KVM: x86: Add EOI exit bitmap inference

In order to support a userspace IOAPIC interacting with an in kernel
APIC, the EOI exit bitmaps need to be configurable.

If the IOAPIC is in userspace (i.e. the irqchip has been split), the
EOI exit bitmaps will be set whenever the GSI Routes are configured.
In particular, for the low MSI routes are reservable for userspace
IOAPICs. For these MSI routes, the EOI Exit bit corresponding to the
destination vector of the route will be set for the destination VCPU.

The intention is for the userspace IOAPICs to use the reservable MSI
routes to inject interrupts into the guest.

This is a slight abuse of the notion of an MSI Route, given that MSIs
classically bypass the IOAPIC. It might be worthwhile to add an
additional route type to improve clarity.

Compile tested for Intel x86.

Signed-off-by: Steve Rutherford <srutherford@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 0d14bf5db534765ea88a900ae085cb5ef1a75004..89e71648d7481b868ec0172a72ab4771b99c51ad 100644 (file)
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3642,7 +3642,7 @@ KVM handlers should exit to userspace with rc = -EREMOTE.
 7.5 KVM_CAP_SPLIT_IRQCHIP
 
 Architectures: x86
-Parameters: None
+Parameters: args[0] - number of routes reserved for userspace IOAPICs
 Returns: 0 on success, -1 on error
 
 Create a local apic for each processor in the kernel. This can be used
@@ -3650,8 +3650,11 @@ 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.
+This capability also enables in kernel routing of interrupt requests;
+when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are
+used in the IRQ routing table.  The first args[0] MSI routes are reserved
+for the IOAPIC pins.  Whenever the LAPIC receives an EOI for these routes,
+a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.
 
 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).

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index af09fa1d1be75a4d8d8280b3b5d250d4a0d89a15..7a5f9debbcd8f75fc74eaca0f8c006c082b890d9 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -688,6 +688,7 @@ struct kvm_arch {
        u64 disabled_quirks;
 
        bool irqchip_split;
+       u8 nr_reserved_ioapic_pins;
 };
 
 struct kvm_vm_stat {

diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index a8842c0dee7325ce5a6fdf3e5e5bf18ad237e0de..084617d37c74d0264926cdb26bef3fb57c06965e 100644 (file)
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -9,6 +9,7 @@ struct kvm;
 struct kvm_vcpu;
 
 #define IOAPIC_NUM_PINS  KVM_IOAPIC_NUM_PINS
+#define MAX_NR_RESERVED_IOAPIC_PINS KVM_MAX_IRQ_ROUTES
 #define IOAPIC_VERSION_ID 0x11 /* IOAPIC version */
 #define IOAPIC_EDGE_TRIG  0
 #define IOAPIC_LEVEL_TRIG 1
@@ -121,5 +122,6 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 
 #endif

diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 67f6b62a68149d32b828706c8c027cee09a3b3dc..177460998bb0d192ff1b11cf208734ceef08fd4e 100644 (file)
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -335,3 +335,45 @@ int kvm_setup_empty_irq_routing(struct kvm *kvm)
 {
        return kvm_set_irq_routing(kvm, empty_routing, 0, 0);
 }
+
+void kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+       if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm))
+               return;
+       kvm_make_scan_ioapic_request(kvm);
+}
+
+void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+       struct kvm *kvm = vcpu->kvm;
+       struct kvm_kernel_irq_routing_entry *entry;
+       struct kvm_irq_routing_table *table;
+       u32 i, nr_ioapic_pins;
+       int idx;
+
+       /* kvm->irq_routing must be read after clearing
+        * KVM_SCAN_IOAPIC. */
+       smp_mb();
+       idx = srcu_read_lock(&kvm->irq_srcu);
+       table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+       nr_ioapic_pins = min_t(u32, table->nr_rt_entries,
+                              kvm->arch.nr_reserved_ioapic_pins);
+       for (i = 0; i < nr_ioapic_pins; ++i) {
+               hlist_for_each_entry(entry, &table->map[i], link) {
+                       u32 dest_id, dest_mode;
+
+                       if (entry->type != KVM_IRQ_ROUTING_MSI)
+                               continue;
+                       dest_id = (entry->msi.address_lo >> 12) & 0xff;
+                       dest_mode = (entry->msi.address_lo >> 2) & 0x1;
+                       if (kvm_apic_match_dest(vcpu, NULL, 0, dest_id,
+                                               dest_mode)) {
+                               u32 vector = entry->msi.data & 0xff;
+
+                               __set_bit(vector,
+                                         (unsigned long *) eoi_exit_bitmap);
+                       }
+               }
+       }
+       srcu_read_unlock(&kvm->irq_srcu, idx);
+}

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ef70f6f3a37a6f5bfb43b0f5efd84f085413d62b..2f4c0d0cbe0a842df820a1cf5186b95f69bd00bc 100644 (file)
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -209,8 +209,7 @@ out:
        if (old)
                kfree_rcu(old, rcu);
 
-       if (ioapic_in_kernel(kvm))
-               kvm_vcpu_request_scan_ioapic(kvm);
+       kvm_make_scan_ioapic_request(kvm);
 }
 
 static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 27429daa054ec88eeacd2b58cb7123255e0d2af6..4aeed2086c5e1caef22c14098330450179e94dd8 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3558,6 +3558,9 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
                break;
        case KVM_CAP_SPLIT_IRQCHIP: {
                mutex_lock(&kvm->lock);
+               r = -EINVAL;
+               if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS)
+                       goto split_irqchip_unlock;
                r = -EEXIST;
                if (irqchip_in_kernel(kvm))
                        goto split_irqchip_unlock;
@@ -3569,6 +3572,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
                /* Pairs with irqchip_in_kernel. */
                smp_wmb();
                kvm->arch.irqchip_split = true;
+               kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
                r = 0;
 split_irqchip_unlock:
                mutex_unlock(&kvm->lock);
@@ -6167,7 +6171,10 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 
        memset(vcpu->arch.eoi_exit_bitmap, 0, 256 / 8);
 
-       kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap);
+       if (irqchip_split(vcpu->kvm))
+               kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap);
+       else
+               kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap);
        kvm_x86_ops->load_eoi_exitmap(vcpu);
 }
 

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3b33215ed447090c3fa6fcd314d675f64a84caea..d754f2d826e99cb1c9382bce5bc50dede4ed3a5e 100644 (file)
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -330,6 +330,18 @@ struct kvm_kernel_irq_routing_entry {
        struct hlist_node link;
 };
 
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+struct kvm_irq_routing_table {
+       int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
+       u32 nr_rt_entries;
+       /*
+        * Array indexed by gsi. Each entry contains list of irq chips
+        * the gsi is connected to.
+        */
+       struct hlist_head map[0];
+};
+#endif
+
 #ifndef KVM_PRIVATE_MEM_SLOTS
 #define KVM_PRIVATE_MEM_SLOTS 0
 #endif
@@ -456,10 +468,14 @@ void vcpu_put(struct kvm_vcpu *vcpu);
 
 #ifdef __KVM_HAVE_IOAPIC
 void kvm_vcpu_request_scan_ioapic(struct kvm *kvm);
+void kvm_arch_irq_routing_update(struct kvm *kvm);
 #else
 static inline void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
 {
 }
+static inline void kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQFD

diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index d7ea8e20dae4ee9b353441e5e342a6279d1485d6..716a1c4db528ffd8c8a2765a20579c02e1095010 100644 (file)
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -31,16 +31,6 @@
 #include <trace/events/kvm.h>
 #include "irq.h"
 
-struct kvm_irq_routing_table {
-       int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
-       u32 nr_rt_entries;
-       /*
-        * Array indexed by gsi. Each entry contains list of irq chips
-        * the gsi is connected to.
-        */
-       struct hlist_head map[0];
-};
-
 int kvm_irq_map_gsi(struct kvm *kvm,
                    struct kvm_kernel_irq_routing_entry *entries, int gsi)
 {
@@ -231,6 +221,8 @@ int kvm_set_irq_routing(struct kvm *kvm,
        kvm_irq_routing_update(kvm);
        mutex_unlock(&kvm->irq_lock);
 
+       kvm_arch_irq_routing_update(kvm);
+
        synchronize_srcu_expedited(&kvm->irq_srcu);
 
        new = old;