multi-process: create IOHUB object to handle irq

IOHUB object is added to manage PCI IRQs. It uses KVM_IRQFD
ioctl to create irqfd to injecting PCI interrupts to the guest.
IOHUB object forwards the irqfd to the remote process. Remote process
uses this fd to directly send interrupts to the guest, bypassing QEMU.

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 51d5c3d54e28a68b002e3875c59599c9f5a424a1.1611938319.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

MAINTAINERS

@@ -3221,6 +3221,8 @@ F: hw/remote/proxy.c
 F: include/hw/remote/proxy.h
 F: hw/remote/proxy-memory-listener.c
 F: include/hw/remote/proxy-memory-listener.h
+F: hw/remote/iohub.c
+F: include/hw/remote/iohub.h
 
 Build and test automation
 -------------------------

hw/remote/iohub.c

@@ -0,0 +1,119 @@
+/*
+ * Remote IO Hub
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_ids.h"
+#include "hw/pci/pci_bus.h"
+#include "qemu/thread.h"
+#include "hw/boards.h"
+#include "hw/remote/machine.h"
+#include "hw/remote/iohub.h"
+#include "qemu/main-loop.h"
+
+void remote_iohub_init(RemoteIOHubState *iohub)
+{
+    int pirq;
+
+    memset(&iohub->irqfds, 0, sizeof(iohub->irqfds));
+    memset(&iohub->resamplefds, 0, sizeof(iohub->resamplefds));
+
+    for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) {
+        qemu_mutex_init(&iohub->irq_level_lock[pirq]);
+        iohub->irq_level[pirq] = 0;
+        event_notifier_init_fd(&iohub->irqfds[pirq], -1);
+        event_notifier_init_fd(&iohub->resamplefds[pirq], -1);
+    }
+}
+
+void remote_iohub_finalize(RemoteIOHubState *iohub)
+{
+    int pirq;
+
+    for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) {
+        qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]),
+                            NULL, NULL, NULL);
+        event_notifier_cleanup(&iohub->irqfds[pirq]);
+        event_notifier_cleanup(&iohub->resamplefds[pirq]);
+        qemu_mutex_destroy(&iohub->irq_level_lock[pirq]);
+    }
+}
+
+int remote_iohub_map_irq(PCIDevice *pci_dev, int intx)
+{
+    return pci_dev->devfn;
+}
+
+void remote_iohub_set_irq(void *opaque, int pirq, int level)
+{
+    RemoteIOHubState *iohub = opaque;
+
+    assert(pirq >= 0);
+    assert(pirq < PCI_DEVFN_MAX);
+
+    QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]);
+
+    if (level) {
+        if (++iohub->irq_level[pirq] == 1) {
+            event_notifier_set(&iohub->irqfds[pirq]);
+        }
+    } else if (iohub->irq_level[pirq] > 0) {
+        iohub->irq_level[pirq]--;
+    }
+}
+
+static void intr_resample_handler(void *opaque)
+{
+    ResampleToken *token = opaque;
+    RemoteIOHubState *iohub = token->iohub;
+    int pirq, s;
+
+    pirq = token->pirq;
+
+    s = event_notifier_test_and_clear(&iohub->resamplefds[pirq]);
+
+    assert(s >= 0);
+
+    QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]);
+
+    if (iohub->irq_level[pirq]) {
+        event_notifier_set(&iohub->irqfds[pirq]);
+    }
+}
+
+void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg)
+{
+    RemoteMachineState *machine = REMOTE_MACHINE(current_machine);
+    RemoteIOHubState *iohub = &machine->iohub;
+    int pirq, intx;
+
+    intx = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1;
+
+    pirq = remote_iohub_map_irq(pci_dev, intx);
+
+    if (event_notifier_get_fd(&iohub->irqfds[pirq]) != -1) {
+        qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]),
+                            NULL, NULL, NULL);
+        event_notifier_cleanup(&iohub->irqfds[pirq]);
+        event_notifier_cleanup(&iohub->resamplefds[pirq]);
+        memset(&iohub->token[pirq], 0, sizeof(ResampleToken));
+    }
+
+    event_notifier_init_fd(&iohub->irqfds[pirq], msg->fds[0]);
+    event_notifier_init_fd(&iohub->resamplefds[pirq], msg->fds[1]);
+
+    iohub->token[pirq].iohub = iohub;
+    iohub->token[pirq].pirq = pirq;
+
+    qemu_set_fd_handler(msg->fds[1], intr_resample_handler, NULL,
+                        &iohub->token[pirq]);
+}

hw/remote/machine.c

@@ -20,12 +20,15 @@
 #include "exec/address-spaces.h"
 #include "exec/memory.h"
 #include "qapi/error.h"
+#include "hw/pci/pci_host.h"
+#include "hw/remote/iohub.h"
 
 static void remote_machine_init(MachineState *machine)
 {
     MemoryRegion *system_memory, *system_io, *pci_memory;
     RemoteMachineState *s = REMOTE_MACHINE(machine);
     RemotePCIHost *rem_host;
+    PCIHostState *pci_host;
 
     system_memory = get_system_memory();
     system_io = get_system_io();
@@ -45,6 +48,13 @@ static void remote_machine_init(MachineState *machine)
     memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1);
 
     qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal);
+
+    pci_host = PCI_HOST_BRIDGE(rem_host);
+
+    remote_iohub_init(&s->iohub);
+
+    pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq,
+                 &s->iohub, REMOTE_IOHUB_NB_PIRQS);
 }
 
 static void remote_machine_class_init(ObjectClass *oc, void *data)

hw/remote/meson.build

@@ -5,6 +5,7 @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c'))
 remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c'))
+remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c'))
 
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c'))
 specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c'))

hw/remote/message.c

@@ -18,6 +18,7 @@
 #include "hw/pci/pci.h"
 #include "exec/memattrs.h"
 #include "hw/remote/memory.h"
+#include "hw/remote/iohub.h"
 
 static void process_config_write(QIOChannel *ioc, PCIDevice *dev,
                                  MPQemuMsg *msg, Error **errp);
@@ -65,6 +66,9 @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data)
         case MPQEMU_CMD_SYNC_SYSMEM:
             remote_sysmem_reconfig(&msg, &local_err);
             break;
+        case MPQEMU_CMD_SET_IRQFD:
+            process_set_irqfd_msg(pci_dev, &msg);
+            break;
         default:
             error_setg(&local_err,
                        "Unknown command (%d) received for device %s"

hw/remote/mpqemu-link.c

@@ -254,6 +254,11 @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
             return false;
         }
         break;
+    case MPQEMU_CMD_SET_IRQFD:
+        if (msg->size || (msg->num_fds != 2)) {
+            return false;
+        }
+        break;
     default:
         break;
     }

hw/remote/proxy.c

@@ -21,6 +21,57 @@
 #include "qemu/error-report.h"
 #include "hw/remote/proxy-memory-listener.h"
 #include "qom/object.h"
+#include "qemu/event_notifier.h"
+#include "sysemu/kvm.h"
+#include "util/event_notifier-posix.c"
+
+static void proxy_intx_update(PCIDevice *pci_dev)
+{
+    PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev);
+    PCIINTxRoute route;
+    int pin = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1;
+
+    if (dev->virq != -1) {
+        kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &dev->intr, dev->virq);
+        dev->virq = -1;
+    }
+
+    route = pci_device_route_intx_to_irq(pci_dev, pin);
+
+    dev->virq = route.irq;
+
+    if (dev->virq != -1) {
+        kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &dev->intr,
+                                           &dev->resample, dev->virq);
+    }
+}
+
+static void setup_irqfd(PCIProxyDev *dev)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+    MPQemuMsg msg;
+    Error *local_err = NULL;
+
+    event_notifier_init(&dev->intr, 0);
+    event_notifier_init(&dev->resample, 0);
+
+    memset(&msg, 0, sizeof(MPQemuMsg));
+    msg.cmd = MPQEMU_CMD_SET_IRQFD;
+    msg.num_fds = 2;
+    msg.fds[0] = event_notifier_get_fd(&dev->intr);
+    msg.fds[1] = event_notifier_get_fd(&dev->resample);
+    msg.size = 0;
+
+    if (!mpqemu_msg_send(&msg, dev->ioc, &local_err)) {
+        error_report_err(local_err);
+    }
+
+    dev->virq = -1;
+
+    proxy_intx_update(pci_dev);
+
+    pci_device_set_intx_routing_notifier(pci_dev, proxy_intx_update);
+}
 
 static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
 {
@@ -56,6 +107,8 @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
     qio_channel_set_blocking(dev->ioc, true, NULL);
 
     proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc);
+
+    setup_irqfd(dev);
 }
 
 static void pci_proxy_dev_exit(PCIDevice *pdev)
@@ -71,6 +124,9 @@ static void pci_proxy_dev_exit(PCIDevice *pdev)
     error_free(dev->migration_blocker);
 
     proxy_memory_listener_deconfigure(&dev->proxy_listener);
+
+    event_notifier_cleanup(&dev->intr);
+    event_notifier_cleanup(&dev->resample);
 }
 
 static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,

include/hw/pci/pci_ids.h

@@ -192,6 +192,9 @@
 #define PCI_DEVICE_ID_SUN_SIMBA          0x5000
 #define PCI_DEVICE_ID_SUN_SABRE          0xa000
 
+#define PCI_VENDOR_ID_ORACLE             0x108e
+#define PCI_DEVICE_ID_REMOTE_IOHUB       0xb000
+
 #define PCI_VENDOR_ID_CMD                0x1095
 #define PCI_DEVICE_ID_CMD_646            0x0646
 

include/hw/remote/iohub.h

@@ -0,0 +1,42 @@
+/*
+ * IO Hub for remote device
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef REMOTE_IOHUB_H
+#define REMOTE_IOHUB_H
+
+#include "hw/pci/pci.h"
+#include "qemu/event_notifier.h"
+#include "qemu/thread-posix.h"
+#include "hw/remote/mpqemu-link.h"
+
+#define REMOTE_IOHUB_NB_PIRQS    PCI_DEVFN_MAX
+
+typedef struct ResampleToken {
+    void *iohub;
+    int pirq;
+} ResampleToken;
+
+typedef struct RemoteIOHubState {
+    PCIDevice d;
+    EventNotifier irqfds[REMOTE_IOHUB_NB_PIRQS];
+    EventNotifier resamplefds[REMOTE_IOHUB_NB_PIRQS];
+    unsigned int irq_level[REMOTE_IOHUB_NB_PIRQS];
+    ResampleToken token[REMOTE_IOHUB_NB_PIRQS];
+    QemuMutex irq_level_lock[REMOTE_IOHUB_NB_PIRQS];
+} RemoteIOHubState;
+
+int remote_iohub_map_irq(PCIDevice *pci_dev, int intx);
+void remote_iohub_set_irq(void *opaque, int pirq, int level);
+void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg);
+
+void remote_iohub_init(RemoteIOHubState *iohub);
+void remote_iohub_finalize(RemoteIOHubState *iohub);
+
+#endif

include/hw/remote/machine.h

@@ -15,11 +15,13 @@
 #include "hw/boards.h"
 #include "hw/pci-host/remote.h"
 #include "io/channel.h"
+#include "hw/remote/iohub.h"
 
 struct RemoteMachineState {
     MachineState parent_obj;
 
     RemotePCIHost *host;
+    RemoteIOHubState iohub;
 };
 
 /* Used to pass to co-routine device and ioc. */

include/hw/remote/mpqemu-link.h

@@ -39,6 +39,7 @@ typedef enum {
     MPQEMU_CMD_PCI_CFGREAD,
     MPQEMU_CMD_BAR_WRITE,
     MPQEMU_CMD_BAR_READ,
+    MPQEMU_CMD_SET_IRQFD,
     MPQEMU_CMD_MAX,
 } MPQemuCmd;
 

include/hw/remote/proxy.h

@@ -12,6 +12,7 @@
 #include "hw/pci/pci.h"
 #include "io/channel.h"
 #include "hw/remote/proxy-memory-listener.h"
+#include "qemu/event_notifier.h"
 
 #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev"
 OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV)
@@ -38,6 +39,9 @@ struct PCIProxyDev {
     QIOChannel *ioc;
     Error *migration_blocker;
     ProxyMemoryListener proxy_listener;
+    int virq;
+    EventNotifier intr;
+    EventNotifier resample;
     ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };