Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pci, pc, virtio: fixes, cleanups, tests Lots of work on tests: BiosTablesTest UEFI app, vhost-user testing for non-Linux hosts. Misc cleanups and fixes all over the place Signed-off-by: Michael S. Tsirkin <mst@redhat.com> # gpg: Signature made Fri 22 Feb 2019 15:51:40 GMT # gpg: using RSA key 281F0DB8D28D5469 # gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>" [full] # gpg: aka "Michael S. Tsirkin <mst@redhat.com>" [full] # Primary key fingerprint: 0270 606B 6F3C DF3D 0B17 0970 C350 3912 AFBE 8E67 # Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA 8A0D 281F 0DB8 D28D 5469 * remotes/mst/tags/for_upstream: (26 commits) pci: Sanity test minimum downstream LNKSTA hw/smbios: fix offset of type 3 sku field pci: Move NVIDIA vendor id to the rest of ids virtio-balloon: Safely handle BALLOON_PAGE_SIZE < host page size virtio-balloon: Use ram_block_discard_range() instead of raw madvise() virtio-balloon: Rework ballon_page() interface virtio-balloon: Corrections to address verification virtio-balloon: Remove unnecessary MADV_WILLNEED on deflate i386/kvm: ignore masked irqs when update msi routes contrib/vhost-user-blk: fix the compilation issue Revert "contrib/vhost-user-blk: fix the compilation issue" pc-dimm: use same mechanism for [get|set]_addr tests/data: introduce "uefi-boot-images" with the "bios-tables-test" ISOs tests/uefi-test-tools: add build scripts tests: introduce "uefi-test-tools" with the BiosTablesTest UEFI app roms: build the EfiRom utility from the roms/edk2 submodule roms: add the edk2 project as a git submodule vhost-user-test: create a temporary directory per TestServer vhost-user-test: small changes to init_hugepagefs vhost-user-test: create a main loop per TestServer ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2026-07-06 00:20:22 -07:00 · 2019-03-04 11:04:31 +00:00
parent 20b084c4b1 88c869198a
commit 1d31f1872b
42 changed files with 1051 additions and 248 deletions
@@ -49,3 +49,6 @@
 [submodule "tests/fp/berkeley-softfloat-3"]
 	path = tests/fp/berkeley-softfloat-3
 	url = https://github.com/cota/berkeley-softfloat-3
+[submodule "roms/edk2"]
+	path = roms/edk2
+	url = https://github.com/tianocore/edk2.git
@@ -609,7 +609,11 @@ clean:
 	rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
 	rm -f qemu-options.def
 	rm -f *.msi
-	find . \( -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
+	find . \( -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f \
+		! -path ./roms/edk2/ArmPkg/Library/GccLto/liblto-aarch64.a \
+		! -path ./roms/edk2/ArmPkg/Library/GccLto/liblto-arm.a \
+		! -path ./roms/edk2/BaseTools/Source/Python/UPT/Dll/sqlite3.dll \
+		-exec rm {} +
 	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -f fsdev/*.pod scsi/*.pod
 	rm -f qemu-img-cmds.h
@@ -9,10 +9,9 @@ common-obj-$(CONFIG_POSIX) += hostmem-file.o
 common-obj-y += cryptodev.o
 common-obj-y += cryptodev-builtin.o

-ifeq ($(CONFIG_VIRTIO),y)
+ifeq ($(CONFIG_VIRTIO_CRYPTO),y)
 common-obj-y += cryptodev-vhost.o
-common-obj-$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX)) += \
-    cryptodev-vhost-user.o
+common-obj-$(CONFIG_VHOST_CRYPTO) += cryptodev-vhost-user.o
 endif

 common-obj-$(CONFIG_LINUX) += hostmem-memfd.o
@@ -368,10 +368,10 @@ libattr=""
 xfs=""
 tcg="yes"
 membarrier=""
-vhost_net="no"
-vhost_crypto="no"
-vhost_scsi="no"
-vhost_vsock="no"
+vhost_net=""
+vhost_crypto=""
+vhost_scsi=""
+vhost_vsock=""
 vhost_user=""
 kvm="no"
 hax="no"
@@ -783,6 +783,7 @@ case $targetos in
 MINGW32*)
  mingw32="yes"
  hax="yes"
+  vhost_user="no"
  audio_possible_drivers="dsound sdl"
  if check_include dsound.h; then
    audio_drv_list="dsound"
@@ -884,10 +885,6 @@ Linux)
  linux="yes"
  linux_user="yes"
  kvm="yes"
-  vhost_net="yes"
-  vhost_crypto="yes"
-  vhost_scsi="yes"
-  vhost_vsock="yes"
  QEMU_INCLUDES="-I\$(SRC_PATH)/linux-headers -I$PWD/linux-headers $QEMU_INCLUDES"
  supported_os="yes"
  libudev="yes"
@@ -1263,11 +1260,7 @@ for opt do
  ;;
  --disable-vhost-crypto) vhost_crypto="no"
  ;;
-  --enable-vhost-crypto)
-      vhost_crypto="yes"
-      if test "$mingw32" = "yes"; then
-          error_exit "vhost-crypto isn't available on win32"
-      fi
+  --enable-vhost-crypto) vhost_crypto="yes"
  ;;
  --disable-vhost-scsi) vhost_scsi="no"
  ;;
@@ -1476,11 +1469,11 @@ for opt do
  ;;
  --disable-vhost-user) vhost_user="no"
  ;;
-  --enable-vhost-user)
-      vhost_user="yes"
-      if test "$mingw32" = "yes"; then
-          error_exit "vhost-user isn't available on win32"
-      fi
+  --enable-vhost-user) vhost_user="yes"
+  ;;
+  --disable-vhost-kernel) vhost_kernel="no"
+  ;;
+  --enable-vhost-kernel) vhost_kernel="yes"
  ;;
  --disable-capstone) capstone="no"
  ;;
@@ -1512,14 +1505,6 @@ for opt do
  esac
 done

-if test "$vhost_user" = ""; then
-    if test "$mingw32" = "yes"; then
-        vhost_user="no"
-    else
-        vhost_user="yes"
-    fi
-fi
-
 case "$cpu" in
    ppc)
           CPU_CFLAGS="-m32"
@@ -1743,8 +1728,12 @@ disabled with --disable-FEATURE, default is enabled if available:
  linux-aio       Linux AIO support
  cap-ng          libcap-ng support
  attr            attr and xattr support
-  vhost-net       vhost-net acceleration support
-  vhost-crypto    vhost-crypto acceleration support
+  vhost-net       vhost-net kernel acceleration support
+  vhost-vsock     virtio sockets device support
+  vhost-scsi      vhost-scsi kernel target support
+  vhost-crypto    vhost-user-crypto backend support
+  vhost-kernel    vhost kernel backend support
+  vhost-user      vhost-user backend support
  spice           spice
  rbd             rados block device (rbd)
  libiscsi        iscsi support
@@ -1770,7 +1759,6 @@ disabled with --disable-FEATURE, default is enabled if available:
  jemalloc        jemalloc support
  avx2            AVX2 optimization support
  replication     replication support
-  vhost-vsock     virtio sockets device support
  opengl          opengl support
  virglrenderer   virgl rendering support
  xfsctl          xfsctl support
@@ -1787,7 +1775,6 @@ disabled with --disable-FEATURE, default is enabled if available:
  parallels       parallels image format support
  sheepdog        sheepdog block driver support
  crypto-afalg    Linux AF_ALG crypto backend driver
-  vhost-user      vhost-user support
  capstone        capstone disassembler support
  debug-mutex     mutex debugging support
  libpmem         libpmem support
@@ -2177,6 +2164,45 @@ else
  l2tpv3=no
 fi

+#########################################
+# vhost interdependencies and host support
+
+# vhost backends
+test "$vhost_user" = "" && vhost_user=yes
+if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then
+  error_exit "vhost-user isn't available on win32"
+fi
+test "$vhost_kernel" = "" && vhost_kernel=$linux
+if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then
+  error_exit "vhost-kernel is only available on Linux"
+fi
+
+# vhost-kernel devices
+test "$vhost_scsi" = "" && vhost_scsi=$vhost_kernel
+if test "$vhost_scsi" = "yes" && test "$vhost_kernel" != "yes"; then
+  error_exit "--enable-vhost-scsi requires --enable-vhost-kernel"
+fi
+test "$vhost_vsock" = "" && vhost_vsock=$vhost_kernel
+if test "$vhost_vsock" = "yes" && test "$vhost_kernel" != "yes"; then
+  error_exit "--enable-vhost-vsock requires --enable-vhost-kernel"
+fi
+
+# vhost-user backends
+test "$vhost_net_user" = "" && vhost_net_user=$vhost_user
+if test "$vhost_net_user" = "yes" && test "$vhost_user" = "no"; then
+  error_exit "--enable-vhost-net-user requires --enable-vhost-user"
+fi
+test "$vhost_crypto" = "" && vhost_crypto=$vhost_user
+if test "$vhost_crypto" = "yes" && test "$vhost_user" = "no"; then
+  error_exit "--enable-vhost-crypto requires --enable-vhost-user"
+fi
+
+# OR the vhost-kernel and vhost-user values for simplicity
+if test "$vhost_net" = ""; then
+  test "$vhost_net_user" = "yes" && vhost_net=yes
+  test "$vhost_kernel" = "yes" && vhost_net=yes
+fi
+
 ##########################################
 # MinGW / Mingw-w64 localtime_r/gmtime_r check

@@ -6622,8 +6648,11 @@ fi
 if test "$vhost_scsi" = "yes" ; then
  echo "CONFIG_VHOST_SCSI=y" >> $config_host_mak
 fi
-if test "$vhost_net" = "yes" && test "$vhost_user" = "yes"; then
-  echo "CONFIG_VHOST_NET_USED=y" >> $config_host_mak
+if test "$vhost_net" = "yes" ; then
+  echo "CONFIG_VHOST_NET=y" >> $config_host_mak
+fi
+if test "$vhost_net_user" = "yes" ; then
+  echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak
 fi
 if test "$vhost_crypto" = "yes" ; then
  echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak
@@ -6631,6 +6660,9 @@ fi
 if test "$vhost_vsock" = "yes" ; then
  echo "CONFIG_VHOST_VSOCK=y" >> $config_host_mak
 fi
+if test "$vhost_kernel" = "yes" ; then
+  echo "CONFIG_VHOST_KERNEL=y" >> $config_host_mak
+fi
 if test "$vhost_user" = "yes" ; then
  echo "CONFIG_VHOST_USER=y" >> $config_host_mak
 fi
@@ -7401,12 +7433,6 @@ if supported_xen_target $target; then
 fi
 if supported_kvm_target $target; then
    echo "CONFIG_KVM=y" >> $config_target_mak
-    if test "$vhost_net" = "yes" ; then
-        echo "CONFIG_VHOST_NET=y" >> $config_target_mak
-        if test "$vhost_user" = "yes" ; then
-            echo "CONFIG_VHOST_USER_NET_TEST_$target_name=y" >> $config_host_mak
-        fi
-    fi
 fi
 if supported_hax_target $target; then
    echo "CONFIG_HAX=y" >> $config_target_mak
@@ -1,5 +1,5 @@
-CONFIG_VHOST_USER_SCSI=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX))
-CONFIG_VHOST_USER_BLK=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX))
+CONFIG_VHOST_USER_SCSI=$(CONFIG_VHOST_USER)
+CONFIG_VHOST_USER_BLK=$(CONFIG_VHOST_USER)
 CONFIG_VIRTIO=y
 CONFIG_VIRTIO_9P=$(CONFIG_VIRTFS)
 CONFIG_VIRTIO_BALLOON=y
@@ -204,9 +204,7 @@ static MemoryRegion *pc_dimm_get_memory_region(PCDIMMDevice *dimm, Error **errp)

 static uint64_t pc_dimm_md_get_addr(const MemoryDeviceState *md)
 {
-    const PCDIMMDevice *dimm = PC_DIMM(md);
-
-    return dimm->addr;
+    return object_property_get_uint(OBJECT(md), PC_DIMM_ADDR_PROP, &error_abort);
 }

 static void pc_dimm_md_set_addr(MemoryDeviceState *md, uint64_t addr,
@@ -37,7 +37,9 @@ obj-$(CONFIG_PSERIES) += spapr_llan.o
 obj-$(CONFIG_XILINX_ETHLITE) += xilinx_ethlite.o

 obj-$(CONFIG_VIRTIO_NET) += virtio-net.o
-obj-y += vhost_net.o
+common-obj-$(call land,$(CONFIG_VIRTIO_NET),$(CONFIG_VHOST_NET)) += vhost_net.o
+common-obj-$(call lnot,$(call land,$(CONFIG_VIRTIO_NET),$(CONFIG_VHOST_NET))) += vhost_net-stub.o
+common-obj-$(CONFIG_ALL) += vhost_net-stub.o

 obj-$(CONFIG_ETSEC) += fsl_etsec/etsec.o fsl_etsec/registers.o \
 			fsl_etsec/rings.o fsl_etsec/miim.o
@@ -0,0 +1,92 @@
+/*
+ * vhost-net support
+ *
+ * Copyright Red Hat, Inc. 2010
+ *
+ * Authors:
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "net/net.h"
+#include "net/tap.h"
+#include "net/vhost-user.h"
+
+#include "hw/virtio/virtio-net.h"
+#include "net/vhost_net.h"
+#include "qemu/error-report.h"
+
+
+uint64_t vhost_net_get_max_queues(VHostNetState *net)
+{
+    return 1;
+}
+
+struct vhost_net *vhost_net_init(VhostNetOptions *options)
+{
+    error_report("vhost-net support is not compiled in");
+    return NULL;
+}
+
+int vhost_net_start(VirtIODevice *dev,
+                    NetClientState *ncs,
+                    int total_queues)
+{
+    return -ENOSYS;
+}
+void vhost_net_stop(VirtIODevice *dev,
+                    NetClientState *ncs,
+                    int total_queues)
+{
+}
+
+void vhost_net_cleanup(struct vhost_net *net)
+{
+}
+
+uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features)
+{
+    return features;
+}
+
+void vhost_net_ack_features(struct vhost_net *net, uint64_t features)
+{
+}
+
+uint64_t vhost_net_get_acked_features(VHostNetState *net)
+{
+    return 0;
+}
+
+bool vhost_net_virtqueue_pending(VHostNetState *net, int idx)
+{
+    return false;
+}
+
+void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
+                              int idx, bool mask)
+{
+}
+
+int vhost_net_notify_migration_done(struct vhost_net *net, char* mac_addr)
+{
+    return -1;
+}
+
+VHostNetState *get_vhost_net(NetClientState *nc)
+{
+    return 0;
+}
+
+int vhost_set_vring_enable(NetClientState *nc, int enable)
+{
+    return 0;
+}
+
+int vhost_net_set_mtu(struct vhost_net *net, uint16_t mtu)
+{
+    return 0;
+}
@@ -18,17 +18,13 @@
 #include "net/tap.h"
 #include "net/vhost-user.h"

+#include "standard-headers/linux/vhost_types.h"
 #include "hw/virtio/virtio-net.h"
 #include "net/vhost_net.h"
 #include "qemu/error-report.h"


-#ifdef CONFIG_VHOST_NET
-#include <linux/vhost.h>
 #include <sys/socket.h>
-#include <linux/kvm.h>
-#include <netpacket/packet.h>
-#include <net/ethernet.h>
 #include <net/if.h>
 #include <netinet/in.h>

@@ -136,7 +132,7 @@ static int vhost_net_get_fd(NetClientState *backend)
        return tap_get_fd(backend);
    default:
        fprintf(stderr, "vhost-net requires tap backend\n");
-        return -EBADFD;
+        return -ENOSYS;
    }
 }

@@ -194,6 +190,7 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options)
    }

    /* Set sane init value. Override when guest acks. */
+#ifdef CONFIG_VHOST_NET_USER
    if (net->nc->info->type == NET_CLIENT_DRIVER_VHOST_USER) {
        features = vhost_user_get_acked_features(net->nc);
        if (~net->dev.features & features) {
@@ -203,6 +200,7 @@ struct vhost_net *vhost_net_init(VhostNetOptions *options)
            goto fail;
        }
    }
+#endif

    vhost_net_ack_features(net, features);

@@ -414,10 +412,12 @@ VHostNetState *get_vhost_net(NetClientState *nc)
    case NET_CLIENT_DRIVER_TAP:
        vhost_net = tap_get_vhost_net(nc);
        break;
+#ifdef CONFIG_VHOST_NET_USER
    case NET_CLIENT_DRIVER_VHOST_USER:
        vhost_net = vhost_user_get_vhost_net(nc);
        assert(vhost_net);
        break;
+#endif
    default:
        break;
    }
@@ -449,76 +449,3 @@ int vhost_net_set_mtu(struct vhost_net *net, uint16_t mtu)

    return vhost_ops->vhost_net_set_mtu(&net->dev, mtu);
 }
-
-#else
-uint64_t vhost_net_get_max_queues(VHostNetState *net)
-{
-    return 1;
-}
-
-struct vhost_net *vhost_net_init(VhostNetOptions *options)
-{
-    error_report("vhost-net support is not compiled in");
-    return NULL;
-}
-
-int vhost_net_start(VirtIODevice *dev,
-                    NetClientState *ncs,
-                    int total_queues)
-{
-    return -ENOSYS;
-}
-void vhost_net_stop(VirtIODevice *dev,
-                    NetClientState *ncs,
-                    int total_queues)
-{
-}
-
-void vhost_net_cleanup(struct vhost_net *net)
-{
-}
-
-uint64_t vhost_net_get_features(struct vhost_net *net, uint64_t features)
-{
-    return features;
-}
-
-void vhost_net_ack_features(struct vhost_net *net, uint64_t features)
-{
-}
-
-uint64_t vhost_net_get_acked_features(VHostNetState *net)
-{
-    return 0;
-}
-
-bool vhost_net_virtqueue_pending(VHostNetState *net, int idx)
-{
-    return false;
-}
-
-void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
-                              int idx, bool mask)
-{
-}
-
-int vhost_net_notify_migration_done(struct vhost_net *net, char* mac_addr)
-{
-    return -1;
-}
-
-VHostNetState *get_vhost_net(NetClientState *nc)
-{
-    return 0;
-}
-
-int vhost_set_vring_enable(NetClientState *nc, int enable)
-{
-    return 0;
-}
-
-int vhost_net_set_mtu(struct vhost_net *net, uint16_t mtu)
-{
-    return 0;
-}
-#endif
@@ -834,9 +834,12 @@ void pcie_add_capability(PCIDevice *dev,
 /*
 * Sync the PCIe Link Status negotiated speed and width of a bridge with the
 * downstream device.  If downstream device is not present, re-write with the
- * Link Capability fields.  Limit width and speed to bridge capabilities for
- * compatibility.  Use config_read to access the downstream device since it
- * could be an assigned device with volatile link information.
+ * Link Capability fields.  If downstream device reports invalid width or
+ * speed, replace with minimum values (LnkSta fields are RsvdZ on VFs but such
+ * values interfere with PCIe native hotplug detecting new devices).  Limit
+ * width and speed to bridge capabilities for compatibility.  Use config_read
+ * to access the downstream device since it could be an assigned device with
+ * volatile link information.
 */
 void pcie_sync_bridge_lnk(PCIDevice *bridge_dev)
 {
@@ -856,11 +859,15 @@ void pcie_sync_bridge_lnk(PCIDevice *bridge_dev)
        if ((lnksta & PCI_EXP_LNKSTA_NLW) > (lnkcap & PCI_EXP_LNKCAP_MLW)) {
            lnksta &= ~PCI_EXP_LNKSTA_NLW;
            lnksta |= lnkcap & PCI_EXP_LNKCAP_MLW;
+        } else if (!(lnksta & PCI_EXP_LNKSTA_NLW)) {
+            lnksta |= QEMU_PCI_EXP_LNKSTA_NLW(QEMU_PCI_EXP_LNK_X1);
        }

        if ((lnksta & PCI_EXP_LNKSTA_CLS) > (lnkcap & PCI_EXP_LNKCAP_SLS)) {
            lnksta &= ~PCI_EXP_LNKSTA_CLS;
            lnksta |= lnkcap & PCI_EXP_LNKCAP_SLS;
+        } else if (!(lnksta & PCI_EXP_LNKSTA_CLS)) {
+            lnksta |= QEMU_PCI_EXP_LNKSTA_CLS(QEMU_PCI_EXP_LNK_2_5GT);
        }
    }

@@ -563,6 +563,7 @@ static void smbios_build_type_3_table(void)
    t->height = 0;
    t->number_of_power_cords = 0;
    t->contained_element_count = 0;
+    t->contained_element_record_length = 0;
    SMBIOS_TABLE_SET_STR(3, sku_number_str, type3.sku);

    SMBIOS_BUILD_TABLE_POST;
@@ -526,8 +526,6 @@ static void vfio_probe_ati_bar2_quirk(VFIOPCIDevice *vdev, int nr)
 * note it for future reference.
 */

-#define PCI_VENDOR_ID_NVIDIA                    0x10de
-
 /*
 * Nvidia has several different methods to get to config space, the
 * nouveu project has several of these documented here:
@@ -2,15 +2,18 @@ ifeq ($(CONFIG_VIRTIO),y)
 common-obj-y += virtio-bus.o
 obj-y += virtio.o

+obj-$(call lor,$(CONFIG_VHOST_USER),$(CONFIG_VHOST_KERNEL)) += vhost.o vhost-backend.o
+common-obj-$(call lnot,$(call lor,$(CONFIG_VHOST_USER),$(CONFIG_VHOST_KERNEL))) += vhost-stub.o
+obj-$(CONFIG_VHOST_USER) += vhost-user.o
+
 common-obj-$(CONFIG_VIRTIO_RNG) += virtio-rng.o
 common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
 common-obj-$(CONFIG_VIRTIO_MMIO) += virtio-mmio.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio-balloon.o
 obj-$(CONFIG_VIRTIO_CRYPTO) += virtio-crypto.o
 obj-$(call land,$(CONFIG_VIRTIO_CRYPTO),$(CONFIG_VIRTIO_PCI)) += virtio-crypto-pci.o
-
-obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o
 obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o
+
 ifeq ($(CONFIG_VIRTIO_PCI),y)
 obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o
 obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk-pci.o
@@ -28,5 +31,4 @@ obj-$(CONFIG_VIRTIO_SERIAL) += virtio-serial-pci.o
 endif
 endif

-common-obj-$(call lnot,$(call land,$(CONFIG_VIRTIO),$(CONFIG_LINUX))) += vhost-stub.o
 common-obj-$(CONFIG_ALL) += vhost-stub.o
@@ -9,11 +9,14 @@
 */

 #include "qemu/osdep.h"
-#include <linux/vhost.h>
-#include <sys/ioctl.h>
 #include "hw/virtio/vhost.h"
 #include "hw/virtio/vhost-backend.h"
 #include "qemu/error-report.h"
+#include "standard-headers/linux/vhost_types.h"
+
+#ifdef CONFIG_VHOST_KERNEL
+#include <linux/vhost.h>
+#include <sys/ioctl.h>

 static int vhost_kernel_call(struct vhost_dev *dev, unsigned long int request,
                             void *arg)
@@ -265,18 +268,23 @@ static const VhostOps kernel_ops = {
        .vhost_set_iotlb_callback = vhost_kernel_set_iotlb_callback,
        .vhost_send_device_iotlb_msg = vhost_kernel_send_device_iotlb_msg,
 };
+#endif

 int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
 {
    int r = 0;

    switch (backend_type) {
+#ifdef CONFIG_VHOST_KERNEL
    case VHOST_BACKEND_TYPE_KERNEL:
        dev->vhost_ops = &kernel_ops;
        break;
+#endif
+#ifdef CONFIG_VHOST_USER
    case VHOST_BACKEND_TYPE_USER:
        dev->vhost_ops = &user_ops;
        break;
+#endif
    default:
        error_report("Unknown vhost backend type");
        r = -1;
@@ -27,8 +27,12 @@
 #include <sys/ioctl.h>
 #include <sys/socket.h>
 #include <sys/un.h>
-#include <linux/vhost.h>
+
+#include "standard-headers/linux/vhost_types.h"
+
+#ifdef CONFIG_LINUX
 #include <linux/userfaultfd.h>
+#endif

 #define VHOST_MEMORY_MAX_NREGIONS    8
 #define VHOST_USER_F_PROTOCOL_FEATURES 30
@@ -1110,6 +1114,7 @@ out:
    return ret;
 }

+#ifdef CONFIG_LINUX
 /*
 * Called back from the postcopy fault thread when a fault is received on our
 * ufd.
@@ -1177,6 +1182,7 @@ static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
    trace_vhost_user_postcopy_waker_nomatch(qemu_ram_get_idstr(rb), offset);
    return 0;
 }
+#endif

 /*
 * Called at the start of an inbound postcopy on reception of the
@@ -1184,6 +1190,7 @@ static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
 */
 static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
 {
+#ifdef CONFIG_LINUX
    struct vhost_user *u = dev->opaque;
    CharBackend *chr = u->user->chr;
    int ufd;
@@ -1227,6 +1234,10 @@ static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
    u->postcopy_fd.idstr = "vhost-user"; /* Need to find unique name */
    postcopy_register_shared_ufd(&u->postcopy_fd);
    return 0;
+#else
+    error_setg(errp, "Postcopy not supported on non-Linux systems");
+    return -1;
+#endif
 }

 /*
@@ -21,7 +21,7 @@
 #include "qemu/range.h"
 #include "qemu/error-report.h"
 #include "qemu/memfd.h"
-#include <linux/vhost.h>
+#include "standard-headers/linux/vhost_types.h"
 #include "exec/address-spaces.h"
 #include "hw/virtio/virtio-bus.h"
 #include "hw/virtio/virtio-access.h"
@@ -33,11 +33,81 @@

 #define BALLOON_PAGE_SIZE  (1 << VIRTIO_BALLOON_PFN_SHIFT)

-static void balloon_page(void *addr, int deflate)
+struct PartiallyBalloonedPage {
+    RAMBlock *rb;
+    ram_addr_t base;
+    unsigned long bitmap[];
+};
+
+static void balloon_inflate_page(VirtIOBalloon *balloon,
+                                 MemoryRegion *mr, hwaddr offset)
 {
-    if (!qemu_balloon_is_inhibited()) {
-        qemu_madvise(addr, BALLOON_PAGE_SIZE,
-                deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
+    void *addr = memory_region_get_ram_ptr(mr) + offset;
+    RAMBlock *rb;
+    size_t rb_page_size;
+    int subpages;
+    ram_addr_t ram_offset, host_page_base;
+
+    /* XXX is there a better way to get to the RAMBlock than via a
+     * host address? */
+    rb = qemu_ram_block_from_host(addr, false, &ram_offset);
+    rb_page_size = qemu_ram_pagesize(rb);
+    host_page_base = ram_offset & ~(rb_page_size - 1);
+
+    if (rb_page_size == BALLOON_PAGE_SIZE) {
+        /* Easy case */
+
+        ram_block_discard_range(rb, ram_offset, rb_page_size);
+        /* We ignore errors from ram_block_discard_range(), because it
+         * has already reported them, and failing to discard a balloon
+         * page is not fatal */
+        return;
+    }
+
+    /* Hard case
+     *
+     * We've put a piece of a larger host page into the balloon - we
+     * need to keep track until we have a whole host page to
+     * discard
+     */
+    warn_report_once(
+"Balloon used with backing page size > 4kiB, this may not be reliable");
+
+    subpages = rb_page_size / BALLOON_PAGE_SIZE;
+
+    if (balloon->pbp
+        && (rb != balloon->pbp->rb
+            || host_page_base != balloon->pbp->base)) {
+        /* We've partially ballooned part of a host page, but now
+         * we're trying to balloon part of a different one.  Too hard,
+         * give up on the old partial page */
+        free(balloon->pbp);
+        balloon->pbp = NULL;
+    }
+
+    if (!balloon->pbp) {
+        /* Starting on a new host page */
+        size_t bitlen = BITS_TO_LONGS(subpages) * sizeof(unsigned long);
+        balloon->pbp = g_malloc0(sizeof(PartiallyBalloonedPage) + bitlen);
+        balloon->pbp->rb = rb;
+        balloon->pbp->base = host_page_base;
+    }
+
+    bitmap_set(balloon->pbp->bitmap,
+               (ram_offset - balloon->pbp->base) / BALLOON_PAGE_SIZE,
+               subpages);
+
+    if (bitmap_full(balloon->pbp->bitmap, subpages)) {
+        /* We've accumulated a full host page, we can actually discard
+         * it now */
+
+        ram_block_discard_range(rb, balloon->pbp->base, rb_page_size);
+        /* We ignore errors from ram_block_discard_range(), because it
+         * has already reported them, and failing to discard a balloon
+         * page is not fatal */
+
+        free(balloon->pbp);
+        balloon->pbp = NULL;
    }
 }

@@ -222,17 +292,19 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
        }

        while (iov_to_buf(elem->out_sg, elem->out_num, offset, &pfn, 4) == 4) {
-            ram_addr_t pa;
-            ram_addr_t addr;
+            hwaddr pa;
            int p = virtio_ldl_p(vdev, &pfn);

-            pa = (ram_addr_t) p << VIRTIO_BALLOON_PFN_SHIFT;
+            pa = (hwaddr) p << VIRTIO_BALLOON_PFN_SHIFT;
            offset += 4;

-            /* FIXME: remove get_system_memory(), but how? */
-            section = memory_region_find(get_system_memory(), pa, 1);
-            if (!int128_nz(section.size) ||
-                !memory_region_is_ram(section.mr) ||
+            section = memory_region_find(get_system_memory(), pa,
+                                         BALLOON_PAGE_SIZE);
+            if (!section.mr) {
+                trace_virtio_balloon_bad_addr(pa);
+                continue;
+            }
+            if (!memory_region_is_ram(section.mr) ||
                memory_region_is_rom(section.mr) ||
                memory_region_is_romd(section.mr)) {
                trace_virtio_balloon_bad_addr(pa);
@@ -242,11 +314,9 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)

            trace_virtio_balloon_handle_output(memory_region_name(section.mr),
                                               pa);
-            /* Using memory_region_get_ram_ptr is bending the rules a bit, but
-               should be OK because we only want a single page.  */
-            addr = section.offset_within_region;
-            balloon_page(memory_region_get_ram_ptr(section.mr) + addr,
-                         !!(vq == s->dvq));
+            if (!qemu_balloon_is_inhibited() && vq != s->dvq) {
+                balloon_inflate_page(s, section.mr, section.offset_within_region);
+            }
            memory_region_unref(section.mr);
        }

@@ -86,7 +86,6 @@
 #pragma GCC poison CONFIG_XTENSA_DIS

 #pragma GCC poison CONFIG_LINUX_USER
-#pragma GCC poison CONFIG_VHOST_NET
 #pragma GCC poison CONFIG_KVM
 #pragma GCC poison CONFIG_SOFTMMU

@@ -162,6 +162,7 @@ struct smbios_type_3 {
    uint8_t height;
    uint8_t number_of_power_cords;
    uint8_t contained_element_count;
+    uint8_t contained_element_record_length;
    uint8_t sku_number_str;
    /* contained elements follow */
 } QEMU_PACKED;
@@ -271,4 +271,6 @@

 #define PCI_VENDOR_ID_SYNOPSYS           0x16C3

+#define PCI_VENDOR_ID_NVIDIA             0x10de
+
 #endif
--- a/Show More
+++ b/Show More