Merge tag 'pull-vfio-20250311' of https://github.com/legoater/qemu into staging

vfio queue:

* Fixed endianness of VFIO device state packets
* Improved IGD passthrough support with legacy mode
* Improved build
* Added support for old AMD GPUs (x550)
* Updated property documentation

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmfQfQcACgkQUaNDx8/7
# 7KEUNw/+PjFpHrz5muQ8itkbyd36eJJdcxCl+9IPIWfnUfB582epkLcgvWyswGUo
# krFTregoRG0PKtgZDtv95owGtVJOgK6XYFadGHiYkvvsb41twOYsP7/SuI+KMiEv
# IDFLMvCTyorSIIoEF8i2EexfGPRV1VoWwvBoHgRRmYlzwzXnufjABpoZ0a25DTye
# DQ4yhSfqoIh1gOcdL9tPictnZg9OxKr2ePXNdrtymtEIhg3ZobD3Jd8J4WCcsfKT
# fxxBO5NsGgA8oM7i02fYN9kgMwqTnVhSAu1wq9PXsbrnNXam+trywAWSO6CjL+rV
# ++STWNSrRoHzuotRBr7BzrTpTFyQyfwBWqUT5L4NlhgXB3Xybk+M6Zj08Yva8pjE
# w78JQKvKp54gU34AWBW0/J6+u3v+iE8l1Eywx6xueF9Q+YSUDeW9B1LDdjFJryhF
# d8j3J+vuglbdsp05D+tVErf5cqFvFDfrjTkXkZNtmx7wky45XS9ZvNazYW1KI3f9
# bg8Wjb7ZujuvxpSjycPRZzdKa8kqSgSZg7fg91Wimiy1Iqe3SZVVWNchLYiPp8Dm
# nXMfOEpVHQZ1vzeo7dVWyxu9Y1ujgvUQy8kMa9q2W2S7HQ5Sna79n7eMVJxqZQ4G
# m0ETFToOcPPOnZBWgqNOSUlSQncFuIVgNTDvycQ9dMhGorYcBDI=
# =Vh0m
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 12 Mar 2025 02:12:23 HKT
# gpg:                using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@redhat.com>" [full]
# gpg:                 aka "Cédric Le Goater <clg@kaod.org>" [full]
# Primary key fingerprint: A0F6 6548 F048 95EB FE6B  0B60 51A3 43C7 CFFB ECA1

* tag 'pull-vfio-20250311' of https://github.com/legoater/qemu: (21 commits)
  vfio/pci: Drop debug commentary from x-device-dirty-page-tracking
  vfio/pci-quirks: Exclude non-ioport BAR from ATI quirk
  hw/vfio: Compile display.c once
  hw/vfio: Compile iommufd.c once
  hw/vfio: Compile more objects once
  hw/vfio: Compile some common objects once
  hw/vfio/common: Get target page size using runtime helpers
  hw/vfio/common: Include missing 'system/tcg.h' header
  hw/vfio/spapr: Do not include <linux/kvm.h>
  system: Declare qemu_[min/max]rampagesize() in 'system/hostmem.h'
  vfio/migration: Use BE byte order for device state wire packets
  vfio/igd: Fix broken KVMGT OpRegion support
  vfio/igd: Introduce x-igd-lpc option for LPC bridge ID quirk
  vfio/igd: Handle x-igd-opregion option in config quirk
  vfio/igd: Decouple common quirks from legacy mode
  vfio/igd: Refactor vfio_probe_igd_bar4_quirk into pci config quirk
  vfio/pci: Add placeholder for device-specific config space quirks
  vfio/igd: Move LPC bridge initialization to a separate function
  vfio/igd: Consolidate OpRegion initialization into a single function
  vfio/igd: Do not include GTT stolen size in etc/igd-bdsm-size
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

hw/ppc/spapr_caps.c

@@ -34,6 +34,7 @@
 #include "kvm_ppc.h"
 #include "migration/vmstate.h"
 #include "system/tcg.h"
+#include "system/hostmem.h"
 
 #include "hw/ppc/spapr.h"
 

hw/s390x/s390-virtio-ccw.c

@@ -41,6 +41,7 @@
 #include "hw/s390x/tod.h"
 #include "system/system.h"
 #include "system/cpus.h"
+#include "system/hostmem.h"
 #include "target/s390x/kvm/pv.h"
 #include "migration/blocker.h"
 #include "qapi/visitor.h"

hw/vfio/common.c

@@ -30,6 +30,7 @@
 #include "exec/address-spaces.h"
 #include "exec/memory.h"
 #include "exec/ram_addr.h"
+#include "exec/target_page.h"
 #include "hw/hw.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
@@ -42,6 +43,7 @@
 #include "migration/misc.h"
 #include "migration/blocker.h"
 #include "migration/qemu-file.h"
+#include "system/tcg.h"
 #include "system/tpm.h"
 
 VFIODeviceList vfio_device_list =
@@ -392,13 +394,14 @@ static void vfio_register_ram_discard_listener(VFIOContainerBase *bcontainer,
                                                MemoryRegionSection *section)
 {
     RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
+    int target_page_size = qemu_target_page_size();
     VFIORamDiscardListener *vrdl;
 
     /* Ignore some corner cases not relevant in practice. */
-    g_assert(QEMU_IS_ALIGNED(section->offset_within_region, TARGET_PAGE_SIZE));
+    g_assert(QEMU_IS_ALIGNED(section->offset_within_region, target_page_size));
     g_assert(QEMU_IS_ALIGNED(section->offset_within_address_space,
-                             TARGET_PAGE_SIZE));
-    g_assert(QEMU_IS_ALIGNED(int128_get64(section->size), TARGET_PAGE_SIZE));
+                             target_page_size));
+    g_assert(QEMU_IS_ALIGNED(int128_get64(section->size), target_page_size));
 
     vrdl = g_new0(VFIORamDiscardListener, 1);
     vrdl->bcontainer = bcontainer;

hw/vfio/iommufd.c

@@ -25,7 +25,6 @@
 #include "qemu/cutils.h"
 #include "qemu/chardev_open.h"
 #include "pci.h"
-#include "exec/ram_addr.h"
 
 static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova,
                             ram_addr_t size, void *vaddr, bool readonly)

hw/vfio/meson.build

@@ -1,27 +1,32 @@
 vfio_ss = ss.source_set()
 vfio_ss.add(files(
-  'helpers.c',
   'common.c',
-  'container-base.c',
   'container.c',
-  'migration.c',
-  'migration-multifd.c',
-  'cpr.c',
 ))
 vfio_ss.add(when: 'CONFIG_PSERIES', if_true: files('spapr.c'))
-vfio_ss.add(when: 'CONFIG_IOMMUFD', if_true: files(
-  'iommufd.c',
-))
 vfio_ss.add(when: 'CONFIG_VFIO_PCI', if_true: files(
-  'display.c',
   'pci-quirks.c',
   'pci.c',
 ))
 vfio_ss.add(when: 'CONFIG_VFIO_CCW', if_true: files('ccw.c'))
 vfio_ss.add(when: 'CONFIG_VFIO_PLATFORM', if_true: files('platform.c'))
-vfio_ss.add(when: 'CONFIG_VFIO_XGMAC', if_true: files('calxeda-xgmac.c'))
-vfio_ss.add(when: 'CONFIG_VFIO_AMD_XGBE', if_true: files('amd-xgbe.c'))
 vfio_ss.add(when: 'CONFIG_VFIO_AP', if_true: files('ap.c'))
 vfio_ss.add(when: 'CONFIG_VFIO_IGD', if_true: files('igd.c'))
 
 specific_ss.add_all(when: 'CONFIG_VFIO', if_true: vfio_ss)
+
+system_ss.add(when: 'CONFIG_VFIO_XGMAC', if_true: files('calxeda-xgmac.c'))
+system_ss.add(when: 'CONFIG_VFIO_AMD_XGBE', if_true: files('amd-xgbe.c'))
+system_ss.add(when: 'CONFIG_VFIO', if_true: files(
+  'helpers.c',
+  'container-base.c',
+  'migration.c',
+  'migration-multifd.c',
+  'cpr.c',
+))
+system_ss.add(when: ['CONFIG_VFIO', 'CONFIG_IOMMUFD'], if_true: files(
+  'iommufd.c',
+))
+system_ss.add(when: 'CONFIG_VFIO_PCI', if_true: files(
+  'display.c',
+))

hw/vfio/migration-multifd.c

@@ -13,6 +13,7 @@
 #include "hw/vfio/vfio-common.h"
 #include "migration/misc.h"
 #include "qapi/error.h"
+#include "qemu/bswap.h"
 #include "qemu/error-report.h"
 #include "qemu/lockable.h"
 #include "qemu/main-loop.h"
@@ -155,12 +156,16 @@ bool vfio_multifd_load_state_buffer(void *opaque, char *data, size_t data_size,
         return false;
     }
 
+    packet->version = be32_to_cpu(packet->version);
     if (packet->version != VFIO_DEVICE_STATE_PACKET_VER_CURRENT) {
         error_setg(errp, "%s: packet has unknown version %" PRIu32,
                    vbasedev->name, packet->version);
         return false;
     }
 
+    packet->idx = be32_to_cpu(packet->idx);
+    packet->flags = be32_to_cpu(packet->flags);
+
     if (packet->idx == UINT32_MAX) {
         error_setg(errp, "%s: packet index is invalid", vbasedev->name);
         return false;
@@ -558,9 +563,9 @@ vfio_save_complete_precopy_thread_config_state(VFIODevice *vbasedev,
 
     packet_len = sizeof(*packet) + bioc->usage;
     packet = g_malloc0(packet_len);
-    packet->version = VFIO_DEVICE_STATE_PACKET_VER_CURRENT;
-    packet->idx = idx;
-    packet->flags = VFIO_DEVICE_STATE_CONFIG_STATE;
+    packet->version = cpu_to_be32(VFIO_DEVICE_STATE_PACKET_VER_CURRENT);
+    packet->idx = cpu_to_be32(idx);
+    packet->flags = cpu_to_be32(VFIO_DEVICE_STATE_CONFIG_STATE);
     memcpy(&packet->data, bioc->data, bioc->usage);
 
     if (!multifd_queue_device_state(idstr, instance_id,
@@ -610,7 +615,7 @@ vfio_multifd_save_complete_precopy_thread(SaveLiveCompletePrecopyThreadData *d,
     }
 
     packet = g_malloc0(sizeof(*packet) + migration->data_buffer_size);
-    packet->version = VFIO_DEVICE_STATE_PACKET_VER_CURRENT;
+    packet->version = cpu_to_be32(VFIO_DEVICE_STATE_PACKET_VER_CURRENT);
 
     for (idx = 0; ; idx++) {
         ssize_t data_size;
@@ -631,7 +636,7 @@ vfio_multifd_save_complete_precopy_thread(SaveLiveCompletePrecopyThreadData *d,
             break;
         }
 
-        packet->idx = idx;
+        packet->idx = cpu_to_be32(idx);
         packet_size = sizeof(*packet) + data_size;
 
         if (!multifd_queue_device_state(d->idstr, d->instance_id,

hw/vfio/migration.c

@@ -27,7 +27,6 @@
 #include "qapi/error.h"
 #include "qapi/qapi-events-vfio.h"
 #include "exec/ramlist.h"
-#include "exec/ram_addr.h"
 #include "pci.h"
 #include "trace.h"
 #include "hw/hw.h"

hw/vfio/pci-quirks.c

@@ -403,7 +403,7 @@ static void vfio_probe_ati_bar4_quirk(VFIOPCIDevice *vdev, int nr)
 
     /* This windows doesn't seem to be used except by legacy VGA code */
     if (!vfio_pci_is(vdev, PCI_VENDOR_ID_ATI, PCI_ANY_ID) ||
-        !vdev->vga || nr != 4) {
+        !vdev->vga || nr != 4 || !vdev->bars[4].ioport) {
         return;
     }
 
@@ -1114,59 +1114,19 @@ static void vfio_probe_rtl8168_bar2_quirk(VFIOPCIDevice *vdev, int nr)
     trace_vfio_quirk_rtl8168_probe(vdev->vbasedev.name);
 }
 
-#define IGD_ASLS 0xfc /* ASL Storage Register */
-
-/*
- * The OpRegion includes the Video BIOS Table, which seems important for
- * telling the driver what sort of outputs it has.  Without this, the device
- * may work in the guest, but we may not get output.  This also requires BIOS
- * support to reserve and populate a section of guest memory sufficient for
- * the table and to write the base address of that memory to the ASLS register
- * of the IGD device.
- */
-bool vfio_pci_igd_opregion_init(VFIOPCIDevice *vdev,
-                                struct vfio_region_info *info, Error **errp)
-{
-    int ret;
-
-    vdev->igd_opregion = g_malloc0(info->size);
-    ret = pread(vdev->vbasedev.fd, vdev->igd_opregion,
-                info->size, info->offset);
-    if (ret != info->size) {
-        error_setg(errp, "failed to read IGD OpRegion");
-        g_free(vdev->igd_opregion);
-        vdev->igd_opregion = NULL;
-        return false;
-    }
-
-    /*
-     * Provide fw_cfg with a copy of the OpRegion which the VM firmware is to
-     * allocate 32bit reserved memory for, copy these contents into, and write
-     * the reserved memory base address to the device ASLS register at 0xFC.
-     * Alignment of this reserved region seems flexible, but using a 4k page
-     * alignment seems to work well.  This interface assumes a single IGD
-     * device, which may be at VM address 00:02.0 in legacy mode or another
-     * address in UPT mode.
-     *
-     * NB, there may be future use cases discovered where the VM should have
-     * direct interaction with the host OpRegion, in which case the write to
-     * the ASLS register would trigger MemoryRegion setup to enable that.
-     */
-    fw_cfg_add_file(fw_cfg_find(), "etc/igd-opregion",
-                    vdev->igd_opregion, info->size);
-
-    trace_vfio_pci_igd_opregion_enabled(vdev->vbasedev.name);
-
-    pci_set_long(vdev->pdev.config + IGD_ASLS, 0);
-    pci_set_long(vdev->pdev.wmask + IGD_ASLS, ~0);
-    pci_set_long(vdev->emulated_config_bits + IGD_ASLS, ~0);
-
-    return true;
-}
-
 /*
  * Common quirk probe entry points.
  */
+bool vfio_config_quirk_setup(VFIOPCIDevice *vdev, Error **errp)
+{
+#ifdef CONFIG_VFIO_IGD
+    if (!vfio_probe_igd_config_quirk(vdev, errp)) {
+        return false;
+    }
+#endif
+    return true;
+}
+
 void vfio_vga_quirk_setup(VFIOPCIDevice *vdev)
 {
     vfio_vga_probe_ati_3c3_quirk(vdev);
@@ -1215,7 +1175,6 @@ void vfio_bar_quirk_setup(VFIOPCIDevice *vdev, int nr)
     vfio_probe_rtl8168_bar2_quirk(vdev, nr);
 #ifdef CONFIG_VFIO_IGD
     vfio_probe_igd_bar0_quirk(vdev, nr);
-    vfio_probe_igd_bar4_quirk(vdev, nr);
 #endif
 }
 

hw/vfio/pci.c

@@ -3128,6 +3128,10 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
         goto out_unset_idev;
     }
 
+    if (!vfio_config_quirk_setup(vdev, errp)) {
+        goto out_unset_idev;
+    }
+
     if (vdev->vga) {
         vfio_vga_quirk_setup(vdev);
     }
@@ -3136,31 +3140,6 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
         vfio_bar_quirk_setup(vdev, i);
     }
 
-    if (!vdev->igd_opregion &&
-        vdev->features & VFIO_FEATURE_ENABLE_IGD_OPREGION) {
-        g_autofree struct vfio_region_info *opregion = NULL;
-
-        if (vdev->pdev.qdev.hotplugged) {
-            error_setg(errp,
-                       "cannot support IGD OpRegion feature on hotplugged "
-                       "device");
-            goto out_unset_idev;
-        }
-
-        ret = vfio_get_dev_region_info(vbasedev,
-                        VFIO_REGION_TYPE_PCI_VENDOR_TYPE | PCI_VENDOR_ID_INTEL,
-                        VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION, &opregion);
-        if (ret) {
-            error_setg_errno(errp, -ret,
-                             "does not support requested IGD OpRegion feature");
-            goto out_unset_idev;
-        }
-
-        if (!vfio_pci_igd_opregion_init(vdev, opregion, errp)) {
-            goto out_unset_idev;
-        }
-    }
-
     /* QEMU emulates all of MSI & MSIX */
     if (pdev->cap_present & QEMU_PCI_CAP_MSIX) {
         memset(vdev->emulated_config_bits + pdev->msix_cap, 0xff,
@@ -3381,6 +3360,10 @@ static const Property vfio_pci_dev_properties[] = {
                     VFIO_FEATURE_ENABLE_REQ_BIT, true),
     DEFINE_PROP_BIT("x-igd-opregion", VFIOPCIDevice, features,
                     VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false),
+    DEFINE_PROP_BIT("x-igd-lpc", VFIOPCIDevice, features,
+                    VFIO_FEATURE_ENABLE_IGD_LPC_BIT, false),
+    DEFINE_PROP_ON_OFF_AUTO("x-igd-legacy-mode", VFIOPCIDevice,
+                            igd_legacy_mode, ON_OFF_AUTO_AUTO),
     DEFINE_PROP_ON_OFF_AUTO("enable-migration", VFIOPCIDevice,
                             vbasedev.enable_migration, ON_OFF_AUTO_AUTO),
     DEFINE_PROP("x-migration-multifd-transfer", VFIOPCIDevice,
@@ -3549,7 +3532,7 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
     object_class_property_set_description(klass, /* 9.1 */
                                           "x-device-dirty-page-tracking",
                                           "Disable device dirty page tracking and use "
-                                          "container-based dirty page tracking (DEBUG)");
+                                          "container-based dirty page tracking");
     object_class_property_set_description(klass, /* 9.1 */
                                           "migration-events",
                                           "Emit VFIO migration QAPI event when a VFIO device "

hw/vfio/pci.h

@@ -154,10 +154,14 @@ struct VFIOPCIDevice {
 #define VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT 2
 #define VFIO_FEATURE_ENABLE_IGD_OPREGION \
                                 (1 << VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT)
+#define VFIO_FEATURE_ENABLE_IGD_LPC_BIT 3
+#define VFIO_FEATURE_ENABLE_IGD_LPC \
+                                (1 << VFIO_FEATURE_ENABLE_IGD_LPC_BIT)
     OnOffAuto display;
     uint32_t display_xres;
     uint32_t display_yres;
     int32_t bootindex;
+    OnOffAuto igd_legacy_mode;
     uint32_t igd_gms;
     OffAutoPCIBAR msix_relo;
     uint8_t nv_gpudirect_clique;
@@ -204,6 +208,7 @@ uint64_t vfio_vga_read(void *opaque, hwaddr addr, unsigned size);
 void vfio_vga_write(void *opaque, hwaddr addr, uint64_t data, unsigned size);
 
 bool vfio_opt_rom_in_denylist(VFIOPCIDevice *vdev);
+bool vfio_config_quirk_setup(VFIOPCIDevice *vdev, Error **errp);
 void vfio_vga_quirk_setup(VFIOPCIDevice *vdev);
 void vfio_vga_quirk_exit(VFIOPCIDevice *vdev);
 void vfio_vga_quirk_finalize(VFIOPCIDevice *vdev);
@@ -215,7 +220,7 @@ bool vfio_add_virt_caps(VFIOPCIDevice *vdev, Error **errp);
 void vfio_quirk_reset(VFIOPCIDevice *vdev);
 VFIOQuirk *vfio_quirk_alloc(int nr_mem);
 void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr);
-void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr);
+bool vfio_probe_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp);
 
 extern const PropertyInfo qdev_prop_nv_gpudirect_clique;
 
@@ -227,10 +232,6 @@ int vfio_pci_get_pci_hot_reset_info(VFIOPCIDevice *vdev,
 
 bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp);
 
-bool vfio_pci_igd_opregion_init(VFIOPCIDevice *vdev,
-                                struct vfio_region_info *info,
-                                Error **errp);
-
 void vfio_display_reset(VFIOPCIDevice *vdev);
 bool vfio_display_probe(VFIOPCIDevice *vdev, Error **errp);
 void vfio_display_finalize(VFIOPCIDevice *vdev);

hw/vfio/spapr.c

@@ -11,10 +11,8 @@
 #include "qemu/osdep.h"
 #include <sys/ioctl.h>
 #include <linux/vfio.h>
-#ifdef CONFIG_KVM
-#include <linux/kvm.h>
-#endif
 #include "system/kvm.h"
+#include "system/hostmem.h"
 #include "exec/address-spaces.h"
 
 #include "hw/vfio/vfio-common.h"

include/exec/ram_addr.h

@@ -102,9 +102,6 @@ static inline unsigned long int ramblock_recv_bitmap_offset(void *host_addr,
 
 bool ramblock_is_pmem(RAMBlock *rb);
 
-long qemu_minrampagesize(void);
-long qemu_maxrampagesize(void);
-
 /**
  * qemu_ram_alloc_from_file,
  * qemu_ram_alloc_from_fd:  Allocate a ram block from the specified backing

include/system/hostmem.h

@@ -93,4 +93,7 @@ bool host_memory_backend_is_mapped(HostMemoryBackend *backend);
 size_t host_memory_backend_pagesize(HostMemoryBackend *memdev);
 char *host_memory_backend_get_name(HostMemoryBackend *backend);
 
+long qemu_minrampagesize(void);
+long qemu_maxrampagesize(void);
+
 #endif