diff mbox series

[17/26] vfio-user: pci_user_realize PCI setup

Message ID 20240529162319.1476680-18-levon@movementarian.org (mailing list archive)
State New, archived
Headers show
Series vfio-user client | expand

Commit Message

John Levon May 29, 2024, 4:23 p.m. UTC 
From: Jagannathan Raman <jag.raman@oracle.com>

PCI BARs read from remote device
PCI config reads/writes sent to remote server

Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
---
 hw/vfio/pci.c      | 249 ++++++++++++++++++++++++++-------------------
 hw/vfio/pci.h      |  10 ++
 hw/vfio/user-pci.c |  42 ++++++++
 3 files changed, 194 insertions(+), 107 deletions(-)
diff mbox series

Patch

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index c69716f2df..d1da64383e 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1728,7 +1728,7 @@  static bool vfio_msix_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
     return true;
 }
 
-static void vfio_teardown_msi(VFIOPCIDevice *vdev)
+void vfio_teardown_msi(VFIOPCIDevice *vdev)
 {
     msi_uninit(&vdev->pdev);
 
@@ -1829,7 +1829,7 @@  static void vfio_bars_register(VFIOPCIDevice *vdev)
     }
 }
 
-static void vfio_bars_exit(VFIOPCIDevice *vdev)
+void vfio_bars_exit(VFIOPCIDevice *vdev)
 {
     int i;
 
@@ -1849,7 +1849,7 @@  static void vfio_bars_exit(VFIOPCIDevice *vdev)
     }
 }
 
-static void vfio_bars_finalize(VFIOPCIDevice *vdev)
+void vfio_bars_finalize(VFIOPCIDevice *vdev)
 {
     int i;
 
@@ -2417,7 +2417,7 @@  static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
     return;
 }
 
-static bool vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
+bool vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
 {
     PCIDevice *pdev = &vdev->pdev;
 
@@ -2766,7 +2766,7 @@  bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)
     return true;
 }
 
-static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
+bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
 {
     VFIODevice *vbasedev = &vdev->vbasedev;
     struct vfio_region_info *reg_info = NULL;
@@ -2884,7 +2884,7 @@  static void vfio_err_notifier_handler(void *opaque)
  * and continue after disabling error recovery support for the
  * device.
  */
-static void vfio_register_err_notifier(VFIOPCIDevice *vdev)
+void vfio_register_err_notifier(VFIOPCIDevice *vdev)
 {
     Error *err = NULL;
     int32_t fd;
@@ -2943,7 +2943,7 @@  static void vfio_req_notifier_handler(void *opaque)
     }
 }
 
-static void vfio_register_req_notifier(VFIOPCIDevice *vdev)
+void vfio_register_req_notifier(VFIOPCIDevice *vdev)
 {
     struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info),
                                       .index = VFIO_PCI_REQ_IRQ_INDEX };
@@ -2998,6 +2998,130 @@  static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
     vdev->req_enabled = false;
 }
 
+bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp)
+{
+    PCIDevice *pdev = &vdev->pdev;
+    VFIODevice *vbasedev = &vdev->vbasedev;
+
+    /* vfio emulates a lot for us, but some bits need extra love */
+    vdev->emulated_config_bits = g_malloc0(vdev->config_size);
+
+    /* QEMU can choose to expose the ROM or not */
+    memset(vdev->emulated_config_bits + PCI_ROM_ADDRESS, 0xff, 4);
+    /* QEMU can also add or extend BARs */
+    memset(vdev->emulated_config_bits + PCI_BASE_ADDRESS_0, 0xff, 6 * 4);
+
+    /*
+     * The PCI spec reserves vendor ID 0xffff as an invalid value.  The
+     * device ID is managed by the vendor and need only be a 16-bit value.
+     * Allow any 16-bit value for subsystem so they can be hidden or changed.
+     */
+    if (vdev->vendor_id != PCI_ANY_ID) {
+        if (vdev->vendor_id >= 0xffff) {
+            error_setg(errp, "invalid PCI vendor ID provided");
+            return false;
+        }
+        vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0);
+        trace_vfio_pci_emulated_vendor_id(vdev->vbasedev.name, vdev->vendor_id);
+    } else {
+        vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
+    }
+
+    if (vdev->device_id != PCI_ANY_ID) {
+        if (vdev->device_id > 0xffff) {
+            error_setg(errp, "invalid PCI device ID provided");
+            return false;
+        }
+        vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0);
+        trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id);
+    } else {
+        vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
+    }
+
+    if (vdev->sub_vendor_id != PCI_ANY_ID) {
+        if (vdev->sub_vendor_id > 0xffff) {
+            error_setg(errp, "invalid PCI subsystem vendor ID provided");
+            return false;
+        }
+        vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID,
+                               vdev->sub_vendor_id, ~0);
+        trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name,
+                                              vdev->sub_vendor_id);
+    }
+
+    if (vdev->sub_device_id != PCI_ANY_ID) {
+        if (vdev->sub_device_id > 0xffff) {
+            error_setg(errp, "invalid PCI subsystem device ID provided");
+            return false;
+        }
+        vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0);
+        trace_vfio_pci_emulated_sub_device_id(vbasedev->name,
+                                              vdev->sub_device_id);
+    }
+
+    /* QEMU can change multi-function devices to single function, or reverse */
+    vdev->emulated_config_bits[PCI_HEADER_TYPE] =
+                                              PCI_HEADER_TYPE_MULTI_FUNCTION;
+
+    /* Restore or clear multifunction, this is always controlled by QEMU */
+    if (vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
+        vdev->pdev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
+    } else {
+        vdev->pdev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
+    }
+
+    /*
+     * Clear host resource mapping info.  If we choose not to register a
+     * BAR, such as might be the case with the option ROM, we can get
+     * confusing, unwritable, residual addresses from the host here.
+     */
+    memset(&vdev->pdev.config[PCI_BASE_ADDRESS_0], 0, 24);
+    memset(&vdev->pdev.config[PCI_ROM_ADDRESS], 0, 4);
+
+    vfio_pci_size_rom(vdev);
+
+    vfio_bars_prepare(vdev);
+
+    if (!vfio_msix_early_setup(vdev, errp)) {
+        return false;
+    }
+
+    vfio_bars_register(vdev);
+
+    return true;
+}
+
+bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp)
+{
+    PCIDevice *pdev = &vdev->pdev;
+
+    /* QEMU emulates all of MSI & MSIX */
+    if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
+        memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
+               MSIX_CAP_LENGTH);
+    }
+
+    if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
+        memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
+               vdev->msi_cap_size);
+    }
+
+    if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
+        vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
+                                                  vfio_intx_mmap_enable, vdev);
+        pci_device_set_intx_routing_notifier(&vdev->pdev,
+                                             vfio_intx_routing_notifier);
+        vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
+        kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
+        if (!vfio_intx_enable(vdev, errp)) {
+            pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
+            kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
+            return false;
+        }
+    }
+    return true;
+}
+
 static void vfio_realize(PCIDevice *pdev, Error **errp)
 {
     ERRP_GUARD();
@@ -3078,90 +3202,15 @@  static void vfio_realize(PCIDevice *pdev, Error **errp)
         goto error;
     }
 
-    /* vfio emulates a lot for us, but some bits need extra love */
-    vdev->emulated_config_bits = g_malloc0(vdev->config_size);
-
-    /* QEMU can choose to expose the ROM or not */
-    memset(vdev->emulated_config_bits + PCI_ROM_ADDRESS, 0xff, 4);
-    /* QEMU can also add or extend BARs */
-    memset(vdev->emulated_config_bits + PCI_BASE_ADDRESS_0, 0xff, 6 * 4);
-
-    /*
-     * The PCI spec reserves vendor ID 0xffff as an invalid value.  The
-     * device ID is managed by the vendor and need only be a 16-bit value.
-     * Allow any 16-bit value for subsystem so they can be hidden or changed.
-     */
-    if (vdev->vendor_id != PCI_ANY_ID) {
-        if (vdev->vendor_id >= 0xffff) {
-            error_setg(errp, "invalid PCI vendor ID provided");
-            goto error;
-        }
-        vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0);
-        trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id);
-    } else {
-        vdev->vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
-    }
-
-    if (vdev->device_id != PCI_ANY_ID) {
-        if (vdev->device_id > 0xffff) {
-            error_setg(errp, "invalid PCI device ID provided");
-            goto error;
-        }
-        vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0);
-        trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id);
-    } else {
-        vdev->device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
-    }
-
-    if (vdev->sub_vendor_id != PCI_ANY_ID) {
-        if (vdev->sub_vendor_id > 0xffff) {
-            error_setg(errp, "invalid PCI subsystem vendor ID provided");
-            goto error;
-        }
-        vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID,
-                               vdev->sub_vendor_id, ~0);
-        trace_vfio_pci_emulated_sub_vendor_id(vbasedev->name,
-                                              vdev->sub_vendor_id);
-    }
-
-    if (vdev->sub_device_id != PCI_ANY_ID) {
-        if (vdev->sub_device_id > 0xffff) {
-            error_setg(errp, "invalid PCI subsystem device ID provided");
-            goto error;
-        }
-        vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id, ~0);
-        trace_vfio_pci_emulated_sub_device_id(vbasedev->name,
-                                              vdev->sub_device_id);
-    }
-
-    /* QEMU can change multi-function devices to single function, or reverse */
-    vdev->emulated_config_bits[PCI_HEADER_TYPE] =
-                                              PCI_HEADER_TYPE_MULTI_FUNCTION;
-
-    /* Restore or clear multifunction, this is always controlled by QEMU */
-    if (vdev->pdev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
-        vdev->pdev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
-    } else {
-        vdev->pdev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
+    if (!vfio_pci_config_setup(vdev, errp)) {
+        goto error;
     }
 
     /*
-     * Clear host resource mapping info.  If we choose not to register a
-     * BAR, such as might be the case with the option ROM, we can get
-     * confusing, unwritable, residual addresses from the host here.
+     * vfio_pci_config_setup will have registered the device's BARs
+     * and setup any MSIX BARs, so errors after it succeeds must
+     * use out_teardown
      */
-    memset(&vdev->pdev.config[PCI_BASE_ADDRESS_0], 0, 24);
-    memset(&vdev->pdev.config[PCI_ROM_ADDRESS], 0, 4);
-
-    vfio_pci_size_rom(vdev);
-
-    vfio_bars_prepare(vdev);
-
-    if (!vfio_msix_early_setup(vdev, errp)) {
-        goto error;
-    }
-
-    vfio_bars_register(vdev);
 
     if (!vfio_add_capabilities(vdev, errp)) {
         goto out_teardown;
@@ -3200,28 +3249,14 @@  static void vfio_realize(PCIDevice *pdev, Error **errp)
         }
     }
 
-    /* QEMU emulates all of MSI & MSIX */
-    if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
-        memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
-               MSIX_CAP_LENGTH);
-    }
-
-    if (pdev->cap_present & QEMU_PCI_CAP_MSI) {
-        memset(vdev->emulated_config_bits + pdev->msi_cap, 0xff,
-               vdev->msi_cap_size);
+    if (!vfio_interrupt_setup(vdev, errp)) {
+        goto out_teardown;
     }
 
-    if (vfio_pci_read_config(&vdev->pdev, PCI_INTERRUPT_PIN, 1)) {
-        vdev->intx.mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
-                                                  vfio_intx_mmap_enable, vdev);
-        pci_device_set_intx_routing_notifier(&vdev->pdev,
-                                             vfio_intx_routing_notifier);
-        vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
-        kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
-        if (!vfio_intx_enable(vdev, errp)) {
-            goto out_deregister;
-        }
-    }
+    /*
+     * vfio_interrupt_setup will have setup INTx's KVM routing
+     * so errors after it succeeds must use out_deregister
+     */
 
     if (vdev->display != ON_OFF_AUTO_OFF) {
         if (!vfio_display_probe(vdev, errp)) {
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 040f4995b5..1eeb67bb2e 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -218,6 +218,16 @@  Object *vfio_pci_get_object(VFIODevice *vbasedev);
 int vfio_pci_save_config(VFIODevice *vbasedev, QEMUFile *f, Error **errp);
 int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f);
 void vfio_pci_put_device(VFIOPCIDevice *vdev);
+bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp);
+void vfio_teardown_msi(VFIOPCIDevice *vdev);
+void vfio_bars_exit(VFIOPCIDevice *vdev);
+void vfio_bars_finalize(VFIOPCIDevice *vdev);
+bool vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp);
+void vfio_put_device(VFIOPCIDevice *vdev);
+void vfio_register_err_notifier(VFIOPCIDevice *vdev);
+void vfio_register_req_notifier(VFIOPCIDevice *vdev);
+bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp);
+bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp);
 void vfio_instance_init(Object *obj);
 
 uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size);
diff --git a/hw/vfio/user-pci.c b/hw/vfio/user-pci.c
index 54b19b68d0..b8a9f7a7fb 100644
--- a/hw/vfio/user-pci.c
+++ b/hw/vfio/user-pci.c
@@ -79,6 +79,7 @@  static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     AddressSpace *as;
     SocketAddress addr;
     VFIOUserProxy *proxy;
+    int ret;
 
     /*
      * TODO: make option parser understand SocketAddress
@@ -126,8 +127,45 @@  static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
         goto error;
     }
 
+    if (!vfio_populate_device(vdev, errp)) {
+        goto error;
+    }
+
+    /* Get a copy of config space */
+    ret = vbasedev->io->region_read(vbasedev, VFIO_PCI_CONFIG_REGION_INDEX, 0,
+                               MIN(pci_config_size(pdev), vdev->config_size),
+                               pdev->config);
+    if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) {
+        error_setg_errno(errp, -ret, "failed to read device config space");
+        goto error;
+    }
+
+    if (!vfio_pci_config_setup(vdev, errp)) {
+        goto error;
+    }
+
+    /*
+     * vfio_pci_config_setup will have registered the device's BARs
+     * and setup any MSIX BARs, so errors after it succeeds must
+     * use out_teardown
+     */
+
+    if (!vfio_add_capabilities(vdev, errp)) {
+        goto out_teardown;
+    }
+
+    if (!vfio_interrupt_setup(vdev, errp)) {
+        goto out_teardown;
+    }
+
+    vfio_register_err_notifier(vdev);
+    vfio_register_req_notifier(vdev);
+
     return;
 
+out_teardown:
+    vfio_teardown_msi(vdev);
+    vfio_bars_exit(vdev);
 error:
     error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.name);
 }
@@ -163,6 +201,10 @@  static void vfio_user_instance_finalize(Object *obj)
     VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
     VFIODevice *vbasedev = &vdev->vbasedev;
 
+    vfio_bars_finalize(vdev);
+    g_free(vdev->emulated_config_bits);
+    g_free(vdev->rom);
+
     vfio_pci_put_device(vdev);
 
     if (vbasedev->proxy != NULL) {