KVM: x86: Update IRTE for posted-interrupts

This patch adds the routine to update IRTE for posted-interrupts
when guest changes the interrupt configuration.

Signed-off-by: Feng Wu <feng.wu@intel.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
[Squashed in automatically generated patch from the build robot
 "KVM: x86: vcpu_to_pi_desc() can be static" - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 79fffbbe2348049d41dfdb7481322e7c95a7e449..a4067ecd437655108b08b95c4ea393fb9b9acb55 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -897,6 +897,9 @@ struct kvm_x86_ops {
                                           gfn_t offset, unsigned long mask);
        /* pmu operations of sub-arch */
        const struct kvm_pmu_ops *pmu_ops;
+
+       int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
+                             uint32_t guest_irq, bool set);
 };
 
 struct kvm_arch_async_pf {

diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ce4abe333c39ba853b96b95d345ce3bb1f1b4f43..120302511802ad3afa7175dfa8b61e9d9104a1fc 100644 (file)
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -992,6 +992,39 @@ TRACE_EVENT(kvm_enter_smm,
                  __entry->smbase)
 );
 
+/*
+ * Tracepoint for VT-d posted-interrupts.
+ */
+TRACE_EVENT(kvm_pi_irte_update,
+       TP_PROTO(unsigned int vcpu_id, unsigned int gsi,
+                unsigned int gvec, u64 pi_desc_addr, bool set),
+       TP_ARGS(vcpu_id, gsi, gvec, pi_desc_addr, set),
+
+       TP_STRUCT__entry(
+               __field(        unsigned int,   vcpu_id         )
+               __field(        unsigned int,   gsi             )
+               __field(        unsigned int,   gvec            )
+               __field(        u64,            pi_desc_addr    )
+               __field(        bool,           set             )
+       ),
+
+       TP_fast_assign(
+               __entry->vcpu_id        = vcpu_id;
+               __entry->gsi            = gsi;
+               __entry->gvec           = gvec;
+               __entry->pi_desc_addr   = pi_desc_addr;
+               __entry->set            = set;
+       ),
+
+       TP_printk("VT-d PI is %s for this irq, vcpu %u, gsi: 0x%x, "
+                 "gvec: 0x%x, pi_desc_addr: 0x%llx",
+                 __entry->set ? "enabled and being updated" : "disabled",
+                 __entry->vcpu_id,
+                 __entry->gsi,
+                 __entry->gvec,
+                 __entry->pi_desc_addr)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4739a52874c246e622a9e83958bec3e2bbe4fc6a..cb26b93a2cd7c90faa119e242f2df756466fb6a3 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -45,6 +45,7 @@
 #include <asm/debugreg.h>
 #include <asm/kexec.h>
 #include <asm/apic.h>
+#include <asm/irq_remapping.h>
 
 #include "trace.h"
 #include "pmu.h"
@@ -603,6 +604,11 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
        return container_of(vcpu, struct vcpu_vmx, vcpu);
 }
 
+static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+{
+       return &(to_vmx(vcpu)->pi_desc);
+}
+
 #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
 #define FIELD(number, name)    [number] = VMCS12_OFFSET(name)
 #define FIELD64(number, name)  [number] = VMCS12_OFFSET(name), \
@@ -10345,6 +10351,81 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
        kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
 }
 
+/*
+ * vmx_update_pi_irte - set IRTE for Posted-Interrupts
+ *
+ * @kvm: kvm
+ * @host_irq: host irq of the interrupt
+ * @guest_irq: gsi of the interrupt
+ * @set: set or unset PI
+ * returns 0 on success, < 0 on failure
+ */
+static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
+                             uint32_t guest_irq, bool set)
+{
+       struct kvm_kernel_irq_routing_entry *e;
+       struct kvm_irq_routing_table *irq_rt;
+       struct kvm_lapic_irq irq;
+       struct kvm_vcpu *vcpu;
+       struct vcpu_data vcpu_info;
+       int idx, ret = -EINVAL;
+
+       if (!kvm_arch_has_assigned_device(kvm) ||
+               !irq_remapping_cap(IRQ_POSTING_CAP))
+               return 0;
+
+       idx = srcu_read_lock(&kvm->irq_srcu);
+       irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+       BUG_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+       hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
+               if (e->type != KVM_IRQ_ROUTING_MSI)
+                       continue;
+               /*
+                * VT-d PI cannot support posting multicast/broadcast
+                * interrupts to a vCPU, we still use interrupt remapping
+                * for these kind of interrupts.
+                *
+                * For lowest-priority interrupts, we only support
+                * those with single CPU as the destination, e.g. user
+                * configures the interrupts via /proc/irq or uses
+                * irqbalance to make the interrupts single-CPU.
+                *
+                * We will support full lowest-priority interrupt later.
+                */
+
+               kvm_set_msi_irq(e, &irq);
+               if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu))
+                       continue;
+
+               vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
+               vcpu_info.vector = irq.vector;
+
+               trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi,
+                               vcpu_info.vector, vcpu_info.pi_desc_addr, set);
+
+               if (set)
+                       ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
+               else {
+                       /* suppress notification event before unposting */
+                       pi_set_sn(vcpu_to_pi_desc(vcpu));
+                       ret = irq_set_vcpu_affinity(host_irq, NULL);
+                       pi_clear_sn(vcpu_to_pi_desc(vcpu));
+               }
+
+               if (ret < 0) {
+                       printk(KERN_INFO "%s: failed to update PI IRTE\n",
+                                       __func__);
+                       goto out;
+               }
+       }
+
+       ret = 0;
+out:
+       srcu_read_unlock(&kvm->irq_srcu, idx);
+       return ret;
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
        .cpu_has_kvm_support = cpu_has_kvm_support,
        .disabled_by_bios = vmx_disabled_by_bios,
@@ -10462,6 +10543,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
        .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
 
        .pmu_ops = &intel_pmu_ops,
+
+       .update_pi_irte = vmx_update_pi_irte,
 };
 
 static int __init vmx_init(void)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 185fc1619c99e0e46ae14f824ff94c8b600290c1..3978ace4ddbc95caafc23ea095ff84ac9a4ed44b 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -64,6 +64,7 @@
 #include <asm/fpu/internal.h> /* Ugh! */
 #include <asm/pvclock.h>
 #include <asm/div64.h>
+#include <asm/irq_remapping.h>
 
 #define MAX_IO_MSRS 256
 #define KVM_MAX_MCE_BANKS 32
@@ -8094,3 +8095,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);