[FYI PATCH 06/20] KVM: x86: Split the APIC from the rest of IRQCHIP.

From: Paolo Bonzini
Date: Mon Sep 28 2015 - 06:44:48 EST


From: Steve Rutherford <srutherford@xxxxxxxxxx>

First patch in a series which enables the relocation of the
PIC/IOAPIC to userspace.

Adds capability KVM_CAP_SPLIT_IRQCHIP;

KVM_CAP_SPLIT_IRQCHIP enables the construction of LAPICs without the
rest of the irqchip.

Compile tested for x86.

Signed-off-by: Steve Rutherford <srutherford@xxxxxxxxxx>
Suggested-by: Andrew Honig <ahonig@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
Documentation/virtual/kvm/api.txt | 17 +++++++++++++++++
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/kvm/i8254.c | 4 +++-
arch/x86/kvm/ioapic.h | 8 ++++++++
arch/x86/kvm/irq.h | 11 ++++++++++-
arch/x86/kvm/irq_comm.c | 9 ++++++++-
arch/x86/kvm/lapic.c | 6 ++++--
arch/x86/kvm/x86.c | 23 +++++++++++++++++++++--
include/linux/kvm_host.h | 1 +
include/uapi/linux/kvm.h | 1 +
10 files changed, 75 insertions(+), 7 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index d9ecceea5a02..43e0816d0de1 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3627,6 +3627,23 @@ struct {

KVM handlers should exit to userspace with rc = -EREMOTE.

+7.5 KVM_CAP_SPLIT_IRQCHIP
+
+Architectures: x86
+Parameters: None
+Returns: 0 on success, -1 on error
+
+Create a local apic for each processor in the kernel. This can be used
+instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
+IOAPIC and PIC (and also the PIT, even though this has to be enabled
+separately).
+
+This supersedes KVM_CREATE_IRQCHIP, creating only local APICs, but no in kernel
+IOAPIC or PIC. This also enables in kernel routing of interrupt requests.
+
+Fails if VCPU has already been created, or if the irqchip is already in the
+kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
+

8. Other capabilities.
----------------------
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a0ef289d5a86..befcf555bddc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -684,6 +684,8 @@ struct kvm_arch {
u32 bsp_vcpu_id;

u64 disabled_quirks;
+
+ bool irqchip_split;
};

struct kvm_vm_stat {
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index f90952f64e79..08116ff227cc 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -35,6 +35,7 @@
#include <linux/kvm_host.h>
#include <linux/slab.h>

+#include "ioapic.h"
#include "irq.h"
#include "i8254.h"
#include "x86.h"
@@ -333,7 +334,8 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
s64 interval;

- if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
+ if (!ioapic_in_kernel(kvm) ||
+ ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
return;

interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index bf36d66a1951..a8842c0dee73 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -97,6 +97,14 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
return kvm->arch.vioapic;
}

+static inline int ioapic_in_kernel(struct kvm *kvm)
+{
+ int ret;
+
+ ret = (ioapic_irqchip(kvm) != NULL);
+ return ret;
+}
+
void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, unsigned int dest, int dest_mode);
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 9e6e7e04de98..2f9703dcd913 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -83,13 +83,22 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
return kvm->arch.vpic;
}

+static inline int irqchip_split(struct kvm *kvm)
+{
+ return kvm->arch.irqchip_split;
+}
+
static inline int irqchip_in_kernel(struct kvm *kvm)
{
struct kvm_pic *vpic = pic_irqchip(kvm);
+ bool ret;
+
+ ret = (vpic != NULL);
+ ret |= irqchip_split(kvm);

/* Read vpic before kvm->irq_routing. */
smp_rmb();
- return vpic != NULL;
+ return ret;
}

static inline int lapic_in_kernel(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 9efff9e5b58c..67f6b62a6814 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -208,7 +208,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
goto unlock;
}
clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
- if (!irqchip_in_kernel(kvm))
+ if (!ioapic_in_kernel(kvm))
goto unlock;

kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
@@ -328,3 +328,10 @@ int kvm_setup_default_irq_routing(struct kvm *kvm)
return kvm_set_irq_routing(kvm, default_routing,
ARRAY_SIZE(default_routing), 0);
}
+
+static const struct kvm_irq_routing_entry empty_routing[] = {};
+
+int kvm_setup_empty_irq_routing(struct kvm *kvm)
+{
+ return kvm_set_irq_routing(kvm, empty_routing, 0, 0);
+}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c4bcc86d6dc4..e05946c36b87 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -209,7 +209,8 @@ out:
if (old)
kfree_rcu(old, rcu);

- kvm_vcpu_request_scan_ioapic(kvm);
+ if (ioapic_in_kernel(kvm))
+ kvm_vcpu_request_scan_ioapic(kvm);
}

static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
@@ -1845,7 +1846,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
apic_find_highest_isr(apic));
kvm_make_request(KVM_REQ_EVENT, vcpu);
- kvm_rtc_eoi_tracking_restore_one(vcpu);
+ if (ioapic_in_kernel(vcpu->kvm))
+ kvm_rtc_eoi_tracking_restore_one(vcpu);
}

void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 080aaa7a4d91..b6fbda026708 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2452,6 +2452,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_ENABLE_CAP_VM:
case KVM_CAP_DISABLE_QUIRKS:
case KVM_CAP_SET_BOOT_CPU_ID:
+ case KVM_CAP_SPLIT_IRQCHIP:
#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_PCI_2_3:
@@ -3559,6 +3560,24 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
kvm->arch.disabled_quirks = cap->args[0];
r = 0;
break;
+ case KVM_CAP_SPLIT_IRQCHIP: {
+ mutex_lock(&kvm->lock);
+ r = -EEXIST;
+ if (irqchip_in_kernel(kvm))
+ goto split_irqchip_unlock;
+ if (atomic_read(&kvm->online_vcpus))
+ goto split_irqchip_unlock;
+ r = kvm_setup_empty_irq_routing(kvm);
+ if (r)
+ goto split_irqchip_unlock;
+ /* Pairs with irqchip_in_kernel. */
+ smp_wmb();
+ kvm->arch.irqchip_split = true;
+ r = 0;
+split_irqchip_unlock:
+ mutex_unlock(&kvm->lock);
+ break;
+ }
default:
r = -EINVAL;
break;
@@ -3672,7 +3691,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
}

r = -ENXIO;
- if (!irqchip_in_kernel(kvm))
+ if (!irqchip_in_kernel(kvm) || irqchip_split(kvm))
goto get_irqchip_out;
r = kvm_vm_ioctl_get_irqchip(kvm, chip);
if (r)
@@ -3696,7 +3715,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
}

r = -ENXIO;
- if (!irqchip_in_kernel(kvm))
+ if (!irqchip_in_kernel(kvm) || irqchip_split(kvm))
goto set_irqchip_out;
r = kvm_vm_ioctl_set_irqchip(kvm, chip);
if (r)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1bef9e21e725..354f147647ab 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1002,6 +1002,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
#endif

int kvm_setup_default_irq_routing(struct kvm *kvm);
+int kvm_setup_empty_irq_routing(struct kvm *kvm);
int kvm_set_irq_routing(struct kvm *kvm,
const struct kvm_irq_routing_entry *entries,
unsigned nr,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index a9256f0331ae..ed00f8fc9ea2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -824,6 +824,7 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_MULTI_ADDRESS_SPACE 118
#define KVM_CAP_GUEST_DEBUG_HW_BPS 119
#define KVM_CAP_GUEST_DEBUG_HW_WPS 120
+#define KVM_CAP_SPLIT_IRQCHIP 121

#ifdef KVM_CAP_IRQ_ROUTING

--
1.8.3.1


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/