vfio-user: handle device interrupts

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>
Message-id: 9523479eaafe050677f4de2af5dd0df18c27cfd9.1655151679.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

3 files changed, 90 insertions, 7 deletions

diff --git a/hw/pci/msi.c b/hw/pci/msi.c
index 47d2b0f33c..5c471b9616 100644
--- a/hw/pci/msi.c
+++ b/hw/pci/msi.c
@@ -134,7 +134,7 @@ void msi_set_message(PCIDevice *dev, MSIMessage msg)
     pci_set_word(dev->config + msi_data_off(dev, msi64bit), msg.data);
 }
 
-MSIMessage msi_get_message(PCIDevice *dev, unsigned int vector)
+static MSIMessage msi_prepare_message(PCIDevice *dev, unsigned int vector)
 {
     uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
     bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
@@ -159,6 +159,11 @@ MSIMessage msi_get_message(PCIDevice *dev, unsigned int vector)
     return msg;
 }
 
+MSIMessage msi_get_message(PCIDevice *dev, unsigned int vector)
+{
+    return dev->msi_prepare_message(dev, vector);
+}
+
 bool msi_enabled(const PCIDevice *dev)
 {
     return msi_present(dev) &&
@@ -241,6 +246,8 @@ int msi_init(struct PCIDevice *dev, uint8_t offset,
                      0xffffffff >> (PCI_MSI_VECTORS_MAX - nr_vectors));
     }
 
+    dev->msi_prepare_message = msi_prepare_message;
+
     return 0;
 }
 
@@ -256,6 +263,7 @@ void msi_uninit(struct PCIDevice *dev)
     cap_size = msi_cap_sizeof(flags);
     pci_del_capability(dev, PCI_CAP_ID_MSI, cap_size);
     dev->cap_present &= ~QEMU_PCI_CAP_MSI;
+    dev->msi_prepare_message = NULL;
 
     MSI_DEV_PRINTF(dev, "uninit\n");
 }
@@ -307,6 +315,39 @@ bool msi_is_masked(const PCIDevice *dev, unsigned int vector)
     return mask & (1U << vector);
 }
 
+void msi_set_mask(PCIDevice *dev, int vector, bool mask, Error **errp)
+{
+    ERRP_GUARD();
+    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
+    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
+    uint32_t irq_state, vector_mask, pending;
+
+    if (vector > PCI_MSI_VECTORS_MAX) {
+        error_setg(errp, "msi: vector %d not allocated. max vector is %d",
+                   vector, PCI_MSI_VECTORS_MAX);
+        return;
+    }
+
+    vector_mask = (1U << vector);
+
+    irq_state = pci_get_long(dev->config + msi_mask_off(dev, msi64bit));
+
+    if (mask) {
+        irq_state |= vector_mask;
+    } else {
+        irq_state &= ~vector_mask;
+    }
+
+    pci_set_long(dev->config + msi_mask_off(dev, msi64bit), irq_state);
+
+    pending = pci_get_long(dev->config + msi_pending_off(dev, msi64bit));
+    if (!mask && (pending & vector_mask)) {
+        pending &= ~vector_mask;
+        pci_set_long(dev->config + msi_pending_off(dev, msi64bit), pending);
+        msi_notify(dev, vector);
+    }
+}
+
 void msi_notify(PCIDevice *dev, unsigned int vector)
 {
     uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
@@ -334,11 +375,7 @@ void msi_notify(PCIDevice *dev, unsigned int vector)
 
 void msi_send_message(PCIDevice *dev, MSIMessage msg)
 {
-    MemTxAttrs attrs = {};
-
-    attrs.requester_id = pci_requester_id(dev);
-    address_space_stl_le(&dev->bus_master_as, msg.address, msg.data,
-                         attrs, NULL);
+    dev->msi_trigger(dev, msg);
 }
 
 /* Normally called by pci_default_write_config(). */
diff --git a/hw/pci/msix.c b/hw/pci/msix.c
index ae9331cd0b..1e381a9813 100644
--- a/hw/pci/msix.c
+++ b/hw/pci/msix.c
@@ -31,7 +31,7 @@
 #define MSIX_ENABLE_MASK (PCI_MSIX_FLAGS_ENABLE >> 8)
 #define MSIX_MASKALL_MASK (PCI_MSIX_FLAGS_MASKALL >> 8)
 
-MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)
+static MSIMessage msix_prepare_message(PCIDevice *dev, unsigned vector)
 {
     uint8_t *table_entry = dev->msix_table + vector * PCI_MSIX_ENTRY_SIZE;
     MSIMessage msg;
@@ -41,6 +41,11 @@ MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)
     return msg;
 }
 
+MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)
+{
+    return dev->msix_prepare_message(dev, vector);
+}
+
 /*
  * Special API for POWER to configure the vectors through
  * a side channel. Should never be used by devices.
@@ -131,6 +136,31 @@ static void msix_handle_mask_update(PCIDevice *dev, int vector, bool was_masked)
     }
 }
 
+void msix_set_mask(PCIDevice *dev, int vector, bool mask, Error **errp)
+{
+    ERRP_GUARD();
+    unsigned offset;
+    bool was_masked;
+
+    if (vector > dev->msix_entries_nr) {
+        error_setg(errp, "msix: vector %d not allocated. max vector is %d",
+                   vector, dev->msix_entries_nr);
+        return;
+    }
+
+    offset = vector * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+    was_masked = msix_is_masked(dev, vector);
+
+    if (mask) {
+        dev->msix_table[offset] |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+    } else {
+        dev->msix_table[offset] &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
+    }
+
+    msix_handle_mask_update(dev, vector, was_masked);
+}
+
 static bool msix_masked(PCIDevice *dev)
 {
     return dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] & MSIX_MASKALL_MASK;
@@ -344,6 +374,8 @@ int msix_init(struct PCIDevice *dev, unsigned short nentries,
                           "msix-pba", pba_size);
     memory_region_add_subregion(pba_bar, pba_offset, &dev->msix_pba_mmio);
 
+    dev->msix_prepare_message = msix_prepare_message;
+
     return 0;
 }
 
@@ -429,6 +461,7 @@ void msix_uninit(PCIDevice *dev, MemoryRegion *table_bar, MemoryRegion *pba_bar)
     g_free(dev->msix_entry_used);
     dev->msix_entry_used = NULL;
     dev->cap_present &= ~QEMU_PCI_CAP_MSIX;
+    dev->msix_prepare_message = NULL;
 }
 
 void msix_uninit_exclusive_bar(PCIDevice *dev)
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 6e7015329c..2f450f6a72 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -317,6 +317,15 @@ void pci_device_deassert_intx(PCIDevice *dev)
     }
 }
 
+static void pci_msi_trigger(PCIDevice *dev, MSIMessage msg)
+{
+    MemTxAttrs attrs = {};
+
+    attrs.requester_id = pci_requester_id(dev);
+    address_space_stl_le(&dev->bus_master_as, msg.address, msg.data,
+                         attrs, NULL);
+}
+
 static void pci_reset_regions(PCIDevice *dev)
 {
     int r;
@@ -1212,6 +1221,8 @@ static void pci_qdev_unrealize(DeviceState *dev)
 
     pci_device_deassert_intx(pci_dev);
     do_pci_unregister_device(pci_dev);
+
+    pci_dev->msi_trigger = NULL;
 }
 
 void pci_register_bar(PCIDevice *pci_dev, int region_num,
@@ -2251,6 +2262,8 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
     }
 
     pci_set_power(pci_dev, true);
+
+    pci_dev->msi_trigger = pci_msi_trigger;
 }
 
 PCIDevice *pci_new_multifunction(int devfn, bool multifunction,