diff mbox series

[v7,15/17] vfio-user: handle device interrupts

Message ID 377ddc113f35efdfcdb41066cca5f5d4a6f32ec7.1648234157.git.jag.raman@oracle.com (mailing list archive)
State New, archived
Headers show
Series vfio-user server in QEMU | expand

Commit Message

Jag Raman March 25, 2022, 7:19 p.m. UTC
Forward remote device's interrupts to the guest

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
---
 include/hw/pci/pci.h              |  10 +++
 include/hw/remote/vfio-user-obj.h |   6 ++
 hw/pci/msi.c                      |  11 +++-
 hw/pci/msix.c                     |  10 ++-
 hw/remote/machine.c               |  14 +++--
 hw/remote/vfio-user-obj.c         | 101 ++++++++++++++++++++++++++++++
 stubs/vfio-user-obj.c             |   6 ++
 MAINTAINERS                       |   1 +
 hw/remote/trace-events            |   1 +
 stubs/meson.build                 |   1 +
 10 files changed, 155 insertions(+), 6 deletions(-)
 create mode 100644 include/hw/remote/vfio-user-obj.h
 create mode 100644 stubs/vfio-user-obj.c
diff mbox series

Patch

diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index 3a32b8dd40..fb8a05ae25 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -16,6 +16,7 @@  extern bool pci_available;
 #define PCI_SLOT(devfn)         (((devfn) >> 3) & 0x1f)
 #define PCI_FUNC(devfn)         ((devfn) & 0x07)
 #define PCI_BUILD_BDF(bus, devfn)     ((bus << 8) | (devfn))
+#define PCI_BDF_TO_DEVFN(x)     ((x) & 0xff)
 #define PCI_BUS_MAX             256
 #define PCI_DEVFN_MAX           256
 #define PCI_SLOT_MAX            32
@@ -126,6 +127,8 @@  typedef uint32_t PCIConfigReadFunc(PCIDevice *pci_dev,
 typedef void PCIMapIORegionFunc(PCIDevice *pci_dev, int region_num,
                                 pcibus_t addr, pcibus_t size, int type);
 typedef void PCIUnregisterFunc(PCIDevice *pci_dev);
+typedef void PCIMSINotify(PCIDevice *pci_dev, unsigned vector);
+typedef void PCIMSIxNotify(PCIDevice *pci_dev, unsigned vector);
 
 typedef struct PCIIORegion {
     pcibus_t addr; /* current PCI mapping address. -1 means not mapped */
@@ -321,6 +324,13 @@  struct PCIDevice {
     /* Space to store MSIX table & pending bit array */
     uint8_t *msix_table;
     uint8_t *msix_pba;
+
+    /* May be used by INTx or MSI during interrupt notification */
+    void *irq_opaque;
+
+    PCIMSINotify *msi_notify;
+    PCIMSIxNotify *msix_notify;
+
     /* MemoryRegion container for msix exclusive BAR setup */
     MemoryRegion msix_exclusive_bar;
     /* Memory Regions for MSIX table and pending bit entries. */
diff --git a/include/hw/remote/vfio-user-obj.h b/include/hw/remote/vfio-user-obj.h
new file mode 100644
index 0000000000..87ab78b875
--- /dev/null
+++ b/include/hw/remote/vfio-user-obj.h
@@ -0,0 +1,6 @@ 
+#ifndef VFIO_USER_OBJ_H
+#define VFIO_USER_OBJ_H
+
+void vfu_object_set_bus_irq(PCIBus *pci_bus);
+
+#endif
diff --git a/hw/pci/msi.c b/hw/pci/msi.c
index 47d2b0f33c..a161a5380b 100644
--- a/hw/pci/msi.c
+++ b/hw/pci/msi.c
@@ -51,6 +51,8 @@ 
  */
 bool msi_nonbroken;
 
+static void pci_msi_notify(PCIDevice *dev, unsigned int vector);
+
 /* If we get rid of cap allocator, we won't need this. */
 static inline uint8_t msi_cap_sizeof(uint16_t flags)
 {
@@ -225,6 +227,8 @@  int msi_init(struct PCIDevice *dev, uint8_t offset,
     dev->msi_cap = config_offset;
     dev->cap_present |= QEMU_PCI_CAP_MSI;
 
+    dev->msi_notify = pci_msi_notify;
+
     pci_set_word(dev->config + msi_flags_off(dev), flags);
     pci_set_word(dev->wmask + msi_flags_off(dev),
                  PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
@@ -307,7 +311,7 @@  bool msi_is_masked(const PCIDevice *dev, unsigned int vector)
     return mask & (1U << vector);
 }
 
-void msi_notify(PCIDevice *dev, unsigned int vector)
+static void pci_msi_notify(PCIDevice *dev, unsigned int vector)
 {
     uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
     bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
@@ -332,6 +336,11 @@  void msi_notify(PCIDevice *dev, unsigned int vector)
     msi_send_message(dev, msg);
 }
 
+void msi_notify(PCIDevice *dev, unsigned int vector)
+{
+    dev->msi_notify(dev, vector);
+}
+
 void msi_send_message(PCIDevice *dev, MSIMessage msg)
 {
     MemTxAttrs attrs = {};
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
index ae9331cd0b..fbf88654b3 100644
--- a/hw/pci/msix.c
+++ b/hw/pci/msix.c
@@ -31,6 +31,8 @@ 
 #define MSIX_ENABLE_MASK (PCI_MSIX_FLAGS_ENABLE >> 8)
 #define MSIX_MASKALL_MASK (PCI_MSIX_FLAGS_MASKALL >> 8)
 
+static void pci_msix_notify(PCIDevice *dev, unsigned vector);
+
 MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)
 {
     uint8_t *table_entry = dev->msix_table + vector * PCI_MSIX_ENTRY_SIZE;
@@ -334,6 +336,7 @@  int msix_init(struct PCIDevice *dev, unsigned short nentries,
     dev->msix_table = g_malloc0(table_size);
     dev->msix_pba = g_malloc0(pba_size);
     dev->msix_entry_used = g_malloc0(nentries * sizeof *dev->msix_entry_used);
+    dev->msix_notify = pci_msix_notify;
 
     msix_mask_all(dev, nentries);
 
@@ -485,7 +488,7 @@  int msix_enabled(PCIDevice *dev)
 }
 
 /* Send an MSI-X message */
-void msix_notify(PCIDevice *dev, unsigned vector)
+static void pci_msix_notify(PCIDevice *dev, unsigned vector)
 {
     MSIMessage msg;
 
@@ -503,6 +506,11 @@  void msix_notify(PCIDevice *dev, unsigned vector)
     msi_send_message(dev, msg);
 }
 
+void msix_notify(PCIDevice *dev, unsigned vector)
+{
+    dev->msix_notify(dev, vector);
+}
+
 void msix_reset(PCIDevice *dev)
 {
     if (!msix_present(dev)) {
diff --git a/hw/remote/machine.c b/hw/remote/machine.c
index 67801c3a4d..95f97ab268 100644
--- a/hw/remote/machine.c
+++ b/hw/remote/machine.c
@@ -23,6 +23,8 @@ 
 #include "hw/remote/iohub.h"
 #include "hw/qdev-core.h"
 #include "hw/remote/iommu.h"
+#include "hw/remote/vfio-user-obj.h"
+#include "hw/pci/msi.h"
 
 static void remote_machine_init(MachineState *machine)
 {
@@ -53,13 +55,17 @@  static void remote_machine_init(MachineState *machine)
     pci_host = PCI_HOST_BRIDGE(rem_host);
 
     if (s->vfio_user) {
+        msi_nonbroken = true;
+
         remote_configure_iommu(pci_host->bus);
-    }
 
-    remote_iohub_init(&s->iohub);
+        vfu_object_set_bus_irq(pci_host->bus);
+    } else {
+        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);
+        pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq,
+                     &s->iohub, REMOTE_IOHUB_NB_PIRQS);
+    }
 
     qbus_set_hotplug_handler(BUS(pci_host->bus), OBJECT(s));
 }
diff --git a/hw/remote/vfio-user-obj.c b/hw/remote/vfio-user-obj.c
index 6910c16243..19d075a9dd 100644
--- a/hw/remote/vfio-user-obj.c
+++ b/hw/remote/vfio-user-obj.c
@@ -54,6 +54,9 @@ 
 #include "hw/pci/pci.h"
 #include "qemu/timer.h"
 #include "exec/memory.h"
+#include "hw/pci/msi.h"
+#include "hw/pci/msix.h"
+#include "hw/remote/vfio-user-obj.h"
 
 #define TYPE_VFU_OBJECT "x-vfio-user-server"
 OBJECT_DECLARE_TYPE(VfuObject, VfuObjectClass, VFU_OBJECT)
@@ -489,6 +492,95 @@  static void vfu_object_register_bars(vfu_ctx_t *vfu_ctx, PCIDevice *pdev)
     }
 }
 
+static int vfu_object_map_irq(PCIDevice *pci_dev, int intx)
+{
+    int pci_bdf = PCI_BUILD_BDF(pci_bus_num(pci_get_bus(pci_dev)),
+                                pci_dev->devfn);
+
+    return pci_bdf;
+}
+
+static void vfu_object_set_irq(void *opaque, int pirq, int level)
+{
+    PCIBus *pci_bus = opaque;
+    PCIDevice *pci_dev = NULL;
+    vfu_ctx_t *vfu_ctx = NULL;
+    int pci_bus_num, devfn;
+
+    if (level) {
+        pci_bus_num = PCI_BUS_NUM(pirq);
+        devfn = PCI_BDF_TO_DEVFN(pirq);
+
+        /*
+         * pci_find_device() performs at O(1) if the device is attached
+         * to the root PCI bus. Whereas, if the device is attached to a
+         * secondary PCI bus (such as when a root port is involved),
+         * finding the parent PCI bus could take O(n)
+         */
+        pci_dev = pci_find_device(pci_bus, pci_bus_num, devfn);
+
+        vfu_ctx = pci_dev->irq_opaque;
+
+        g_assert(vfu_ctx);
+
+        vfu_irq_trigger(vfu_ctx, 0);
+    }
+}
+
+static void vfu_object_msi_notify(PCIDevice *pci_dev, unsigned vector)
+{
+    vfu_ctx_t *vfu_ctx = pci_dev->irq_opaque;
+    unsigned nr_vectors = 0;
+
+    g_assert(vfu_ctx);
+
+    nr_vectors = msix_nr_vectors_allocated(pci_dev);
+    if (!nr_vectors) {
+        nr_vectors = msi_nr_vectors_allocated(pci_dev);
+    }
+
+    g_assert(vector < nr_vectors);
+
+    vfu_irq_trigger(vfu_ctx, vector);
+}
+
+static int vfu_object_setup_irqs(VfuObject *o, PCIDevice *pci_dev)
+{
+    vfu_ctx_t *vfu_ctx = o->vfu_ctx;
+    int ret;
+
+    ret = vfu_setup_device_nr_irqs(vfu_ctx, VFU_DEV_INTX_IRQ, 1);
+    if (ret < 0) {
+        return ret;
+    }
+
+    ret = 0;
+    if (msix_nr_vectors_allocated(pci_dev)) {
+        ret = vfu_setup_device_nr_irqs(vfu_ctx, VFU_DEV_MSIX_IRQ,
+                                       msix_nr_vectors_allocated(pci_dev));
+
+        pci_dev->msix_notify = vfu_object_msi_notify;
+    } else if (msi_nr_vectors_allocated(pci_dev)) {
+        ret = vfu_setup_device_nr_irqs(vfu_ctx, VFU_DEV_MSI_IRQ,
+                                       msi_nr_vectors_allocated(pci_dev));
+
+        pci_dev->msi_notify = vfu_object_msi_notify;
+    }
+
+    if (ret < 0) {
+        return ret;
+    }
+
+    pci_dev->irq_opaque = vfu_ctx;
+
+    return 0;
+}
+
+void vfu_object_set_bus_irq(PCIBus *pci_bus)
+{
+    pci_bus_irqs(pci_bus, vfu_object_set_irq, vfu_object_map_irq, pci_bus, 1);
+}
+
 /*
  * TYPE_VFU_OBJECT depends on the availability of the 'socket' and 'device'
  * properties. It also depends on devices instantiated in QEMU. These
@@ -587,6 +679,13 @@  static void vfu_object_init_ctx(VfuObject *o, Error **errp)
 
     vfu_object_register_bars(o->vfu_ctx, o->pci_dev);
 
+    ret = vfu_object_setup_irqs(o, o->pci_dev);
+    if (ret < 0) {
+        error_setg(errp, "vfu: Failed to setup interrupts for %s",
+                   o->device);
+        goto fail;
+    }
+
     ret = vfu_realize_ctx(o->vfu_ctx);
     if (ret < 0) {
         error_setg(errp, "vfu: Failed to realize device %s- %s",
@@ -612,6 +711,7 @@  fail:
         o->unplug_blocker = NULL;
     }
     if (o->pci_dev) {
+        o->pci_dev->irq_opaque = NULL;
         object_unref(OBJECT(o->pci_dev));
         o->pci_dev = NULL;
     }
@@ -671,6 +771,7 @@  static void vfu_object_finalize(Object *obj)
     }
 
     if (o->pci_dev) {
+        o->pci_dev->irq_opaque = NULL;
         object_unref(OBJECT(o->pci_dev));
         o->pci_dev = NULL;
     }
diff --git a/stubs/vfio-user-obj.c b/stubs/vfio-user-obj.c
new file mode 100644
index 0000000000..79100d768e
--- /dev/null
+++ b/stubs/vfio-user-obj.c
@@ -0,0 +1,6 @@ 
+#include "qemu/osdep.h"
+#include "hw/remote/vfio-user-obj.h"
+
+void vfu_object_set_bus_irq(PCIBus *pci_bus)
+{
+}
diff --git a/MAINTAINERS b/MAINTAINERS
index 21694a9698..d07f2a0985 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3599,6 +3599,7 @@  F: hw/remote/iohub.c
 F: include/hw/remote/iohub.h
 F: subprojects/libvfio-user
 F: hw/remote/vfio-user-obj.c
+F: include/hw/remote/vfio-user-obj.h
 F: hw/remote/iommu.c
 F: include/hw/remote/iommu.h
 
diff --git a/hw/remote/trace-events b/hw/remote/trace-events
index 847d50d88f..c167b3c7a5 100644
--- a/hw/remote/trace-events
+++ b/hw/remote/trace-events
@@ -12,3 +12,4 @@  vfu_dma_unregister(uint64_t gpa) "vfu: unregistering GPA 0x%"PRIx64""
 vfu_bar_register(int i, uint64_t addr, uint64_t size) "vfu: BAR %d: addr 0x%"PRIx64" size 0x%"PRIx64""
 vfu_bar_rw_enter(const char *op, uint64_t addr) "vfu: %s request for BAR address 0x%"PRIx64""
 vfu_bar_rw_exit(const char *op, uint64_t addr) "vfu: Finished %s of BAR address 0x%"PRIx64""
+vfu_interrupt(int pirq) "vfu: sending interrupt to device - PIRQ %d"
diff --git a/stubs/meson.build b/stubs/meson.build
index 6f80fec761..d8f3fd5c44 100644
--- a/stubs/meson.build
+++ b/stubs/meson.build
@@ -60,3 +60,4 @@  if have_system
 else
   stub_ss.add(files('qdev.c'))
 endif
+stub_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_false: files('vfio-user-obj.c'))