Merge remote-tracking branch 'remotes/awilliam/tags/vfio-update-20150706.0' into staging

VFIO updates for 2.4-rc0
- "real" host page size API (Peter Crosthwaite)
- platform device irqfd support (Eric Auger)
- spapr container disconnect fix (Alexey Kardashevskiy)
- quirk for broken Chelsio hardware (Gabriel Laupre)
- coverity fix (Paolo Bonzini)

# gpg: Signature made Mon Jul  6 19:23:49 2015 BST using RSA key ID 3BB08B22
# gpg: Good signature from "Alex Williamson <alex.williamson@redhat.com>"
# gpg:                 aka "Alex Williamson <alex@shazbot.org>"
# gpg:                 aka "Alex Williamson <alwillia@redhat.com>"
# gpg:                 aka "Alex Williamson <alex.l.williamson@gmail.com>"

* remotes/awilliam/tags/vfio-update-20150706.0:
  vfio/pci : Add pba_offset PCI quirk for Chelsio T5 devices
  vfio: Unregister IOMMU notifiers when container is destroyed
  hw/vfio/platform: add irqfd support
  kvm: some fixes to kvm_resamplefds_allowed
  sysbus: add irq_routing_notifier
  intc: arm_gic_kvm: set the qemu_irq/gsi mapping
  kvm-all.c: add qemu_irq/gsi hash table and utility routines
  kvm: rename kvm_irqchip_[add,remove]_irqfd_notifier with gsi suffix
  vfio: cpu: Use "real" page size API
  cpu-all: complete "real" host page size API
  vfio: fix return type of pread

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

Conflicts:
	kvm-all.c

16 files changed, 224 insertions, 21 deletions

diff --git a/hw/core/sysbus.c b/hw/core/sysbus.c
index 278a2d1bdd..3c58629894 100644
--- a/hw/core/sysbus.c
+++ b/hw/core/sysbus.c
@@ -109,7 +109,13 @@ qemu_irq sysbus_get_connected_irq(SysBusDevice *dev, int n)
 
 void sysbus_connect_irq(SysBusDevice *dev, int n, qemu_irq irq)
 {
+    SysBusDeviceClass *sbd = SYS_BUS_DEVICE_GET_CLASS(dev);
+
     qdev_connect_gpio_out_named(DEVICE(dev), SYSBUS_DEVICE_GPIO_IRQ, n, irq);
+
+    if (sbd->connect_irq_notifier) {
+        sbd->connect_irq_notifier(dev, irq);
+    }
 }
 
 /* Check whether an MMIO region exists */
diff --git a/hw/intc/arm_gic_kvm.c b/hw/intc/arm_gic_kvm.c
index 2cb7d255d2..f56bff1afb 100644
--- a/hw/intc/arm_gic_kvm.c
+++ b/hw/intc/arm_gic_kvm.c
@@ -570,6 +570,12 @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp)
      */
     i += (GIC_INTERNAL * s->num_cpu);
     qdev_init_gpio_in(dev, kvm_arm_gic_set_irq, i);
+
+    for (i = 0; i < s->num_irq - GIC_INTERNAL; i++) {
+        qemu_irq irq = qdev_get_gpio_in(dev, i);
+        kvm_irqchip_set_qemuirq_gsi(kvm_state, irq, i);
+    }
+
     /* We never use our outbound IRQ/FIQ lines but provide them so that
      * we maintain the same interface as the non-KVM GIC.
      */
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index d631337e11..e345a6e9b8 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -1316,8 +1316,8 @@ static int virtio_ccw_add_irqfd(VirtioCcwDevice *dev, int n)
     VirtQueue *vq = virtio_get_queue(vdev, n);
     EventNotifier *notifier = virtio_queue_get_guest_notifier(vq);
 
-    return kvm_irqchip_add_irqfd_notifier(kvm_state, notifier, NULL,
-                                          dev->routes.gsi[n]);
+    return kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, notifier, NULL,
+                                              dev->routes.gsi[n]);
 }
 
 static void virtio_ccw_remove_irqfd(VirtioCcwDevice *dev, int n)
@@ -1327,8 +1327,8 @@ static void virtio_ccw_remove_irqfd(VirtioCcwDevice *dev, int n)
     EventNotifier *notifier = virtio_queue_get_guest_notifier(vq);
     int ret;
 
-    ret = kvm_irqchip_remove_irqfd_notifier(kvm_state, notifier,
-                                            dev->routes.gsi[n]);
+    ret = kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, notifier,
+                                                dev->routes.gsi[n]);
     assert(ret == 0);
 }
 
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index b1045da857..85ee9b005e 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -772,11 +772,19 @@ static void vfio_disconnect_container(VFIOGroup *group)
 
     if (QLIST_EMPTY(&container->group_list)) {
         VFIOAddressSpace *space = container->space;
+        VFIOGuestIOMMU *giommu, *tmp;
 
         if (container->iommu_data.release) {
             container->iommu_data.release(container);
         }
         QLIST_REMOVE(container, next);
+
+        QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) {
+            memory_region_unregister_iommu_notifier(&giommu->n);
+            QLIST_REMOVE(giommu, giommu_next);
+            g_free(giommu);
+        }
+
         trace_vfio_disconnect_container(container->fd);
         close(container->fd);
         g_free(container);
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index e0e339a534..2ed877fe9f 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -597,7 +597,7 @@ static void vfio_add_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage *msg,
         return;
     }
 
-    if (kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->kvm_interrupt,
+    if (kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &vector->kvm_interrupt,
                                        NULL, virq) < 0) {
         kvm_irqchip_release_virq(kvm_state, virq);
         event_notifier_cleanup(&vector->kvm_interrupt);
@@ -609,8 +609,8 @@ static void vfio_add_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage *msg,
 
 static void vfio_remove_kvm_msi_virq(VFIOMSIVector *vector)
 {
-    kvm_irqchip_remove_irqfd_notifier(kvm_state, &vector->kvm_interrupt,
-                                      vector->virq);
+    kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &vector->kvm_interrupt,
+                                          vector->virq);
     kvm_irqchip_release_virq(kvm_state, vector->virq);
     vector->virq = -1;
     event_notifier_cleanup(&vector->kvm_interrupt);
@@ -939,7 +939,7 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev)
     };
     uint64_t size;
     off_t off = 0;
-    size_t bytes;
+    ssize_t bytes;
 
     if (ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_REGION_INFO, &reg_info)) {
         error_report("vfio: Error getting ROM info: %m");
@@ -2252,6 +2252,33 @@ static int vfio_early_setup_msix(VFIOPCIDevice *vdev)
     vdev->msix->pba_offset = pba & ~PCI_MSIX_FLAGS_BIRMASK;
     vdev->msix->entries = (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
 
+    /*
+     * Test the size of the pba_offset variable and catch if it extends outside
+     * of the specified BAR. If it is the case, we need to apply a hardware
+     * specific quirk if the device is known or we have a broken configuration.
+     */
+    if (vdev->msix->pba_offset >=
+        vdev->bars[vdev->msix->pba_bar].region.size) {
+
+        PCIDevice *pdev = &vdev->pdev;
+        uint16_t vendor = pci_get_word(pdev->config + PCI_VENDOR_ID);
+        uint16_t device = pci_get_word(pdev->config + PCI_DEVICE_ID);
+
+        /*
+         * Chelsio T5 Virtual Function devices are encoded as 0x58xx for T5
+         * adapters. The T5 hardware returns an incorrect value of 0x8000 for
+         * the VF PBA offset while the BAR itself is only 8k. The correct value
+         * is 0x1000, so we hard code that here.
+         */
+        if (vendor == PCI_VENDOR_ID_CHELSIO && (device & 0xff00) == 0x5800) {
+            vdev->msix->pba_offset = 0x1000;
+        } else {
+            error_report("vfio: Hardware reports invalid configuration, "
+                         "MSIX PBA outside of specified BAR");
+            return -EINVAL;
+        }
+    }
+
     trace_vfio_early_setup_msix(vdev->vbasedev.name, pos,
                                 vdev->msix->table_bar,
                                 vdev->msix->table_offset,
@@ -2388,7 +2415,7 @@ static void vfio_map_bar(VFIOPCIDevice *vdev, int nr)
      * potentially insert a direct-mapped subregion before and after it.
      */
     if (vdev->msix && vdev->msix->table_bar == nr) {
-        size = vdev->msix->table_offset & qemu_host_page_mask;
+        size = vdev->msix->table_offset & qemu_real_host_page_mask;
     }
 
     strncat(name, " mmap", sizeof(name) - strlen(name) - 1);
@@ -2401,8 +2428,9 @@ static void vfio_map_bar(VFIOPCIDevice *vdev, int nr)
     if (vdev->msix && vdev->msix->table_bar == nr) {
         uint64_t start;
 
-        start = HOST_PAGE_ALIGN((uint64_t)vdev->msix->table_offset +
-                                (vdev->msix->entries * PCI_MSIX_ENTRY_SIZE));
+        start = REAL_HOST_PAGE_ALIGN((uint64_t)vdev->msix->table_offset +
+                                     (vdev->msix->entries *
+                                      PCI_MSIX_ENTRY_SIZE));
 
         size = start < bar->region.size ? bar->region.size - start : 0;
         strncat(name, " msix-hi", sizeof(name) - strlen(name) - 1);
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
index 5c678b914e..60365d1279 100644
--- a/hw/vfio/platform.c
+++ b/hw/vfio/platform.c
@@ -26,6 +26,7 @@
 #include "hw/sysbus.h"
 #include "trace.h"
 #include "hw/platform-bus.h"
+#include "sysemu/kvm.h"
 
 /*
  * Functions used whatever the injection method
@@ -51,6 +52,7 @@ static VFIOINTp *vfio_init_intp(VFIODevice *vbasedev,
     intp->pin = info.index;
     intp->flags = info.flags;
     intp->state = VFIO_IRQ_INACTIVE;
+    intp->kvm_accel = false;
 
     sysbus_init_irq(sbdev, &intp->qemuirq);
 
@@ -61,6 +63,13 @@ static VFIOINTp *vfio_init_intp(VFIODevice *vbasedev,
         error_report("vfio: Error: trigger event_notifier_init failed ");
         return NULL;
     }
+    /* Get an eventfd for resample/unmask */
+    ret = event_notifier_init(&intp->unmask, 0);
+    if (ret) {
+        g_free(intp);
+        error_report("vfio: Error: resamplefd event_notifier_init failed");
+        return NULL;
+    }
 
     QLIST_INSERT_HEAD(&vdev->intp_list, intp, next);
     return intp;
@@ -315,6 +324,94 @@ static int vfio_start_eventfd_injection(VFIOINTp *intp)
     return ret;
 }
 
+/*
+ * Functions used for irqfd
+ */
+
+/**
+ * vfio_set_resample_eventfd - sets the resamplefd for an IRQ
+ * @intp: the IRQ struct handle
+ * programs the VFIO driver to unmask this IRQ when the
+ * intp->unmask eventfd is triggered
+ */
+static int vfio_set_resample_eventfd(VFIOINTp *intp)
+{
+    VFIODevice *vbasedev = &intp->vdev->vbasedev;
+    struct vfio_irq_set *irq_set;
+    int argsz, ret;
+    int32_t *pfd;
+
+    argsz = sizeof(*irq_set) + sizeof(*pfd);
+    irq_set = g_malloc0(argsz);
+    irq_set->argsz = argsz;
+    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_UNMASK;
+    irq_set->index = intp->pin;
+    irq_set->start = 0;
+    irq_set->count = 1;
+    pfd = (int32_t *)&irq_set->data;
+    *pfd = event_notifier_get_fd(&intp->unmask);
+    qemu_set_fd_handler(*pfd, NULL, NULL, NULL);
+    ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
+    g_free(irq_set);
+    if (ret < 0) {
+        error_report("vfio: Failed to set resample eventfd: %m");
+    }
+    return ret;
+}
+
+static void vfio_start_irqfd_injection(SysBusDevice *sbdev, qemu_irq irq)
+{
+    VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(sbdev);
+    VFIOINTp *intp;
+
+    if (!kvm_irqfds_enabled() || !kvm_resamplefds_enabled() ||
+        !vdev->irqfd_allowed) {
+        return;
+    }
+
+    QLIST_FOREACH(intp, &vdev->intp_list, next) {
+        if (intp->qemuirq == irq) {
+            break;
+        }
+    }
+    assert(intp);
+
+    /* Get to a known interrupt state */
+    qemu_set_fd_handler(event_notifier_get_fd(&intp->interrupt),
+                        NULL, NULL, vdev);
+
+    vfio_mask_single_irqindex(&vdev->vbasedev, intp->pin);
+    qemu_set_irq(intp->qemuirq, 0);
+
+    if (kvm_irqchip_add_irqfd_notifier(kvm_state, &intp->interrupt,
+                                   &intp->unmask, irq) < 0) {
+        goto fail_irqfd;
+    }
+
+    if (vfio_set_trigger_eventfd(intp, NULL) < 0) {
+        goto fail_vfio;
+    }
+    if (vfio_set_resample_eventfd(intp) < 0) {
+        goto fail_vfio;
+    }
+
+    /* Let's resume injection with irqfd setup */
+    vfio_unmask_single_irqindex(&vdev->vbasedev, intp->pin);
+
+    intp->kvm_accel = true;
+
+    trace_vfio_platform_start_irqfd_injection(intp->pin,
+                                     event_notifier_get_fd(&intp->interrupt),
+                                     event_notifier_get_fd(&intp->unmask));
+    return;
+fail_vfio:
+    kvm_irqchip_remove_irqfd_notifier(kvm_state, &intp->interrupt, irq);
+fail_irqfd:
+    vfio_start_eventfd_injection(intp);
+    vfio_unmask_single_irqindex(&vdev->vbasedev, intp->pin);
+    return;
+}
+
 /* VFIO skeleton */
 
 static void vfio_platform_compute_needs_reset(VFIODevice *vbasedev)
@@ -584,17 +681,20 @@ static Property vfio_platform_dev_properties[] = {
     DEFINE_PROP_BOOL("x-mmap", VFIOPlatformDevice, vbasedev.allow_mmap, true),
     DEFINE_PROP_UINT32("mmap-timeout-ms", VFIOPlatformDevice,
                        mmap_timeout, 1100),
+    DEFINE_PROP_BOOL("x-irqfd", VFIOPlatformDevice, irqfd_allowed, true),
     DEFINE_PROP_END_OF_LIST(),
 };
 
 static void vfio_platform_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
+    SysBusDeviceClass *sbc = SYS_BUS_DEVICE_CLASS(klass);
 
     dc->realize = vfio_platform_realize;
     dc->props = vfio_platform_dev_properties;
     dc->vmsd = &vfio_platform_vmstate;
     dc->desc = "VFIO-based platform device assignment";
+    sbc->connect_irq_notifier = vfio_start_irqfd_injection;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
 }
 
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 6a0174e9cc..7a89081e4f 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -495,7 +495,7 @@ static int kvm_virtio_pci_irqfd_use(VirtIOPCIProxy *proxy,
     VirtQueue *vq = virtio_get_queue(vdev, queue_no);
     EventNotifier *n = virtio_queue_get_guest_notifier(vq);
     int ret;
-    ret = kvm_irqchip_add_irqfd_notifier(kvm_state, n, NULL, irqfd->virq);
+    ret = kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, n, NULL, irqfd->virq);
     return ret;
 }
 
@@ -509,7 +509,7 @@ static void kvm_virtio_pci_irqfd_release(VirtIOPCIProxy *proxy,
     VirtIOIRQFD *irqfd = &proxy->vector_irqfd[vector];
     int ret;
 
-    ret = kvm_irqchip_remove_irqfd_notifier(kvm_state, n, irqfd->virq);
+    ret = kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, n, irqfd->virq);
     assert(ret == 0);
 }
 
diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h
index 8999634981..ea6a9a667c 100644
--- a/include/exec/cpu-all.h
+++ b/include/exec/cpu-all.h
@@ -183,10 +183,13 @@ extern unsigned long reserved_va;
 
 /* ??? These should be the larger of uintptr_t and target_ulong.  */
 extern uintptr_t qemu_real_host_page_size;
+extern uintptr_t qemu_real_host_page_mask;
 extern uintptr_t qemu_host_page_size;
 extern uintptr_t qemu_host_page_mask;
 
 #define HOST_PAGE_ALIGN(addr) (((addr) + qemu_host_page_size - 1) & qemu_host_page_mask)
+#define REAL_HOST_PAGE_ALIGN(addr) (((addr) + qemu_real_host_page_size - 1) & \
+                                    qemu_real_host_page_mask)
 
 /* same as PROT_xxx */
 #define PAGE_READ      0x0001
diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h
index 49c062b8ce..d98e6c915d 100644
--- a/include/hw/pci/pci_ids.h
+++ b/include/hw/pci/pci_ids.h
@@ -114,6 +114,8 @@
 #define PCI_VENDOR_ID_ENSONIQ            0x1274
 #define PCI_DEVICE_ID_ENSONIQ_ES1370     0x5000
 
+#define PCI_VENDOR_ID_CHELSIO            0x1425
+
 #define PCI_VENDOR_ID_FREESCALE          0x1957
 #define PCI_DEVICE_ID_MPC8533E           0x0030
 
diff --git a/include/hw/sysbus.h b/include/hw/sysbus.h
index 34f93c39bf..cc1dba49bf 100644
--- a/include/hw/sysbus.h
+++ b/include/hw/sysbus.h
@@ -58,6 +58,7 @@ typedef struct SysBusDeviceClass {
      * omitted then. (This is not considered a fatal error.)
      */
     char *(*explicit_ofw_unit_address)(const SysBusDevice *dev);
+    void (*connect_irq_notifier)(SysBusDevice *dev, qemu_irq irq);
 } SysBusDeviceClass;
 
 struct SysBusDevice {
diff --git a/include/hw/vfio/vfio-platform.h b/include/hw/vfio/vfio-platform.h
index 26b2ad6f4e..c5cf1d79f3 100644
--- a/include/hw/vfio/vfio-platform.h
+++ b/include/hw/vfio/vfio-platform.h
@@ -41,6 +41,7 @@ typedef struct VFIOINTp {
     int state; /* inactive, pending, active */
     uint8_t pin; /* index */
     uint32_t flags; /* IRQ info flags */
+    bool kvm_accel; /* set when QEMU bypass through KVM enabled */
 } VFIOINTp;
 
 /* function type for user side eventfd handler */
@@ -57,6 +58,7 @@ typedef struct VFIOPlatformDevice {
     uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */
     QEMUTimer *mmap_timer; /* allows fast-path resume after IRQ hit */
     QemuMutex intp_mutex; /* protect the intp_list IRQ state */
+    bool irqfd_allowed; /* debug option to force irqfd on/off */
 } VFIOPlatformDevice;
 
 typedef struct VFIOPlatformDeviceClass {
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index f459fbdbd4..983e99e1e7 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -19,6 +19,7 @@
 #include "qemu/queue.h"
 #include "qom/cpu.h"
 #include "exec/memattrs.h"
+#include "hw/irq.h"
 
 #ifdef CONFIG_KVM
 #include <linux/kvm.h>
@@ -151,6 +152,7 @@ extern bool kvm_readonly_mem_allowed;
 #define kvm_halt_in_kernel() (false)
 #define kvm_eventfds_enabled() (false)
 #define kvm_irqfds_enabled() (false)
+#define kvm_resamplefds_enabled() (false)
 #define kvm_msi_via_irqfd_enabled() (false)
 #define kvm_gsi_routing_allowed() (false)
 #define kvm_gsi_direct_mapping() (false)
@@ -416,9 +418,15 @@ void kvm_irqchip_release_virq(KVMState *s, int virq);
 
 int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter);
 
+int kvm_irqchip_add_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
+                                       EventNotifier *rn, int virq);
+int kvm_irqchip_remove_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
+                                          int virq);
 int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
-                                   EventNotifier *rn, int virq);
-int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq);
+                                   EventNotifier *rn, qemu_irq irq);
+int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n,
+                                      qemu_irq irq);
+void kvm_irqchip_set_qemuirq_gsi(KVMState *s, qemu_irq irq, int gsi);
 void kvm_pc_gsi_handler(void *opaque, int n, int level);
 void kvm_pc_setup_irq_routing(bool pci_enabled);
 void kvm_init_irq_routing(KVMState *s);
diff --git a/kvm-all.c b/kvm-all.c
index edff01ca03..06e06f2b3f 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -35,6 +35,7 @@
 #include "exec/address-spaces.h"
 #include "qemu/event_notifier.h"
 #include "trace.h"
+#include "hw/irq.h"
 
 #include "hw/boards.h"
 
@@ -84,6 +85,7 @@ struct KVMState
      * unsigned, and treating them as signed here can break things */
     unsigned irq_set_ioctl;
     unsigned int sigmask_len;
+    GHashTable *gsimap;
 #ifdef KVM_CAP_IRQ_ROUTING
     struct kvm_irq_routing *irq_routes;
     int nr_allocated_irq_routes;
@@ -1332,19 +1334,49 @@ int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
 }
 #endif /* !KVM_CAP_IRQ_ROUTING */
 
-int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
-                                   EventNotifier *rn, int virq)
+int kvm_irqchip_add_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
+                                       EventNotifier *rn, int virq)
 {
     return kvm_irqchip_assign_irqfd(s, event_notifier_get_fd(n),
            rn ? event_notifier_get_fd(rn) : -1, virq, true);
 }
 
-int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
+int kvm_irqchip_remove_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
+                                          int virq)
 {
     return kvm_irqchip_assign_irqfd(s, event_notifier_get_fd(n), -1, virq,
            false);
 }
 
+int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
+                                   EventNotifier *rn, qemu_irq irq)
+{
+    gpointer key, gsi;
+    gboolean found = g_hash_table_lookup_extended(s->gsimap, irq, &key, &gsi);
+
+    if (!found) {
+        return -ENXIO;
+    }
+    return kvm_irqchip_add_irqfd_notifier_gsi(s, n, rn, GPOINTER_TO_INT(gsi));
+}
+
+int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n,
+                                      qemu_irq irq)
+{
+    gpointer key, gsi;
+    gboolean found = g_hash_table_lookup_extended(s->gsimap, irq, &key, &gsi);
+
+    if (!found) {
+        return -ENXIO;
+    }
+    return kvm_irqchip_remove_irqfd_notifier_gsi(s, n, GPOINTER_TO_INT(gsi));
+}
+
+void kvm_irqchip_set_qemuirq_gsi(KVMState *s, qemu_irq irq, int gsi)
+{
+    g_hash_table_insert(s->gsimap, irq, GINT_TO_POINTER(gsi));
+}
+
 static void kvm_irqchip_create(MachineState *machine, KVMState *s)
 {
     int ret;
@@ -1380,6 +1412,8 @@ static void kvm_irqchip_create(MachineState *machine, KVMState *s)
     kvm_halt_in_kernel_allowed = true;
 
     kvm_init_irq_routing(s);
+
+    s->gsimap = g_hash_table_new(g_direct_hash, g_direct_equal);
 }
 
 /* Find number of supported CPUs using the recommended
diff --git a/kvm-stub.c b/kvm-stub.c
index 7ba90c546f..d9ad624eee 100644
--- a/kvm-stub.c
+++ b/kvm-stub.c
@@ -24,6 +24,7 @@ bool kvm_kernel_irqchip;
 bool kvm_async_interrupts_allowed;
 bool kvm_eventfds_allowed;
 bool kvm_irqfds_allowed;
+bool kvm_resamplefds_allowed;
 bool kvm_msi_via_irqfd_allowed;
 bool kvm_gsi_routing_allowed;
 bool kvm_gsi_direct_mapping;
@@ -137,13 +138,14 @@ int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter)
     return -ENOSYS;
 }
 
-int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
-                                   EventNotifier *rn, int virq)
+int kvm_irqchip_add_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
+                                       EventNotifier *rn, int virq)
 {
     return -ENOSYS;
 }
 
-int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
+int kvm_irqchip_remove_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
+                                          int virq)
 {
     return -ENOSYS;
 }
diff --git a/trace-events b/trace-events
index 52b7efa9a4..d24d80aed2 100644
--- a/trace-events
+++ b/trace-events
@@ -1594,6 +1594,7 @@ vfio_platform_intp_interrupt(int pin, int fd) "Inject IRQ #%d (fd = %d)"
 vfio_platform_intp_inject_pending_lockheld(int pin, int fd) "Inject pending IRQ #%d (fd = %d)"
 vfio_platform_populate_interrupts(int pin, int count, int flags) "- IRQ index %d: count %d, flags=0x%x"
 vfio_intp_interrupt_set_pending(int index) "irq %d is set PENDING"
+vfio_platform_start_irqfd_injection(int index, int fd, int resamplefd) "IRQ index=%d, fd = %d, resamplefd = %d"
 
 #hw/acpi/memory_hotplug.c
 mhp_acpi_invalid_slot_selected(uint32_t slot) "0x%"PRIx32
diff --git a/translate-all.c b/translate-all.c
index 412bc9005f..50d53fdac0 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -118,6 +118,7 @@ typedef struct PageDesc {
 #define V_L1_SHIFT (L1_MAP_ADDR_SPACE_BITS - TARGET_PAGE_BITS - V_L1_BITS)
 
 uintptr_t qemu_real_host_page_size;
+uintptr_t qemu_real_host_page_mask;
 uintptr_t qemu_host_page_size;
 uintptr_t qemu_host_page_mask;
 
@@ -307,6 +308,7 @@ void page_size_init(void)
     /* NOTE: we can always suppose that qemu_host_page_size >=
        TARGET_PAGE_SIZE */
     qemu_real_host_page_size = getpagesize();
+    qemu_real_host_page_mask = ~(qemu_real_host_page_size - 1);
     if (qemu_host_page_size == 0) {
         qemu_host_page_size = qemu_real_host_page_size;
     }