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

virtio,acpi: features, fixes, cleanups.

vdpa support
virtio-mem support
a handy script for disassembling acpi tables
misc fixes and cleanups

Signed-off-by: Michael S. Tsirkin <[email protected]>

# gpg: Signature made Tue 07 Jul 2020 13:00:35 BST
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "[email protected]"
# gpg: Good signature from "Michael S. Tsirkin <[email protected]>" [full]
# gpg:                 aka "Michael S. Tsirkin <[email protected]>" [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: (41 commits)
  vhost-vdpa: introduce vhost-vdpa net client
  vhost-vdpa: introduce vhost-vdpa backend
  vhost_net: introduce set_config & get_config
  vhost: implement vhost_force_iommu method
  vhost: introduce new VhostOps vhost_force_iommu
  vhost: implement vhost_vq_get_addr method
  vhost: introduce new VhostOps vhost_vq_get_addr
  vhost: implement vhost_dev_start method
  vhost: introduce new VhostOps vhost_dev_start
  vhost: check the existence of vhost_set_iotlb_callback
  virtio-pci: implement queue_enabled method
  virtio-bus: introduce queue_enabled method
  vhost_net: use the function qemu_get_peer
  net: introduce qemu_get_peer
  MAINTAINERS: add VT-d entry
  docs: vhost-user: add Virtio status protocol feature
  tests/acpi: remove stale allowed tables
  numa: Auto-enable NUMA when any memory devices are possible
  virtio-mem: Exclude unplugged memory during migration
  virtio-mem: Add trace events
  ...

Signed-off-by: Peter Maydell <[email protected]>

# Conflicts:
#	hw/arm/virt.c
#	hw/virtio/trace-events

Author: pm215

MAINTAINERS

@@ -1792,6 +1792,15 @@ F: hw/virtio/virtio-crypto.c
 F: hw/virtio/virtio-crypto-pci.c
 F: include/hw/virtio/virtio-crypto.h
 
+virtio-mem
+M: David Hildenbrand <[email protected]>
+S: Supported
+W: https://virtio-mem.gitlab.io/
+F: hw/virtio/virtio-mem.c
+F: hw/virtio/virtio-mem-pci.h
+F: hw/virtio/virtio-mem-pci.c
+F: include/hw/virtio/virtio-mem.h
+
 nvme
 M: Keith Busch <[email protected]>
 L: [email protected]
@@ -2617,6 +2626,15 @@ F: tests/uefi-test-tools/
 F: .gitlab-ci.d/edk2.yml
 F: .gitlab-ci.d/edk2/
 
+VT-d Emulation
+M: Michael S. Tsirkin <[email protected]>
+M: Peter Xu <[email protected]>
+R: Jason Wang <[email protected]>
+S: Supported
+F: hw/i386/intel_iommu.c
+F: hw/i386/intel_iommu_internal.h
+F: include/hw/i386/intel_iommu.h
+
 Usermode Emulation
 ------------------
 Overall usermode emulation

accel/kvm/kvm-all.c

@@ -40,7 +40,6 @@
 #include "trace.h"
 #include "hw/irq.h"
 #include "sysemu/sev.h"
-#include "sysemu/balloon.h"
 #include "qapi/visitor.h"
 #include "qapi/qapi-types-common.h"
 #include "qapi/qapi-visit-common.h"
@@ -2229,7 +2228,8 @@ static int kvm_init(MachineState *ms)
 
     s->sync_mmu = !!kvm_vm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
     if (!s->sync_mmu) {
-        qemu_balloon_inhibit(true);
+        ret = ram_block_discard_disable(true);
+        assert(!ret);
     }
 
     return 0;

balloon.c

@@ -36,23 +36,6 @@
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
 static void *balloon_opaque;
-static int balloon_inhibit_count;
-
-bool qemu_balloon_is_inhibited(void)
-{
-    return atomic_read(&balloon_inhibit_count) > 0;
-}
-
-void qemu_balloon_inhibit(bool state)
-{
-    if (state) {
-        atomic_inc(&balloon_inhibit_count);
-    } else {
-        atomic_dec(&balloon_inhibit_count);
-    }
-
-    assert(atomic_read(&balloon_inhibit_count) >= 0);
-}
 
 static bool have_balloon(Error **errp)
 {

configure

@@ -1575,6 +1575,10 @@ for opt do
   ;;
   --enable-vhost-user) vhost_user="yes"
   ;;
+  --disable-vhost-vdpa) vhost_vdpa="no"
+  ;;
+  --enable-vhost-vdpa) vhost_vdpa="yes"
+  ;;
   --disable-vhost-kernel) vhost_kernel="no"
   ;;
   --enable-vhost-kernel) vhost_kernel="yes"
@@ -1883,6 +1887,7 @@ disabled with --disable-FEATURE, default is enabled if available:
   vhost-crypto    vhost-user-crypto backend support
   vhost-kernel    vhost kernel backend support
   vhost-user      vhost-user backend support
+  vhost-vdpa      vhost-vdpa kernel backend support
   spice           spice
   rbd             rados block device (rbd)
   libiscsi        iscsi support
@@ -2394,6 +2399,10 @@ 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_vdpa" = "" && vhost_vdpa=$linux
+if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then
+  error_exit "vhost-vdpa is only available on Linux"
+fi
 test "$vhost_kernel" = "" && vhost_kernel=$linux
 if test "$vhost_kernel" = "yes" && test "$linux" != "yes"; then
   error_exit "vhost-kernel is only available on Linux"
@@ -2422,6 +2431,11 @@ test "$vhost_user_fs" = "" && vhost_user_fs=$vhost_user
 if test "$vhost_user_fs" = "yes" && test "$vhost_user" = "no"; then
   error_exit "--enable-vhost-user-fs requires --enable-vhost-user"
 fi
+#vhost-vdpa backends
+test "$vhost_net_vdpa" = "" && vhost_net_vdpa=$vhost_vdpa
+if test "$vhost_net_vdpa" = "yes" && test "$vhost_vdpa" = "no"; then
+  error_exit "--enable-vhost-net-vdpa requires --enable-vhost-vdpa"
+fi
 
 # OR the vhost-kernel and vhost-user values for simplicity
 if test "$vhost_net" = ""; then
@@ -6947,6 +6961,7 @@ echo "vhost-scsi support $vhost_scsi"
 echo "vhost-vsock support $vhost_vsock"
 echo "vhost-user support $vhost_user"
 echo "vhost-user-fs support $vhost_user_fs"
+echo "vhost-vdpa support $vhost_vdpa"
 echo "Trace backends    $trace_backends"
 if have_backend "simple"; then
 echo "Trace output file $trace_file-<pid>"
@@ -7454,6 +7469,9 @@ fi
 if test "$vhost_net_user" = "yes" ; then
   echo "CONFIG_VHOST_NET_USER=y" >> $config_host_mak
 fi
+if test "$vhost_net_vdpa" = "yes" ; then
+  echo "CONFIG_VHOST_NET_VDPA=y" >> $config_host_mak
+fi
 if test "$vhost_crypto" = "yes" ; then
   echo "CONFIG_VHOST_CRYPTO=y" >> $config_host_mak
 fi
@@ -7469,6 +7487,9 @@ fi
 if test "$vhost_user" = "yes" ; then
   echo "CONFIG_VHOST_USER=y" >> $config_host_mak
 fi
+if test "$vhost_vdpa" = "yes" ; then
+  echo "CONFIG_VHOST_VDPA=y" >> $config_host_mak
+fi
 if test "$vhost_user_fs" = "yes" ; then
   echo "CONFIG_VHOST_USER_FS=y" >> $config_host_mak
 fi

docs/interop/index.rst

@@ -20,3 +20,4 @@ Contents:
    qemu-ga
    vhost-user
    vhost-user-gpu
+   vhost-vdpa

docs/interop/vhost-user.rst

@@ -816,6 +816,7 @@ Protocol features
   #define VHOST_USER_PROTOCOL_F_RESET_DEVICE         13
   #define VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS 14
   #define VHOST_USER_PROTOCOL_F_CONFIGURE_MEM_SLOTS  15
+  #define VHOST_USER_PROTOCOL_F_STATUS               16
 
 Master message types
 --------------------
@@ -1307,6 +1308,29 @@ Master message types
   ``VHOST_USER_ADD_MEM_REG`` message, this message is used to set and
   update the memory tables of the slave device.
 
+``VHOST_USER_SET_STATUS``
+  :id: 39
+  :equivalent ioctl: VHOST_VDPA_SET_STATUS
+  :slave payload: N/A
+  :master payload: ``u64``
+
+  When the ``VHOST_USER_PROTOCOL_F_STATUS`` protocol feature has been
+  successfully negotiated, this message is submitted by the master to
+  notify the backend with updated device status as defined in the Virtio
+  specification.
+
+``VHOST_USER_GET_STATUS``
+  :id: 40
+  :equivalent ioctl: VHOST_VDPA_GET_STATUS
+  :slave payload: ``u64``
+  :master payload: N/A
+
+  When the ``VHOST_USER_PROTOCOL_F_STATUS`` protocol feature has been
+  successfully negotiated, this message is submitted by the master to
+  query the backend for its device status as defined in the Virtio
+  specification.
+
+
 Slave message types
 -------------------
 

docs/interop/vhost-vdpa.rst

@@ -0,0 +1,17 @@
+=====================
+Vhost-vdpa Protocol
+=====================
+
+Introduction
+=============
+vDPA(Virtual data path acceleration) device is a device that uses
+a datapath which complies with the virtio specifications with vendor
+specific control path. vDPA devices can be both physically located on
+the hardware or emulated by software.
+
+This document describes the vDPA support in qemu
+
+Here is the kernel commit here
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4c8cf31885f69e86be0b5b9e6677a26797365e1d
+
+TODO : More information will add later

exec.c

@@ -4115,4 +4115,56 @@ void mtree_print_dispatch(AddressSpaceDispatch *d, MemoryRegion *root)
     }
 }
 
+/*
+ * If positive, discarding RAM is disabled. If negative, discarding RAM is
+ * required to work and cannot be disabled.
+ */
+static int ram_block_discard_disabled;
+
+int ram_block_discard_disable(bool state)
+{
+    int old;
+
+    if (!state) {
+        atomic_dec(&ram_block_discard_disabled);
+        return 0;
+    }
+
+    do {
+        old = atomic_read(&ram_block_discard_disabled);
+        if (old < 0) {
+            return -EBUSY;
+        }
+    } while (atomic_cmpxchg(&ram_block_discard_disabled, old, old + 1) != old);
+    return 0;
+}
+
+int ram_block_discard_require(bool state)
+{
+    int old;
+
+    if (!state) {
+        atomic_inc(&ram_block_discard_disabled);
+        return 0;
+    }
+
+    do {
+        old = atomic_read(&ram_block_discard_disabled);
+        if (old > 0) {
+            return -EBUSY;
+        }
+    } while (atomic_cmpxchg(&ram_block_discard_disabled, old, old - 1) != old);
+    return 0;
+}
+
+bool ram_block_discard_is_disabled(void)
+{
+    return atomic_read(&ram_block_discard_disabled) > 0;
+}
+
+bool ram_block_discard_is_required(void)
+{
+    return atomic_read(&ram_block_discard_disabled) < 0;
+}
+
 #endif

hw/arm/virt.c

@@ -2401,6 +2401,7 @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
     hc->unplug = virt_machine_device_unplug_cb;
     mc->nvdimm_supported = true;
     mc->auto_enable_numa_with_memhp = true;
+    mc->auto_enable_numa_with_memdev = true;
     mc->default_ram_id = "mach-virt.ram";
 
     object_class_property_add(oc, "acpi", "OnOffAuto",
@@ -2516,6 +2517,7 @@ static void virt_machine_5_0_options(MachineClass *mc)
     compat_props_add(mc->compat_props, hw_compat_5_0, hw_compat_5_0_len);
     mc->numa_mem_supported = true;
     vmc->acpi_expose_flash = true;
+    mc->auto_enable_numa_with_memdev = false;
 }
 DEFINE_VIRT_MACHINE(5, 0)
 

hw/core/numa.c

@@ -688,8 +688,9 @@ void numa_complete_configuration(MachineState *ms)
     NodeInfo *numa_info = ms->numa_state->nodes;
 
     /*
-     * If memory hotplug is enabled (slots > 0) but without '-numa'
-     * options explicitly on CLI, guestes will break.
+     * If memory hotplug is enabled (slot > 0) or memory devices are enabled
+     * (ms->maxram_size > ram_size) but without '-numa' options explicitly on
+     * CLI, guests will break.
      *
      *   Windows: won't enable memory hotplug without SRAT table at all
      *
@@ -704,9 +705,9 @@ void numa_complete_configuration(MachineState *ms)
      * assume there is just one node with whole RAM.
      */
     if (ms->numa_state->num_nodes == 0 &&
-        ((ms->ram_slots > 0 &&
-        mc->auto_enable_numa_with_memhp) ||
-        mc->auto_enable_numa)) {
+        ((ms->ram_slots && mc->auto_enable_numa_with_memhp) ||
+         (ms->maxram_size > ms->ram_size && mc->auto_enable_numa_with_memdev) ||
+         mc->auto_enable_numa)) {
             NumaNodeOptions node = { };
             parse_numa_node(ms, &node, &error_abort);
             numa_info[0].node_mem = ram_size;
@@ -824,6 +825,7 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[])
     MemoryDeviceInfoList *info;
     PCDIMMDeviceInfo     *pcdimm_info;
     VirtioPMEMDeviceInfo *vpi;
+    VirtioMEMDeviceInfo *vmi;
 
     for (info = info_list; info; info = info->next) {
         MemoryDeviceInfo *value = info->value;
@@ -844,6 +846,11 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[])
                 node_mem[0].node_mem += vpi->size;
                 node_mem[0].node_plugged_mem += vpi->size;
                 break;
+            case MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM:
+                vmi = value->u.virtio_mem.data;
+                node_mem[vmi->node].node_mem += vmi->size;
+                node_mem[vmi->node].node_plugged_mem += vmi->size;
+                break;
             default:
                 g_assert_not_reached();
             }