[PATCH 07/10] kvm: expose MSI capability to guest

[Sheng Yang <sheng@linux.intel.com>]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 qemu/hw/device-assignment.c |  112 ++++++++++++++++++++++++++++++++++++++++---
 qemu/hw/device-assignment.h |    7 +++
 2 files changed, 112 insertions(+), 7 deletions(-)

diff --git a/qemu/hw/device-assignment.c b/qemu/hw/device-assignment.c
index fc05ac7..089c5b7 100644
--- a/qemu/hw/device-assignment.c
+++ b/qemu/hw/device-assignment.c
@@ -265,7 +265,8 @@ static void assigned_dev_pci_write_config(PCIDevice *d, uint32_t address,
     }
 
     if ((address >= 0x10 && address <= 0x24) || address == 0x34 ||
-        address == 0x3c || address == 0x3d) {
+        address == 0x3c || address == 0x3d ||
+        pci_access_cap_config(d, address, len)) {
         /* used for update-mappings (BAR emulation) */
         pci_default_write_config(d, address, val, len);
         return;
@@ -299,7 +300,8 @@ static uint32_t assigned_dev_pci_read_config(PCIDevice *d, uint32_t address,
     AssignedDevice *pci_dev = container_of(d, AssignedDevice, dev);
 
     if ((address >= 0x10 && address <= 0x24) || address == 0x34 ||
-        address == 0x3c || address == 0x3d) {
+        address == 0x3c || address == 0x3d ||
+        pci_access_cap_config(d, address, len)) {
         val = pci_default_read_config(d, address, len);
         DEBUG("(%x.%x): address=%04x val=0x%08x len=%d\n",
               (d->devfn >> 3) & 0x1F, (d->devfn & 0x7), address, val, len);
@@ -328,11 +330,13 @@ do_log:
     DEBUG("(%x.%x): address=%04x val=0x%08x len=%d\n",
           (d->devfn >> 3) & 0x1F, (d->devfn & 0x7), address, val, len);
 
-    /* kill the special capabilities */
-    if (address == 4 && len == 4)
-        val &= ~0x100000;
-    else if (address == 6)
-        val &= ~0x10;
+    if (!pci_dev->cap.available) {
+        /* kill the special capabilities */
+        if (address == 4 && len == 4)
+            val &= ~0x100000;
+        else if (address == 6)
+            val &= ~0x10;
+    }
 
     return val;
 }
@@ -637,6 +641,96 @@ void assigned_dev_update_irqs()
     }
 }
 
+#if defined(KVM_CAP_DEVICE_MSI) && defined (KVM_CAP_IRQ_ROUTING)
+static void assigned_dev_update_msi(PCIDevice *pci_dev, unsigned int ctrl_pos)
+{
+    struct kvm_assigned_irq assigned_irq_data;
+    struct kvm_irq_routing_entry gsi_entry;
+    AssignedDevice *assigned_dev = container_of(pci_dev, AssignedDevice, dev);
+    uint8_t ctrl_byte = pci_dev->cap.config[ctrl_pos];
+
+    memset(&assigned_irq_data, 0, sizeof assigned_irq_data);
+    assigned_irq_data.assigned_dev_id  =
+        calc_assigned_dev_id(assigned_dev->h_busnr,
+                (uint8_t)assigned_dev->h_devfn);
+
+    if (ctrl_byte & PCI_MSI_FLAGS_ENABLE) {
+        gsi_entry.u.msi.address_lo = *(uint32_t *)(pci_dev->cap.config +
+                PCI_MSI_ADDRESS_LO);
+        gsi_entry.u.msi.address_hi = 0;
+        gsi_entry.u.msi.data = *(uint16_t *)(pci_dev->cap.config +
+                PCI_MSI_DATA_32);
+        gsi_entry.type = KVM_IRQ_ROUTING_MSI;
+        gsi_entry.gsi = kvm_get_irq_route_gsi(kvm_context);
+        kvm_add_routing_entry(kvm_context, &gsi_entry);
+        if (kvm_commit_irq_routes(kvm_context) < 0) {
+            perror("assigned_dev_enable_msi: kvm_commit_irq_routes");
+            assigned_dev->cap.state &= ~ASSIGNED_DEVICE_MSI_ENABLED;
+            return;
+        }
+        assigned_irq_data.guest_irq = gsi_entry.gsi;
+        assigned_irq_data.flags = KVM_DEV_IRQ_ASSIGN_ENABLE_MSI;
+    } else {
+        assigned_irq_data.guest_irq = assigned_dev->girq;
+    }
+
+    if (kvm_assign_irq(kvm_context, &assigned_irq_data) < 0)
+        perror("assigned_dev_enable_msi");
+    if (assigned_irq_data.flags & KVM_DEV_IRQ_ASSIGN_ENABLE_MSI) {
+        assigned_dev->cap.state |= ASSIGNED_DEVICE_MSI_ENABLED;
+        pci_dev->cap.config[ctrl_pos] |= PCI_MSI_FLAGS_ENABLE;
+    } else {
+        assigned_dev->cap.state &= ~ASSIGNED_DEVICE_MSI_ENABLED;
+        pci_dev->cap.config[ctrl_pos] &= ~PCI_MSI_FLAGS_ENABLE;
+    }
+}
+#endif
+
+void assigned_device_pci_cap_write_config(PCIDevice *pci_dev, uint32_t address,
+                                          uint32_t val, int len)
+{
+    AssignedDevice *assigned_dev = container_of(pci_dev, AssignedDevice, dev);
+    unsigned int pos = pci_dev->cap.start, ctrl_pos;
+
+    pci_default_cap_write_config(pci_dev, address, val, len);
+#if defined(KVM_CAP_DEVICE_MSI) && defined (KVM_CAP_IRQ_ROUTING)
+    if (assigned_dev->cap.available & ASSIGNED_DEVICE_CAP_MSI) {
+        ctrl_pos = pos + PCI_MSI_FLAGS;
+        if (address <= ctrl_pos && address + len > ctrl_pos)
+            assigned_dev_update_msi(pci_dev, ctrl_pos - pci_dev->cap.start);
+        pos += PCI_CAPABILITY_CONFIG_MSI_LENGTH;
+    }
+#endif
+    return;
+}
+
+static void assigned_device_pci_cap_init(PCIDevice *pci_dev)
+{
+    AssignedDevice *dev = container_of(pci_dev, AssignedDevice, dev);
+    int next_cap_pt;
+    struct pci_access *pacc;
+    int h_bus, h_dev, h_func;
+
+    pci_dev->cap.length = 0;
+    h_bus = dev->h_busnr;
+    h_dev = dev->h_devfn >> 3;
+    h_func = dev->h_devfn & 0x07;
+    pacc = pci_alloc();
+    pci_init(pacc);
+    dev->pdev = pci_get_dev(pacc, 0, h_bus, h_dev, h_func);
+    pci_cleanup(pacc);
+#if defined(KVM_CAP_DEVICE_MSI) && defined (KVM_CAP_IRQ_ROUTING)
+    /* Expose MSI capability
+     * MSI capability is the 1st capability in cap.config */
+    if (pci_find_cap_offset(dev->pdev, PCI_CAP_ID_MSI)) {
+        dev->cap.available |= ASSIGNED_DEVICE_CAP_MSI;
+        pci_dev->cap.config[pci_dev->cap.length] = PCI_CAP_ID_MSI;
+        pci_dev->cap.length += PCI_CAPABILITY_CONFIG_MSI_LENGTH;
+        next_cap_pt = 1;
+    }
+#endif
+}
+
 struct PCIDevice *init_assigned_device(AssignedDevInfo *adev, PCIBus *bus)
 {
     int r;
@@ -692,6 +786,10 @@ struct PCIDevice *init_assigned_device(AssignedDevInfo *adev, PCIBus *bus)
     if (r < 0)
         goto assigned_out;
 
+    pci_enable_capability_support(pci_dev, 0, NULL,
+                    assigned_device_pci_cap_write_config,
+                    assigned_device_pci_cap_init);
+
     return &dev->dev;
 
 assigned_out:
diff --git a/qemu/hw/device-assignment.h b/qemu/hw/device-assignment.h
index 0fd78de..39d73d9 100644
--- a/qemu/hw/device-assignment.h
+++ b/qemu/hw/device-assignment.h
@@ -81,6 +81,13 @@ typedef struct {
     unsigned char h_busnr;
     unsigned int h_devfn;
     int bound;
+    struct pci_dev *pdev;
+    struct {
+#define ASSIGNED_DEVICE_CAP_MSI (1 << 0)
+        uint32_t available;
+#define ASSIGNED_DEVICE_MSI_ENABLED (1 << 0)
+        uint32_t state;
+    } cap;
 } AssignedDevice;
 
 typedef struct AssignedDevInfo AssignedDevInfo;
-- 
1.5.4.5