[PULL,069/115] KVM: Kick resamplefd for split kernel irqchip

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index b048c10af9..f24d7da783 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -160,9 +160,59 @@  static const KVMCapabilityInfo kvm_required_capabilites[] = {
 static NotifierList kvm_irqchip_change_notifiers =
     NOTIFIER_LIST_INITIALIZER(kvm_irqchip_change_notifiers);
 
+struct KVMResampleFd {
+    int gsi;
+    EventNotifier *resample_event;
+    QLIST_ENTRY(KVMResampleFd) node;
+};
+typedef struct KVMResampleFd KVMResampleFd;
+
+/*
+ * Only used with split irqchip where we need to do the resample fd
+ * kick for the kernel from userspace.
+ */
+static QLIST_HEAD(, KVMResampleFd) kvm_resample_fd_list =
+    QLIST_HEAD_INITIALIZER(kvm_resample_fd_list);
+
 #define kvm_slots_lock(kml)      qemu_mutex_lock(&(kml)->slots_lock)
 #define kvm_slots_unlock(kml)    qemu_mutex_unlock(&(kml)->slots_lock)
 
+static inline void kvm_resample_fd_remove(int gsi)
+{
+    KVMResampleFd *rfd;
+
+    QLIST_FOREACH(rfd, &kvm_resample_fd_list, node) {
+        if (rfd->gsi == gsi) {
+            QLIST_REMOVE(rfd, node);
+            g_free(rfd);
+            break;
+        }
+    }
+}
+
+static inline void kvm_resample_fd_insert(int gsi, EventNotifier *event)
+{
+    KVMResampleFd *rfd = g_new0(KVMResampleFd, 1);
+
+    rfd->gsi = gsi;
+    rfd->resample_event = event;
+
+    QLIST_INSERT_HEAD(&kvm_resample_fd_list, rfd, node);
+}
+
+void kvm_resample_fd_notify(int gsi)
+{
+    KVMResampleFd *rfd;
+
+    QLIST_FOREACH(rfd, &kvm_resample_fd_list, node) {
+        if (rfd->gsi == gsi) {
+            event_notifier_set(rfd->resample_event);
+            trace_kvm_resample_fd_notify(gsi);
+            return;
+        }
+    }
+}
+
 int kvm_get_max_memslots(void)
 {
     KVMState *s = KVM_STATE(current_accel());
@@ -1676,8 +1726,33 @@  static int kvm_irqchip_assign_irqfd(KVMState *s, EventNotifier *event,
     };
 
     if (rfd != -1) {
-        irqfd.flags |= KVM_IRQFD_FLAG_RESAMPLE;
-        irqfd.resamplefd = rfd;
+        assert(assign);
+        if (kvm_irqchip_is_split()) {
+            /*
+             * When the slow irqchip (e.g. IOAPIC) is in the
+             * userspace, KVM kernel resamplefd will not work because
+             * the EOI of the interrupt will be delivered to userspace
+             * instead, so the KVM kernel resamplefd kick will be
+             * skipped.  The userspace here mimics what the kernel
+             * provides with resamplefd, remember the resamplefd and
+             * kick it when we receive EOI of this IRQ.
+             *
+             * This is hackery because IOAPIC is mostly bypassed
+             * (except EOI broadcasts) when irqfd is used.  However
+             * this can bring much performance back for split irqchip
+             * with INTx IRQs (for VFIO, this gives 93% perf of the
+             * full fast path, which is 46% perf boost comparing to
+             * the INTx slow path).
+             */
+            kvm_resample_fd_insert(virq, resample);
+        } else {
+            irqfd.flags |= KVM_IRQFD_FLAG_RESAMPLE;
+            irqfd.resamplefd = rfd;
+        }
+    } else if (!assign) {
+        if (kvm_irqchip_is_split()) {
+            kvm_resample_fd_remove(virq);
+        }
     }
 
     if (!kvm_irqfds_enabled()) {
diff --git a/accel/kvm/trace-events b/accel/kvm/trace-events
index 4fb6e59d19..a68eb66534 100644
--- a/accel/kvm/trace-events
+++ b/accel/kvm/trace-events
@@ -16,4 +16,5 @@  kvm_set_ioeventfd_mmio(int fd, uint64_t addr, uint32_t val, bool assign, uint32_
 kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint32_t val, bool assign, uint32_t size, bool datamatch) "fd: %d @0x%x val=0x%x assign: %d size: %d match: %d"
 kvm_set_user_memory(uint32_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, int ret) "Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " ret=%d"
 kvm_clear_dirty_log(uint32_t slot, uint64_t start, uint32_t size) "slot#%"PRId32" start 0x%"PRIx64" size 0x%"PRIx32
+kvm_resample_fd_notify(int gsi) "gsi %d"
 
diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c
index ffe30dc457..bca71b5934 100644
--- a/hw/intc/ioapic.c
+++ b/hw/intc/ioapic.c
@@ -241,6 +241,25 @@  void ioapic_eoi_broadcast(int vector)
                 continue;
             }
 
+#ifdef CONFIG_KVM
+            /*
+             * When IOAPIC is in the userspace while APIC is still in
+             * the kernel (i.e., split irqchip), we have a trick to
+             * kick the resamplefd logic for registered irqfds from
+             * userspace to deactivate the IRQ.  When that happens, it
+             * means the irq bypassed userspace IOAPIC (so the irr and
+             * remote-irr of the table entry should be bypassed too
+             * even if interrupt come).  Still kick the resamplefds if
+             * they're bound to the IRQ, to make sure to EOI the
+             * interrupt for the hardware correctly.
+             *
+             * Note: We still need to go through the irr & remote-irr
+             * operations below because we don't know whether there're
+             * emulated devices that are using/sharing the same IRQ.
+             */
+            kvm_resample_fd_notify(n);
+#endif
+
             if (!(entry & IOAPIC_LVT_REMOTE_IRR)) {
                 continue;
             }
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index 3b2250471c..b4174d941c 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -554,4 +554,8 @@  int kvm_set_one_reg(CPUState *cs, uint64_t id, void *source);
 int kvm_get_one_reg(CPUState *cs, uint64_t id, void *target);
 struct ppc_radix_page_info *kvm_get_radix_page_info(void);
 int kvm_get_max_memslots(void);
+
+/* Notify resamplefd for EOI of specific interrupts. */
+void kvm_resample_fd_notify(int gsi);
+
 #endif