS
void __init kvm_spinlock_init(void);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index c7965ff429c5..a4c2f25ad74d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -159,6 +159,15 @@ int arch_show_interrupts(struct seq_file *p, int prec)
irq_stats(j)->hyperv_stimer0_count);
seq_puts(p, " Hyper-V stimer0 interrupts\n");
}
+#endif
+#ifdef CONFIG_KVM_GUEST
+ if (test_bit(KVM_ASYNC_PF_VECTOR, system_vectors)) {
+ seq_printf(p, "%*s: ", prec, "APF");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->kvm_async_pf_pageready_count);
+ seq_puts(p, " KVM async PF page ready interrupts\n");
+ }
#endif
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 6efe0410fb72..1c00c7ba01ff 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -259,9 +259,39 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned lon
rcu_irq_exit();
break;
}
+
+ if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT))
+ wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
}
NOKPROBE_SYMBOL(do_async_page_fault);
+__visible void __irq_entry kvm_async_pf_intr(struct pt_regs *regs)
+{
+ u32 token, reason;
+
+ entering_ack_irq();
+
+ inc_irq_stat(kvm_async_pf_pageready_count);
+
+ if (__this_cpu_read(apf_reason.enabled)) {
+ reason = __this_cpu_read(apf_reason.reason);
+ if (reason == KVM_PV_REASON_PAGE_READY) {
+ token = __this_cpu_read(apf_reason.token);
+ /*
+ * Make sure we read 'token' before we reset
+ * 'reason' or it can get lost.
+ */
+ mb();
+ __this_cpu_write(apf_reason.reason, 0);
+ kvm_async_pf_task_wake(token);
+ }
+ }
+
+ wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
+
+ exiting_irq();
+}
In theory, it's possible the interrupt happens in the context of the
suspended process. With the call to kvm_async_pf_task_wake(), the
suspended process tries to wake up itself, but it seems it's not
working because of aacedf26fb760 ("sched/core: Optimize try_to_wake_up()
for local wakeups").
It's one of issue I observed when enabling async page fault for arm64,
but not sure it's valid to x86.
Thanks,
Gavin
static void __init paravirt_ops_setup(void)
{
pv_info.name = "KVM";
@@ -316,10 +346,17 @@ static void kvm_guest_cpu_init(void)
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
+ if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT))
+ pa |= KVM_ASYNC_PF_DELIVERY_AS_INT;
+
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
__this_cpu_write(apf_reason.enabled, 1);
printk(KERN_INFO"KVM setup async PF for cpu %d\n",
smp_processor_id());
+
+ if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT))
+ wrmsrl(MSR_KVM_ASYNC_PF2, KVM_ASYNC_PF2_ENABLED |
+ KVM_ASYNC_PF_VECTOR);
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) {
@@ -649,6 +686,11 @@ static void __init kvm_guest_init(void)
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apic_set_eoi_write(kvm_guest_apic_eoi_write);
+ if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT)) {
+ pr_info("KVM using interrupt for async PF page-ready\n");
+ alloc_intr_gate(KVM_ASYNC_PF_VECTOR, kvm_async_pf_vector);
+ }
+
#ifdef CONFIG_SMP
smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
