[PATCH v2] ARM: KVM: add irqfd and irq routing support
From: Eric Auger
Date: Mon Jun 02 2014 - 03:30:33 EST
This patch enables irqfd and irq routing on ARM.
It turns on CONFIG_HAVE_KVM_EVENTFD and CONFIG_HAVE_KVM_IRQ_ROUTING
irqfd framework enables to assign physical IRQs to guests.
1) user-side uses KVM_IRQFD VM ioctl to pass KVM a kvm_irqfd struct that
associates a VM, an eventfd, an IRQ number (aka. the GSI). When an actor
signals the eventfd (typically a VFIO platform driver), the irqfd subsystem
injects the specified IRQ into the VM (the "GSI" takes the semantic of a
virtual IRQ for that guest).
2) the other use case is user-side does 1) and uses KVM_SET_GSI_ROUTING
VM ioctl to create an association between a VM, a physical IRQ (aka GSI) and
a virtual IRQ (aka irchip.pin). This creates a so-called GSI routing entry.
When someone triggers the eventfd, irqfd handles it but uses the specified
routing and eventually injects irqchip.pin virtual IRQ into the guest. In that
context the GSI takes the semantic of a physical IRQ while the irqchip.pin
takes the semantic of a virtual IRQ.
in 1) routing is used by irqfd but an identity routing is created by default
making the gsi = irqchip.pin. Note on ARM there is a single interrupt
controller kind, the GIC.
GSI routing mostly is implemented in generic irqchip.c.
The tiny ARM specific part is directly implemented in the virtual interrupt
controller (vgic.c) as it is done for powerpc for instance. This option was
prefered compared to implementing other #ifdef in irq_comm.c (x86 and ia64).
Hence irq_comm.c is not used at all.
Routing currently is not used for anything else than irqfd IRQ injection. Only
SPI can be injected. This means the vgic is not totally hidden behind the
irqchip. There are separate discussions on PPI/SGI routing.
Only level sensitive IRQs are supported (with a registered resampler). As a
reminder the resampler is a second eventfd called by irqfd framework when the
virtual IRQ is completed by the guest. This eventfd is supposed to be handled
on user-side
MSI routing is not supported yet.
This work was tested with Calxeda Midway xgmac main interrupt (with and without
explicit user routing) with qemu-system-arm and QEMU VFIO platform device.
changes v1 -> v2:
2 fixes:
- v1 assumed gsi/irqchip.pin was already incremented by VGIC_NR_PRIVATE_IRQS.
This is now vgic_set_assigned_irq that increments it before injection.
- v2 now handles the case where a pending assigned irq is cleared through
MMIO access. The irq is properly acked allowing the resamplefd handler
to possibly unmask the physical IRQ.
Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
Conflicts:
Documentation/virtual/kvm/api.txt
arch/arm/kvm/Kconfig
Conflicts:
Documentation/virtual/kvm/api.txt
---
Documentation/virtual/kvm/api.txt | 4 +-
arch/arm/include/uapi/asm/kvm.h | 8 +++
arch/arm/kvm/Kconfig | 2 +
arch/arm/kvm/Makefile | 1 +
arch/arm/kvm/irq.h | 25 +++++++
virt/kvm/arm/vgic.c | 141 ++++++++++++++++++++++++++++++++++++--
6 files changed, 174 insertions(+), 7 deletions(-)
create mode 100644 arch/arm/kvm/irq.h
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index b4f5365..b376334 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1339,7 +1339,7 @@ KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
4.52 KVM_SET_GSI_ROUTING
Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 ia64 s390
+Architectures: x86 ia64 s390 arm
Type: vm ioctl
Parameters: struct kvm_irq_routing (in)
Returns: 0 on success, -1 on error
@@ -2126,7 +2126,7 @@ into the hash PTE second double word).
4.75 KVM_IRQFD
Capability: KVM_CAP_IRQFD
-Architectures: x86 s390
+Architectures: x86 s390 arm
Type: vm ioctl
Parameters: struct kvm_irqfd (in)
Returns: 0 on success, -1 on error
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index ef0c878..89b864d 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -192,6 +192,14 @@ struct kvm_arch_memory_slot {
/* Highest supported SPI, from VGIC_NR_IRQS */
#define KVM_ARM_IRQ_GIC_MAX 127
+/* needed by IRQ routing */
+
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS 1
+
+/* virtual interrupt controller input pins (max 480 SPI, 32 SGI/PPI) */
+#define KVM_IRQCHIP_NUM_PINS 256
+
/* PSCI interface */
#define KVM_PSCI_FN_BASE 0x95c1ba5e
#define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n))
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 4be5bb1..096692c 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -24,6 +24,7 @@ config KVM
select KVM_MMIO
select KVM_ARM_HOST
depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
+ select HAVE_KVM_EVENTFD
---help---
Support hosting virtualized guest machines. You will also
need to select one or more of the processor modules below.
@@ -56,6 +57,7 @@ config KVM_ARM_VGIC
bool "KVM support for Virtual GIC"
depends on KVM_ARM_HOST && OF
select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQ_ROUTING
default y
---help---
Adds support for a hardware assisted, in-kernel GIC emulation.
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 789bca9..29de111 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -21,4 +21,5 @@ obj-y += kvm-arm.o init.o interrupts.o
obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+obj-$(CONFIG_HAVE_KVM_EVENTFD) += $(KVM)/eventfd.o $(KVM)/irqchip.o
obj-$(CONFIG_KVM_ARM_TIMER) += $(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..4d6fcc6
--- /dev/null
+++ b/arch/arm/kvm/irq.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2014, STMicroelectronics
+ * Authors: Eric Auger <eric.auger@xxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include <linux/kvm_host.h>
+/*
+ * Placeholder for irqchip and irq/msi routing declarations
+ * included in irqchip.c
+ */
+
+#endif
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 56ff9be..39afa0d 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -93,6 +93,9 @@ static struct device_node *vgic_node;
#define ACCESS_WRITE_VALUE (3 << 1)
#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1))
+static struct kvm_irq_routing_entry identity_table[VGIC_NR_IRQS];
+static int set_default_routing_table(struct kvm *kvm);
+
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
static void vgic_update_state(struct kvm *kvm);
static void vgic_kick_vcpus(struct kvm *kvm);
@@ -408,11 +411,27 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ unsigned int i;
+ bool is_assigned_irq;
+ DECLARE_BITMAP(old, VGIC_NR_SHARED_IRQS);
+ DECLARE_BITMAP(diff, VGIC_NR_SHARED_IRQS);
+ unsigned long *pending =
+ vgic_bitmap_get_shared_map(&dist->irq_state);
+ u32 *reg;
+ bitmap_copy(old, pending, VGIC_NR_SHARED_IRQS);
+ reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
vcpu->vcpu_id, offset);
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
if (mmio->is_write) {
+ pending = vgic_bitmap_get_shared_map(&dist->irq_state);
+ bitmap_xor(diff, old, pending, VGIC_NR_SHARED_IRQS);
+ for_each_set_bit(i, diff, VGIC_NR_SHARED_IRQS) {
+ is_assigned_irq = kvm_irq_has_notifier(vcpu->kvm, 0, i);
+ if (is_assigned_irq)
+ kvm_notify_acked_irq(vcpu->kvm, 0, i);
+ }
vgic_update_state(vcpu->kvm);
return true;
}
@@ -1172,6 +1191,8 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
bool level_pending = false;
+ struct kvm *kvm;
+ int is_assigned_irq;
kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);
@@ -1189,12 +1210,23 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
vgic_irq_clear_active(vcpu, irq);
vgic_cpu->vgic_lr[lr] &= ~GICH_LR_EOI;
+ kvm = vcpu->kvm;
+ is_assigned_irq =
+ kvm_irq_has_notifier(kvm, 0, irq-VGIC_NR_PRIVATE_IRQS);
/* Any additional pending interrupt? */
- if (vgic_dist_irq_is_pending(vcpu, irq)) {
- vgic_cpu_irq_set(vcpu, irq);
- level_pending = true;
- } else {
+ if (is_assigned_irq) {
vgic_cpu_irq_clear(vcpu, irq);
+ kvm_debug("EOI irqchip routed vIRQ %d\n", irq);
+ kvm_notify_acked_irq(kvm, 0,
+ irq-VGIC_NR_PRIVATE_IRQS);
+ vgic_dist_irq_clear(vcpu, irq);
+ } else {
+ if (vgic_dist_irq_is_pending(vcpu, irq)) {
+ vgic_cpu_irq_set(vcpu, irq);
+ level_pending = true;
+ } else {
+ vgic_cpu_irq_clear(vcpu, irq);
+ }
}
/*
@@ -1627,6 +1659,8 @@ int kvm_vgic_create(struct kvm *kvm)
kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
+ set_default_routing_table(kvm);
+
out_unlock:
for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
@@ -2017,3 +2051,100 @@ struct kvm_device_ops kvm_arm_vgic_v2_ops = {
.get_attr = vgic_get_attr,
.has_attr = vgic_has_attr,
};
+
+
+/*
+ * set up a default identity routing table
+ * The user-side can further change the routing table using
+ * KVM_SET_GSI_ROUTING VM ioctl
+ */
+
+static int set_default_routing_table(struct kvm *kvm)
+{
+ struct kvm_irq_routing_entry;
+ int i;
+ for (i = 0; i < VGIC_NR_IRQS; i++) {
+ identity_table[i].gsi = i;
+ identity_table[i].type = KVM_IRQ_ROUTING_IRQCHIP;
+ identity_table[i].u.irqchip.irqchip = 0;
+ identity_table[i].u.irqchip.pin = i;
+ }
+ return kvm_set_irq_routing(kvm, identity_table,
+ ARRAY_SIZE(identity_table), 0);
+}
+
+
+/*
+ * Functions needed for GSI routing (used by irqchip.c)
+ * implemented in irq_comm.c for x86 and ia64
+ * in architecture specific files for some other archictures (powerpc)
+ */
+
+static int vgic_set_assigned_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ unsigned int spi = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS;
+
+ if (irq_source_id == KVM_USERSPACE_IRQ_SOURCE_ID) {
+ /*
+ * This path is not tested yet,
+ * only irqchip with resampler was exercised
+ */
+ kvm_vgic_inject_irq(kvm, 0, spi, level);
+ } else if (irq_source_id == KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID) {
+ if (level == 1) {
+ kvm_debug("Inject irqchip routed vIRQ %d\n",
+ e->irqchip.pin);
+ kvm_vgic_inject_irq(kvm, 0, spi, level);
+ /*
+ * toggling down vIRQ wire is directly handled in
+ * process_maintenance for this reason:
+ * irqfd_resampler_ack is called in
+ * process_maintenance which holds the dist lock.
+ * irqfd_resampler_ack calls kvm_set_irq
+ * which ends_up calling kvm_vgic_inject_irq.
+ * This later attempts to take the lock -> deadlock!
+ */
+ }
+ }
+ return 0;
+
+}
+
+/* void implementation requested to compile irqchip.c */
+
+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;
+}
+
+int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
+ struct kvm_kernel_irq_routing_entry *e,
+ const struct kvm_irq_routing_entry *ue)
+{
+ int r = -EINVAL;
+
+ switch (ue->type) {
+ case KVM_IRQ_ROUTING_IRQCHIP:
+ e->set = vgic_set_assigned_irq;
+ e->irqchip.irqchip = ue->u.irqchip.irqchip;
+ e->irqchip.pin = ue->u.irqchip.pin;
+ if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS)
+ goto out;
+ /* chip[0][virtualID] = physicalID */
+ rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
+ break;
+ default:
+ goto out;
+ }
+
+ r = 0;
+out:
+ return r;
+}
+
+
+
+
--
1.9.1
--
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/