Merge tag 'kvm-arm-for-4.8-take2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/ARM Changes for v4.8 - Take 2
Includes GSI routing support to go along with the new VGIC and a small fix that
has been cooking in -next for a while.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 5237e1b..da3c395 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1433,13 +1433,16 @@
4.52 KVM_SET_GSI_ROUTING
Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 s390
+Architectures: x86 s390 arm arm64
Type: vm ioctl
Parameters: struct kvm_irq_routing (in)
Returns: 0 on success, -1 on error
Sets the GSI routing table entries, overwriting any previously set entries.
+On arm/arm64, GSI routing has the following limitation:
+- GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.
+
struct kvm_irq_routing {
__u32 nr;
__u32 flags;
@@ -1468,7 +1471,13 @@
#define KVM_IRQ_ROUTING_S390_ADAPTER 3
#define KVM_IRQ_ROUTING_HV_SINT 4
-No flags are specified so far, the corresponding field must be set to zero.
+flags:
+- KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
+ type, specifies that the devid field contains a valid value. The per-VM
+ KVM_CAP_MSI_DEVID capability advertises the requirement to provide
+ the device ID. If this capability is not available, userspace should
+ never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
+- zero otherwise
struct kvm_irq_routing_irqchip {
__u32 irqchip;
@@ -1479,9 +1488,16 @@
__u32 address_lo;
__u32 address_hi;
__u32 data;
- __u32 pad;
+ union {
+ __u32 pad;
+ __u32 devid;
+ };
};
+If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
+for the device that wrote the MSI message. For PCI, this is usually a
+BFD identifier in the lower 16 bits.
+
On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
@@ -2199,14 +2215,14 @@
__u8 pad[12];
};
-flags: KVM_MSI_VALID_DEVID: devid contains a valid value
-devid: If KVM_MSI_VALID_DEVID is set, contains a unique device identifier
- for the device that wrote the MSI message.
- For PCI, this is usually a BFD identifier in the lower 16 bits.
+flags: KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM
+ KVM_CAP_MSI_DEVID capability advertises the requirement to provide
+ the device ID. If this capability is not available, userspace
+ should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
-The per-VM KVM_CAP_MSI_DEVID capability advertises the need to provide
-the device ID. If this capability is not set, userland cannot rely on
-the kernel to allow the KVM_MSI_VALID_DEVID flag being set.
+If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
+for the device that wrote the MSI message. For PCI, this is usually a
+BFD identifier in the lower 16 bits.
On x86, address_hi is ignored unless the KVM_CAP_X2APIC_API capability is
enabled. If it is enabled, address_hi bits 31-8 provide bits 31-8 of the
@@ -2383,9 +2399,13 @@
irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
-On ARM/ARM64, the gsi field in the kvm_irqfd struct specifies the Shared
-Peripheral Interrupt (SPI) index, such that the GIC interrupt ID is
-given by gsi + 32.
+On arm/arm64, gsi routing being supported, the following can happen:
+- in case no routing entry is associated to this gsi, injection fails
+- in case the gsi is associated to an irqchip routing entry,
+ irqchip.pin + 32 corresponds to the injected SPI ID.
+- in case the gsi is associated to an MSI routing entry, the MSI
+ message and device ID are translated into an LPI (support restricted
+ to GICv3 ITS in-kernel emulation).
4.76 KVM_PPC_ALLOCATE_HTAB
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 95a0005..3e1cd04 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -32,6 +32,8 @@
select KVM_VFIO
select HAVE_KVM_EVENTFD
select HAVE_KVM_IRQFD
+ select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQ_ROUTING
depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
---help---
Support hosting virtualized guest machines.
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 5e28df8..10d77a6 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -29,4 +29,5 @@
obj-y += $(KVM)/arm/vgic/vgic-mmio.o
obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
+obj-y += $(KVM)/irqchip.o
obj-y += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/irq.h b/arch/arm/kvm/irq.h
new file mode 100644
index 0000000..b74099b
--- /dev/null
+++ b/arch/arm/kvm/irq.h
@@ -0,0 +1,19 @@
+/*
+ * irq.h: in kernel interrupt controller related definitions
+ * Copyright (c) 2016 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This header is included by irqchip.c. However, on ARM, interrupt
+ * controller declarations are located in include/kvm/arm_vgic.h since
+ * they are mostly shared between arm and arm64.
+ */
+
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include <kvm/arm_vgic.h>
+
+#endif
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 9d2eff0..9c9edc9 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -37,6 +37,8 @@
select KVM_ARM_VGIC_V3
select KVM_ARM_PMU if HW_PERF_EVENTS
select HAVE_KVM_MSI
+ select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQ_ROUTING
---help---
Support hosting virtualized guest machines.
We don't support KVM with 16K page tables yet, due to the multiple
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index a5b9664..695eb3c 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -30,5 +30,6 @@
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-mmio-v3.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-kvm-device.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic-its.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/irqchip.o
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o
kvm-$(CONFIG_KVM_ARM_PMU) += $(KVM)/arm/pmu.o
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index e9e0e6d..898c0e6 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -132,16 +132,14 @@
static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
{
unsigned long cpsr = *vcpu_cpsr(vcpu);
- bool is_aarch32;
+ bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
u32 esr = 0;
- is_aarch32 = vcpu_mode_is_32bit(vcpu);
-
- *vcpu_spsr(vcpu) = cpsr;
*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
-
*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
+
*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+ *vcpu_spsr(vcpu) = cpsr;
vcpu_sys_reg(vcpu, FAR_EL1) = addr;
@@ -172,11 +170,11 @@
unsigned long cpsr = *vcpu_cpsr(vcpu);
u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
- *vcpu_spsr(vcpu) = cpsr;
*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
-
*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
+
*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+ *vcpu_spsr(vcpu) = cpsr;
/*
* Build an unknown exception, depending on the instruction
diff --git a/arch/arm64/kvm/irq.h b/arch/arm64/kvm/irq.h
new file mode 100644
index 0000000..b74099b
--- /dev/null
+++ b/arch/arm64/kvm/irq.h
@@ -0,0 +1,19 @@
+/*
+ * irq.h: in kernel interrupt controller related definitions
+ * Copyright (c) 2016 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This header is included by irqchip.c. However, on ARM, interrupt
+ * controller declarations are located in include/kvm/arm_vgic.h since
+ * they are mostly shared between arm and arm64.
+ */
+
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include <kvm/arm_vgic.h>
+
+#endif
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 61ebdc1..035731e 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -120,4 +120,7 @@
int apic_has_pending_timer(struct kvm_vcpu *vcpu);
+int kvm_setup_default_irq_routing(struct kvm *kvm);
+int kvm_setup_empty_irq_routing(struct kvm *kvm);
+
#endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 540da51..19b698e 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -34,6 +34,7 @@
#define VGIC_MAX_SPI 1019
#define VGIC_MAX_RESERVED 1023
#define VGIC_MIN_LPI 8192
+#define KVM_IRQCHIP_NUM_PINS (1020 - 32)
enum vgic_type {
VGIC_V2, /* Good ol' GICv2 */
@@ -314,4 +315,10 @@
int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+/**
+ * kvm_vgic_setup_default_irq_routing:
+ * Setup a default flat gsi routing table mapping all SPIs
+ */
+int kvm_vgic_setup_default_irq_routing(struct kvm *kvm);
+
#endif /* __KVM_ARM_VGIC_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index aafd702..01e908a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -317,7 +317,13 @@
unsigned irqchip;
unsigned pin;
} irqchip;
- struct msi_msg msi;
+ struct {
+ u32 address_lo;
+ u32 address_hi;
+ u32 data;
+ u32 flags;
+ u32 devid;
+ } msi;
struct kvm_s390_adapter_int adapter;
struct kvm_hv_sint hv_sint;
};
@@ -1003,12 +1009,12 @@
#ifdef CONFIG_S390
#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that...
+#elif defined(CONFIG_ARM64)
+#define KVM_MAX_IRQ_ROUTES 4096
#else
#define KVM_MAX_IRQ_ROUTES 1024
#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 e98bb4c..300ef25 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -882,7 +882,10 @@
__u32 address_lo;
__u32 address_hi;
__u32 data;
- __u32 pad;
+ union {
+ __u32 pad;
+ __u32 devid;
+ };
};
struct kvm_irq_routing_s390_adapter {
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 1e30ce0..fb4b0a7 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -264,6 +264,10 @@
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_vgic_vcpu_init(vcpu);
+ ret = kvm_vgic_setup_default_irq_routing(kvm);
+ if (ret)
+ goto out;
+
dist->initialized = true;
out:
return ret;
diff --git a/virt/kvm/arm/vgic/vgic-irqfd.c b/virt/kvm/arm/vgic/vgic-irqfd.c
index c675513..b31a51a 100644
--- a/virt/kvm/arm/vgic/vgic-irqfd.c
+++ b/virt/kvm/arm/vgic/vgic-irqfd.c
@@ -17,36 +17,116 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <trace/events/kvm.h>
+#include <kvm/arm_vgic.h>
+#include "vgic.h"
-int kvm_irq_map_gsi(struct kvm *kvm,
- struct kvm_kernel_irq_routing_entry *entries,
- int gsi)
+/**
+ * vgic_irqfd_set_irq: inject the IRQ corresponding to the
+ * irqchip routing entry
+ *
+ * This is the entry point for irqfd IRQ injection
+ */
+static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id,
+ int level, bool line_status)
{
- return 0;
+ unsigned int spi_id = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS;
+
+ if (!vgic_valid_spi(kvm, spi_id))
+ return -EINVAL;
+ return kvm_vgic_inject_irq(kvm, 0, spi_id, level);
}
-int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned int irqchip,
- unsigned int pin)
+/**
+ * kvm_set_routing_entry: populate a kvm routing entry
+ * from a user routing entry
+ *
+ * @kvm: the VM this entry is applied to
+ * @e: kvm kernel routing entry handle
+ * @ue: user api routing entry handle
+ * return 0 on success, -EINVAL on errors.
+ */
+#ifdef KVM_CAP_X2APIC_API
+int kvm_set_routing_entry(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *e,
+ const struct kvm_irq_routing_entry *ue)
+#else
+/* Remove this version and the ifdefery once merged into 4.8 */
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+ const struct kvm_irq_routing_entry *ue)
+#endif
{
- return pin;
+ int r = -EINVAL;
+
+ switch (ue->type) {
+ case KVM_IRQ_ROUTING_IRQCHIP:
+ e->set = vgic_irqfd_set_irq;
+ e->irqchip.irqchip = ue->u.irqchip.irqchip;
+ e->irqchip.pin = ue->u.irqchip.pin;
+ if ((e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) ||
+ (e->irqchip.irqchip >= KVM_NR_IRQCHIPS))
+ goto out;
+ break;
+ case KVM_IRQ_ROUTING_MSI:
+ e->set = kvm_set_msi;
+ e->msi.address_lo = ue->u.msi.address_lo;
+ e->msi.address_hi = ue->u.msi.address_hi;
+ e->msi.data = ue->u.msi.data;
+ e->msi.flags = ue->flags;
+ e->msi.devid = ue->u.msi.devid;
+ break;
+ default:
+ goto out;
+ }
+ r = 0;
+out:
+ return r;
}
-int kvm_set_irq(struct kvm *kvm, int irq_source_id,
- u32 irq, int level, bool line_status)
-{
- unsigned int spi = irq + VGIC_NR_PRIVATE_IRQS;
-
- trace_kvm_set_irq(irq, level, irq_source_id);
-
- BUG_ON(!vgic_initialized(kvm));
-
- return kvm_vgic_inject_irq(kvm, 0, spi, level);
-}
-
-/* MSI not implemented yet */
+/**
+ * kvm_set_msi: inject the MSI corresponding to the
+ * MSI routing entry
+ *
+ * This is the entry point for irqfd MSI injection
+ * and userspace MSI injection.
+ */
int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id,
int level, bool line_status)
{
- return 0;
+ struct kvm_msi msi;
+
+ msi.address_lo = e->msi.address_lo;
+ msi.address_hi = e->msi.address_hi;
+ msi.data = e->msi.data;
+ msi.flags = e->msi.flags;
+ msi.devid = e->msi.devid;
+
+ if (!vgic_has_its(kvm))
+ return -ENODEV;
+
+ return vgic_its_inject_msi(kvm, &msi);
+}
+
+int kvm_vgic_setup_default_irq_routing(struct kvm *kvm)
+{
+ struct kvm_irq_routing_entry *entries;
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ u32 nr = dist->nr_spis;
+ int i, ret;
+
+ entries = kcalloc(nr, sizeof(struct kvm_kernel_irq_routing_entry),
+ GFP_KERNEL);
+ if (!entries)
+ return -ENOMEM;
+
+ for (i = 0; i < nr; i++) {
+ entries[i].gsi = i;
+ entries[i].type = KVM_IRQ_ROUTING_IRQCHIP;
+ entries[i].u.irqchip.irqchip = 0;
+ entries[i].u.irqchip.pin = i;
+ }
+ ret = kvm_set_irq_routing(kvm, entries, nr, 0);
+ kfree(entries);
+ return ret;
}
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 39f3358..e7aeac7 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -711,10 +711,3 @@
return map_is_active;
}
-int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
-{
- if (vgic_has_its(kvm))
- return vgic_its_inject_msi(kvm, msi);
- else
- return -ENODEV;
-}
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index df99e9c..3bcc999 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -62,12 +62,14 @@
{
struct kvm_kernel_irq_routing_entry route;
- if (!irqchip_in_kernel(kvm) || msi->flags != 0)
+ if (!irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID))
return -EINVAL;
route.msi.address_lo = msi->address_lo;
route.msi.address_hi = msi->address_hi;
route.msi.data = msi->data;
+ route.msi.flags = msi->flags;
+ route.msi.devid = msi->devid;
return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false);
}
@@ -177,6 +179,7 @@
unsigned flags)
{
struct kvm_irq_routing_table *new, *old;
+ struct kvm_kernel_irq_routing_entry *e;
u32 i, j, nr_rt_entries = 0;
int r;
@@ -200,23 +203,25 @@
new->chip[i][j] = -1;
for (i = 0; i < nr; ++i) {
- struct kvm_kernel_irq_routing_entry *e;
-
r = -ENOMEM;
e = kzalloc(sizeof(*e), GFP_KERNEL);
if (!e)
goto out;
r = -EINVAL;
- if (ue->flags) {
- kfree(e);
- goto out;
+ switch (ue->type) {
+ case KVM_IRQ_ROUTING_MSI:
+ if (ue->flags & ~KVM_MSI_VALID_DEVID)
+ goto free_entry;
+ break;
+ default:
+ if (ue->flags)
+ goto free_entry;
+ break;
}
r = setup_routing_entry(kvm, new, e, ue);
- if (r) {
- kfree(e);
- goto out;
- }
+ if (r)
+ goto free_entry;
++ue;
}
@@ -233,7 +238,10 @@
new = old;
r = 0;
+ goto out;
+free_entry:
+ kfree(e);
out:
free_irq_routing_table(new);