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 <mst@redhat.com>

# gpg: Signature made Tue 07 Jul 2020 13:00:35 BST
# gpg:                using RSA key 5D09FD0871C8F85B94CA8A0D281F0DB8D28D5469
# gpg:                issuer "mst@redhat.com"
# 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: (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 <peter.maydell@linaro.org>

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

include/exec/memory.h

@@ -2478,6 +2478,47 @@ static inline MemOp devend_memop(enum device_endian end)
 }
 #endif
 
+/*
+ * Inhibit technologies that require discarding of pages in RAM blocks, e.g.,
+ * to manage the actual amount of memory consumed by the VM (then, the memory
+ * provided by RAM blocks might be bigger than the desired memory consumption).
+ * This *must* be set if:
+ * - Discarding parts of a RAM blocks does not result in the change being
+ *   reflected in the VM and the pages getting freed.
+ * - All memory in RAM blocks is pinned or duplicated, invaldiating any previous
+ *   discards blindly.
+ * - Discarding parts of a RAM blocks will result in integrity issues (e.g.,
+ *   encrypted VMs).
+ * Technologies that only temporarily pin the current working set of a
+ * driver are fine, because we don't expect such pages to be discarded
+ * (esp. based on guest action like balloon inflation).
+ *
+ * This is *not* to be used to protect from concurrent discards (esp.,
+ * postcopy).
+ *
+ * Returns 0 if successful. Returns -EBUSY if a technology that relies on
+ * discards to work reliably is active.
+ */
+int ram_block_discard_disable(bool state);
+
+/*
+ * Inhibit technologies that disable discarding of pages in RAM blocks.
+ *
+ * Returns 0 if successful. Returns -EBUSY if discards are already set to
+ * broken.
+ */
+int ram_block_discard_require(bool state);
+
+/*
+ * Test if discarding of memory in ram blocks is disabled.
+ */
+bool ram_block_discard_is_disabled(void);
+
+/*
+ * Test if discarding of memory in ram blocks is required to work reliably.
+ */
+bool ram_block_discard_is_required(void);
+
 #endif
 
 #endif

include/hw/boards.h

@@ -207,6 +207,7 @@ struct MachineClass {
     const char **valid_cpu_types;
     strList *allowed_dynamic_sysbus_devices;
     bool auto_enable_numa_with_memhp;
+    bool auto_enable_numa_with_memdev;
     void (*numa_auto_assign_ram)(MachineClass *mc, NodeInfo *nodes,
                                  int nb_nodes, ram_addr_t size);
     bool ignore_boot_device_suffixes;

include/hw/pci/pci.h

@@ -87,6 +87,7 @@ extern bool pci_available;
 #define PCI_DEVICE_ID_VIRTIO_VSOCK       0x1012
 #define PCI_DEVICE_ID_VIRTIO_PMEM        0x1013
 #define PCI_DEVICE_ID_VIRTIO_IOMMU       0x1014
+#define PCI_DEVICE_ID_VIRTIO_MEM         0x1015
 
 #define PCI_VENDOR_ID_REDHAT             0x1b36
 #define PCI_DEVICE_ID_REDHAT_BRIDGE      0x0001

include/hw/vfio/vfio-common.h

@@ -108,7 +108,7 @@ typedef struct VFIODevice {
     bool reset_works;
     bool needs_reset;
     bool no_mmap;
-    bool balloon_allowed;
+    bool ram_block_discard_allowed;
     VFIODeviceOps *ops;
     unsigned int num_irqs;
     unsigned int num_regions;
@@ -128,7 +128,7 @@ typedef struct VFIOGroup {
     QLIST_HEAD(, VFIODevice) device_list;
     QLIST_ENTRY(VFIOGroup) next;
     QLIST_ENTRY(VFIOGroup) container_next;
-    bool balloon_allowed;
+    bool ram_block_discard_allowed;
 } VFIOGroup;
 
 typedef struct VFIODMABuf {

include/hw/virtio/vhost-backend.h

@@ -17,7 +17,8 @@ typedef enum VhostBackendType {
     VHOST_BACKEND_TYPE_NONE = 0,
     VHOST_BACKEND_TYPE_KERNEL = 1,
     VHOST_BACKEND_TYPE_USER = 2,
-    VHOST_BACKEND_TYPE_MAX = 3,
+    VHOST_BACKEND_TYPE_VDPA = 3,
+    VHOST_BACKEND_TYPE_MAX = 4,
 } VhostBackendType;
 
 typedef enum VhostSetConfigType {
@@ -34,6 +35,7 @@ struct vhost_vring_state;
 struct vhost_vring_addr;
 struct vhost_scsi_target;
 struct vhost_iotlb_msg;
+struct vhost_virtqueue;
 
 typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque);
 typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);
@@ -112,6 +114,16 @@ typedef int (*vhost_get_inflight_fd_op)(struct vhost_dev *dev,
 typedef int (*vhost_set_inflight_fd_op)(struct vhost_dev *dev,
                                         struct vhost_inflight *inflight);
 
+typedef int (*vhost_dev_start_op)(struct vhost_dev *dev, bool started);
+
+typedef int (*vhost_vq_get_addr_op)(struct vhost_dev *dev,
+                    struct vhost_vring_addr *addr,
+                    struct vhost_virtqueue *vq);
+
+typedef int (*vhost_get_device_id_op)(struct vhost_dev *dev, uint32_t *dev_id);
+
+typedef bool (*vhost_force_iommu_op)(struct vhost_dev *dev);
+
 typedef struct VhostOps {
     VhostBackendType backend_type;
     vhost_backend_init vhost_backend_init;
@@ -152,9 +164,14 @@ typedef struct VhostOps {
     vhost_backend_mem_section_filter_op vhost_backend_mem_section_filter;
     vhost_get_inflight_fd_op vhost_get_inflight_fd;
     vhost_set_inflight_fd_op vhost_set_inflight_fd;
+    vhost_dev_start_op vhost_dev_start;
+    vhost_vq_get_addr_op  vhost_vq_get_addr;
+    vhost_get_device_id_op vhost_get_device_id;
+    vhost_force_iommu_op vhost_force_iommu;
 } VhostOps;
 
 extern const VhostOps user_ops;
+extern const VhostOps vdpa_ops;
 
 int vhost_set_backend_type(struct vhost_dev *dev,
                            VhostBackendType backend_type);

include/hw/virtio/vhost-vdpa.h

@@ -0,0 +1,26 @@
+/*
+ * vhost-vdpa.h
+ *
+ * Copyright(c) 2017-2018 Intel Corporation.
+ * Copyright(c) 2020 Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef HW_VIRTIO_VHOST_VDPA_H
+#define HW_VIRTIO_VHOST_VDPA_H
+
+#include "hw/virtio/virtio.h"
+
+typedef struct vhost_vdpa {
+    int device_fd;
+    uint32_t msg_type;
+    MemoryListener listener;
+} VhostVDPA;
+
+extern AddressSpace address_space_memory;
+extern int vhost_vdpa_get_device_id(struct vhost_dev *dev,
+                                   uint32_t *device_id);
+#endif

include/hw/virtio/vhost.h

@@ -92,6 +92,13 @@ struct vhost_dev {
     const VhostDevConfigOps *config_ops;
 };
 
+struct vhost_net {
+    struct vhost_dev dev;
+    struct vhost_virtqueue vqs[2];
+    int backend;
+    NetClientState *nc;
+};
+
 int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
                    VhostBackendType backend_type,
                    uint32_t busyloop_timeout);

include/hw/virtio/virtio-bus.h

@@ -83,6 +83,10 @@ typedef struct VirtioBusClass {
      */
     int (*ioeventfd_assign)(DeviceState *d, EventNotifier *notifier,
                             int n, bool assign);
+    /*
+     * Whether queue number n is enabled.
+     */
+    bool (*queue_enabled)(DeviceState *d, int n);
     /*
      * Does the transport have variable vring alignment?
      * (ie can it ever call virtio_queue_set_align()?)

include/hw/virtio/virtio-mem.h

@@ -0,0 +1,86 @@
+/*
+ * Virtio MEM device
+ *
+ * Copyright (C) 2020 Red Hat, Inc.
+ *
+ * Authors:
+ *  David Hildenbrand <david@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef HW_VIRTIO_MEM_H
+#define HW_VIRTIO_MEM_H
+
+#include "standard-headers/linux/virtio_mem.h"
+#include "hw/virtio/virtio.h"
+#include "qapi/qapi-types-misc.h"
+#include "sysemu/hostmem.h"
+
+#define TYPE_VIRTIO_MEM "virtio-mem"
+
+#define VIRTIO_MEM(obj) \
+        OBJECT_CHECK(VirtIOMEM, (obj), TYPE_VIRTIO_MEM)
+#define VIRTIO_MEM_CLASS(oc) \
+        OBJECT_CLASS_CHECK(VirtIOMEMClass, (oc), TYPE_VIRTIO_MEM)
+#define VIRTIO_MEM_GET_CLASS(obj) \
+        OBJECT_GET_CLASS(VirtIOMEMClass, (obj), TYPE_VIRTIO_MEM)
+
+#define VIRTIO_MEM_MEMDEV_PROP "memdev"
+#define VIRTIO_MEM_NODE_PROP "node"
+#define VIRTIO_MEM_SIZE_PROP "size"
+#define VIRTIO_MEM_REQUESTED_SIZE_PROP "requested-size"
+#define VIRTIO_MEM_BLOCK_SIZE_PROP "block-size"
+#define VIRTIO_MEM_ADDR_PROP "memaddr"
+
+typedef struct VirtIOMEM {
+    VirtIODevice parent_obj;
+
+    /* guest -> host request queue */
+    VirtQueue *vq;
+
+    /* bitmap used to track unplugged memory */
+    int32_t bitmap_size;
+    unsigned long *bitmap;
+
+    /* assigned memory backend and memory region */
+    HostMemoryBackend *memdev;
+
+    /* NUMA node */
+    uint32_t node;
+
+    /* assigned address of the region in guest physical memory */
+    uint64_t addr;
+
+    /* usable region size (<= region_size) */
+    uint64_t usable_region_size;
+
+    /* actual size (how much the guest plugged) */
+    uint64_t size;
+
+    /* requested size */
+    uint64_t requested_size;
+
+    /* block size and alignment */
+    uint64_t block_size;
+
+    /* notifiers to notify when "size" changes */
+    NotifierList size_change_notifiers;
+
+    /* don't migrate unplugged memory */
+    NotifierWithReturn precopy_notifier;
+} VirtIOMEM;
+
+typedef struct VirtIOMEMClass {
+    /* private */
+    VirtIODevice parent;
+
+    /* public */
+    void (*fill_device_info)(const VirtIOMEM *vmen, VirtioMEMDeviceInfo *vi);
+    MemoryRegion *(*get_memory_region)(VirtIOMEM *vmem, Error **errp);
+    void (*add_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier);
+    void (*remove_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier);
+} VirtIOMEMClass;
+
+#endif

include/migration/colo.h

@@ -25,7 +25,7 @@ void migrate_start_colo_process(MigrationState *s);
 bool migration_in_colo_state(void);
 
 /* loadvm */
-void migration_incoming_enable_colo(void);
+int migration_incoming_enable_colo(void);
 void migration_incoming_disable_colo(void);
 bool migration_incoming_colo_enabled(void);
 void *colo_process_incoming_thread(void *opaque);

include/migration/misc.h

@@ -69,6 +69,8 @@ bool migration_has_failed(MigrationState *);
 /* ...and after the device transmission */
 bool migration_in_postcopy_after_devices(MigrationState *);
 void migration_global_dump(Monitor *mon);
+/* True if incomming migration entered POSTCOPY_INCOMING_DISCARD */
+bool migration_in_incoming_postcopy(void);
 
 /* migration/block-dirty-bitmap.c */
 void dirty_bitmap_mig_init(void);

include/net/net.h

@@ -176,6 +176,7 @@ void hmp_info_network(Monitor *mon, const QDict *qdict);
 void net_socket_rs_init(SocketReadState *rs,
                         SocketReadStateFinalize *finalize,
                         bool vnet_hdr);
+NetClientState *qemu_get_peer(NetClientState *nc, int queue_index);
 
 /* NIC info */
 

include/net/vhost-vdpa.h

@@ -0,0 +1,22 @@
+/*
+ * vhost-vdpa.h
+ *
+ * Copyright(c) 2017-2018 Intel Corporation.
+ * Copyright(c) 2020 Red Hat, Inc.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef VHOST_VDPA_H
+#define VHOST_VDPA_H
+
+#define TYPE_VHOST_VDPA "vhost-vdpa"
+
+struct vhost_net *vhost_vdpa_get_vhost_net(NetClientState *nc);
+uint64_t vhost_vdpa_get_acked_features(NetClientState *nc);
+
+extern const int vdpa_feature_bits[];
+
+#endif /* VHOST_VDPA_H */

include/net/vhost_net.h

@@ -28,6 +28,11 @@ void vhost_net_cleanup(VHostNetState *net);
 uint64_t vhost_net_get_features(VHostNetState *net, uint64_t features);
 void vhost_net_ack_features(VHostNetState *net, uint64_t features);
 
+int vhost_net_get_config(struct vhost_net *net,  uint8_t *config,
+                         uint32_t config_len);
+
+int vhost_net_set_config(struct vhost_net *net, const uint8_t *data,
+                         uint32_t offset, uint32_t size, uint32_t flags);
 bool vhost_net_virtqueue_pending(VHostNetState *net, int n);
 void vhost_net_virtqueue_mask(VHostNetState *net, VirtIODevice *dev,
                               int idx, bool mask);

include/sysemu/balloon.h

@@ -23,7 +23,5 @@ typedef void (QEMUBalloonStatus)(void *opaque, BalloonInfo *info);
 int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
                              QEMUBalloonStatus *stat_func, void *opaque);
 void qemu_remove_balloon_handler(void *opaque);
-bool qemu_balloon_is_inhibited(void);
-void qemu_balloon_inhibit(bool state);
 
 #endif