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

virtio, vhost, pc: fixes, features

beginnings of iotlb support for vhost
acpi hotplug rework
vhost net tx flush on link down
passing mtu to guests
hotplug for virtio crypto
fixes and cleanups all over the place

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Tue 10 Jan 2017 05:37:48 GMT
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# 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)
  acpi-test: update expected files
  memhp: move DIMM devices into dedicated scope with related common methods
  memhp: don't generate memory hotplug AML if it's not enabled/supported
  memhp: move memory hotplug only defines to memory_hotplug.c
  memhp: move GPE handler_E03 into build_memory_hotplug_aml()
  memhp: merge build_memory_devices() into build_memory_hotplug_aml()
  memhp: consolidate scattered MHPD device declaration
  memhp: move build_memory_devices() into memory_hotplug.c
  memhp: move build_memory_hotplug_aml() into memory_hotplug.c
  tests: pc: add memory hotplug acpi tables tests
  virtio-net: Add MTU feature support
  vhost-net: Notify the backend about the host MTU
  vhost-user: Add MTU protocol feature and op
  net: virtio-net discards TX data after link down
  virtio: Introduce virtqueue_drop_all procedure
  net: vhost stop updates virtio queue state
  net: Add virtio queue interface to update used index from vring state
  balloon: Don't balloon roms
  virtio: fix vq->inuse recalc after migr
  pcie_aer: support configurable AER capa version
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

16 files changed, 116 insertions, 46 deletions

diff --git a/include/exec/memory.h b/include/exec/memory.h
index 64560f61b4..bec9756667 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -628,6 +628,9 @@ static inline bool memory_region_is_romd(MemoryRegion *mr)
  */
 static inline bool memory_region_is_iommu(MemoryRegion *mr)
 {
+    if (mr->alias) {
+        return memory_region_is_iommu(mr->alias);
+    }
     return mr->iommu_ops;
 }
 
@@ -1537,6 +1540,11 @@ void stl_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
 void stl_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
 void stq_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
 void stq_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
+/* address_space_get_iotlb_entry: translate an address into an IOTLB
+ * entry. Should be called from an RCU critical section.
+ */
+IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr,
+                                            bool is_write);
 
 /* address_space_translate: translate an address range into an address space
  * into a MemoryRegion and an address range into that section.  Should be
diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h
index d43ec005cb..4cc3630e61 100644
--- a/include/hw/acpi/acpi-defs.h
+++ b/include/hw/acpi/acpi-defs.h
@@ -627,8 +627,20 @@ struct AcpiDmarHardwareUnit {
 } QEMU_PACKED;
 typedef struct AcpiDmarHardwareUnit AcpiDmarHardwareUnit;
 
+/* Type 2: Root Port ATS Capability Reporting Structure */
+struct AcpiDmarRootPortATS {
+    uint16_t type;
+    uint16_t length;
+    uint8_t flags;
+    uint8_t reserved;
+    uint16_t pci_segment;
+    AcpiDmarDeviceScope scope[0];
+} QEMU_PACKED;
+typedef struct AcpiDmarRootPortATS AcpiDmarRootPortATS;
+
 /* Masks for Flags field above */
 #define ACPI_DMAR_INCLUDE_PCI_ALL   1
+#define ACPI_DMAR_ATSR_ALL_PORTS    1
 
 /*
  * Input Output Remapping Table (IORT)
diff --git a/include/hw/acpi/memory_hotplug.h b/include/hw/acpi/memory_hotplug.h
index d2c7452397..db8ebc9cea 100644
--- a/include/hw/acpi/memory_hotplug.h
+++ b/include/hw/acpi/memory_hotplug.h
@@ -30,7 +30,7 @@ typedef struct MemHotplugState {
 } MemHotplugState;
 
 void acpi_memory_hotplug_init(MemoryRegion *as, Object *owner,
-                              MemHotplugState *state);
+                              MemHotplugState *state, uint16_t io_base);
 
 void acpi_memory_plug_cb(HotplugHandler *hotplug_dev, MemHotplugState *mem_st,
                          DeviceState *dev, Error **errp);
@@ -47,11 +47,7 @@ extern const VMStateDescription vmstate_memory_hotplug;
 
 void acpi_memory_ospm_status(MemHotplugState *mem_st, ACPIOSTInfoList ***list);
 
-#define MEMORY_HOTPLUG_DEVICE        "MHPD"
-#define MEMORY_SLOT_SCAN_METHOD      "MSCN"
-#define MEMORY_HOTPLUG_HANDLER_PATH "\\_SB.PCI0." \
-     MEMORY_HOTPLUG_DEVICE "." MEMORY_SLOT_SCAN_METHOD
-
-void build_memory_hotplug_aml(Aml *ctx, uint32_t nr_mem,
-                              uint16_t io_base, uint16_t io_len);
+void build_memory_hotplug_aml(Aml *table, uint32_t nr_mem,
+                              const char *res_root,
+                              const char *event_handler_method);
 #endif
diff --git a/include/hw/acpi/pc-hotplug.h b/include/hw/acpi/pc-hotplug.h
index 6a8d268f84..31bc9191c3 100644
--- a/include/hw/acpi/pc-hotplug.h
+++ b/include/hw/acpi/pc-hotplug.h
@@ -29,29 +29,6 @@
 #define PIIX4_CPU_HOTPLUG_IO_BASE 0xaf00
 #define CPU_HOTPLUG_RESOURCE_DEVICE PRES
 
-#define ACPI_MEMORY_HOTPLUG_IO_LEN 24
 #define ACPI_MEMORY_HOTPLUG_BASE 0x0a00
 
-#define MEMORY_SLOTS_NUMBER          "MDNR"
-#define MEMORY_HOTPLUG_IO_REGION     "HPMR"
-#define MEMORY_SLOT_ADDR_LOW         "MRBL"
-#define MEMORY_SLOT_ADDR_HIGH        "MRBH"
-#define MEMORY_SLOT_SIZE_LOW         "MRLL"
-#define MEMORY_SLOT_SIZE_HIGH        "MRLH"
-#define MEMORY_SLOT_PROXIMITY        "MPX"
-#define MEMORY_SLOT_ENABLED          "MES"
-#define MEMORY_SLOT_INSERT_EVENT     "MINS"
-#define MEMORY_SLOT_REMOVE_EVENT     "MRMV"
-#define MEMORY_SLOT_EJECT            "MEJ"
-#define MEMORY_SLOT_SLECTOR          "MSEL"
-#define MEMORY_SLOT_OST_EVENT        "MOEV"
-#define MEMORY_SLOT_OST_STATUS       "MOSC"
-#define MEMORY_SLOT_LOCK             "MLCK"
-#define MEMORY_SLOT_STATUS_METHOD    "MRST"
-#define MEMORY_SLOT_CRS_METHOD       "MCRS"
-#define MEMORY_SLOT_OST_METHOD       "MOST"
-#define MEMORY_SLOT_PROXIMITY_METHOD "MPXM"
-#define MEMORY_SLOT_EJECT_METHOD     "MEJ0"
-#define MEMORY_SLOT_NOTIFY_METHOD    "MTFY"
-
 #endif
diff --git a/include/hw/i386/x86-iommu.h b/include/hw/i386/x86-iommu.h
index 0c89d9835b..361c07cdc6 100644
--- a/include/hw/i386/x86-iommu.h
+++ b/include/hw/i386/x86-iommu.h
@@ -73,6 +73,7 @@ typedef struct IEC_Notifier IEC_Notifier;
 struct X86IOMMUState {
     SysBusDevice busdev;
     bool intr_supported;        /* Whether vIOMMU supports IR */
+    bool dt_supported;          /* Whether vIOMMU supports DT */
     IommuType type;             /* IOMMU type - AMD/Intel     */
     QLIST_HEAD(, IEC_Notifier) iec_notifiers; /* IEC notify list */
 };
diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h
index 056d25e53c..b08451d2c5 100644
--- a/include/hw/pci/pcie.h
+++ b/include/hw/pci/pcie.h
@@ -74,6 +74,9 @@ struct PCIExpressDevice {
     /* AER */
     uint16_t aer_cap;
     PCIEAERLog aer_log;
+
+    /* Offset of ATS capability in config space */
+    uint16_t ats_cap;
 };
 
 #define COMPAT_PROP_PCP "power_controller_present"
@@ -120,6 +123,7 @@ void pcie_add_capability(PCIDevice *dev,
 
 void pcie_ari_init(PCIDevice *dev, uint16_t offset, uint16_t nextfn);
 void pcie_dev_ser_num_init(PCIDevice *dev, uint16_t offset, uint64_t ser_num);
+void pcie_ats_init(PCIDevice *dev, uint16_t offset);
 
 extern const VMStateDescription vmstate_pcie_device;
 
diff --git a/include/hw/pci/pcie_aer.h b/include/hw/pci/pcie_aer.h
index c2ee4e2bdb..526802bd31 100644
--- a/include/hw/pci/pcie_aer.h
+++ b/include/hw/pci/pcie_aer.h
@@ -44,7 +44,6 @@ struct PCIEAERLog {
      */
 #define PCIE_AER_LOG_MAX_DEFAULT        8
 #define PCIE_AER_LOG_MAX_LIMIT          128
-#define PCIE_AER_LOG_MAX_UNSET          0xffff
     uint16_t log_max;
 
     /* Error log. log_max-sized array */
@@ -87,7 +86,8 @@ struct PCIEAERErr {
 
 extern const VMStateDescription vmstate_pcie_aer_log;
 
-int pcie_aer_init(PCIDevice *dev, uint16_t offset, uint16_t size);
+int pcie_aer_init(PCIDevice *dev, uint8_t cap_ver, uint16_t offset,
+                  uint16_t size, Error **errp);
 void pcie_aer_exit(PCIDevice *dev);
 void pcie_aer_write_config(PCIDevice *dev,
                            uint32_t addr, uint32_t val, int len);
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index 6e90703cad..30abc11cf1 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -32,6 +32,7 @@ typedef int (*vhost_backend_memslots_limit)(struct vhost_dev *dev);
 
 typedef int (*vhost_net_set_backend_op)(struct vhost_dev *dev,
                                 struct vhost_vring_file *file);
+typedef int (*vhost_net_set_mtu_op)(struct vhost_dev *dev, uint16_t mtu);
 typedef int (*vhost_scsi_set_endpoint_op)(struct vhost_dev *dev,
                                   struct vhost_scsi_target *target);
 typedef int (*vhost_scsi_clear_endpoint_op)(struct vhost_dev *dev,
@@ -83,6 +84,7 @@ typedef struct VhostOps {
     vhost_backend_cleanup vhost_backend_cleanup;
     vhost_backend_memslots_limit vhost_backend_memslots_limit;
     vhost_net_set_backend_op vhost_net_set_backend;
+    vhost_net_set_mtu_op vhost_net_set_mtu;
     vhost_scsi_set_endpoint_op vhost_scsi_set_endpoint;
     vhost_scsi_clear_endpoint_op vhost_scsi_clear_endpoint;
     vhost_scsi_get_abi_version_op vhost_scsi_get_abi_version;
diff --git a/include/hw/virtio/virtio-access.h b/include/hw/virtio/virtio-access.h
index 440b4555ea..91ae14d254 100644
--- a/include/hw/virtio/virtio-access.h
+++ b/include/hw/virtio/virtio-access.h
@@ -17,6 +17,7 @@
 #define QEMU_VIRTIO_ACCESS_H
 
 #include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-bus.h"
 #include "exec/address-spaces.h"
 
 #if defined(TARGET_PPC64) || defined(TARGET_ARM)
@@ -40,45 +41,55 @@ static inline bool virtio_access_is_big_endian(VirtIODevice *vdev)
 
 static inline uint16_t virtio_lduw_phys(VirtIODevice *vdev, hwaddr pa)
 {
+    AddressSpace *dma_as = vdev->dma_as;
+
     if (virtio_access_is_big_endian(vdev)) {
-        return lduw_be_phys(&address_space_memory, pa);
+        return lduw_be_phys(dma_as, pa);
     }
-    return lduw_le_phys(&address_space_memory, pa);
+    return lduw_le_phys(dma_as, pa);
 }
 
 static inline uint32_t virtio_ldl_phys(VirtIODevice *vdev, hwaddr pa)
 {
+    AddressSpace *dma_as = vdev->dma_as;
+
     if (virtio_access_is_big_endian(vdev)) {
-        return ldl_be_phys(&address_space_memory, pa);
+        return ldl_be_phys(dma_as, pa);
     }
-    return ldl_le_phys(&address_space_memory, pa);
+    return ldl_le_phys(dma_as, pa);
 }
 
 static inline uint64_t virtio_ldq_phys(VirtIODevice *vdev, hwaddr pa)
 {
+    AddressSpace *dma_as = vdev->dma_as;
+
     if (virtio_access_is_big_endian(vdev)) {
-        return ldq_be_phys(&address_space_memory, pa);
+        return ldq_be_phys(dma_as, pa);
     }
-    return ldq_le_phys(&address_space_memory, pa);
+    return ldq_le_phys(dma_as, pa);
 }
 
 static inline void virtio_stw_phys(VirtIODevice *vdev, hwaddr pa,
                                    uint16_t value)
 {
+    AddressSpace *dma_as = vdev->dma_as;
+
     if (virtio_access_is_big_endian(vdev)) {
-        stw_be_phys(&address_space_memory, pa, value);
+        stw_be_phys(dma_as, pa, value);
     } else {
-        stw_le_phys(&address_space_memory, pa, value);
+        stw_le_phys(dma_as, pa, value);
     }
 }
 
 static inline void virtio_stl_phys(VirtIODevice *vdev, hwaddr pa,
                                    uint32_t value)
 {
+    AddressSpace *dma_as = vdev->dma_as;
+
     if (virtio_access_is_big_endian(vdev)) {
-        stl_be_phys(&address_space_memory, pa, value);
+        stl_be_phys(dma_as, pa, value);
     } else {
-        stl_le_phys(&address_space_memory, pa, value);
+        stl_le_phys(dma_as, pa, value);
     }
 }
 
diff --git a/include/hw/virtio/virtio-bus.h b/include/hw/virtio/virtio-bus.h
index 8a51e2c564..a63c1d216d 100644
--- a/include/hw/virtio/virtio-bus.h
+++ b/include/hw/virtio/virtio-bus.h
@@ -88,6 +88,7 @@ typedef struct VirtioBusClass {
      * Note that changing this will break migration for this transport.
      */
     bool has_variable_vring_alignment;
+    AddressSpace *(*get_dma_as)(DeviceState *d);
 } VirtioBusClass;
 
 struct VirtioBusState {
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 0ced975c57..8ea56a8f60 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -36,6 +36,7 @@ typedef struct virtio_net_conf
     int32_t txburst;
     char *tx;
     uint16_t rx_queue_size;
+    uint16_t mtu;
 } virtio_net_conf;
 
 /* Maximum packet size we can receive from tap device: header + 64k */
diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
index ab0e030cc4..e5541c61f7 100644
--- a/include/hw/virtio/virtio.h
+++ b/include/hw/virtio/virtio.h
@@ -92,6 +92,7 @@ struct VirtIODevice
     char *bus_name;
     uint8_t device_endian;
     bool use_guest_notifier_mask;
+    AddressSpace *dma_as;
     QLIST_HEAD(, VirtQueue) *vector_queues;
 };
 
@@ -170,9 +171,10 @@ bool virtqueue_rewind(VirtQueue *vq, unsigned int num);
 void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
                     unsigned int len, unsigned int idx);
 
-void virtqueue_map(VirtQueueElement *elem);
+void virtqueue_map(VirtIODevice *vdev, VirtQueueElement *elem);
 void *virtqueue_pop(VirtQueue *vq, size_t sz);
-void *qemu_get_virtqueue_element(QEMUFile *f, size_t sz);
+unsigned int virtqueue_drop_all(VirtQueue *vq);
+void *qemu_get_virtqueue_element(VirtIODevice *vdev, QEMUFile *f, size_t sz);
 void qemu_put_virtqueue_element(QEMUFile *f, VirtQueueElement *elem);
 int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes,
                           unsigned int out_bytes);
@@ -255,7 +257,9 @@ typedef struct VirtIORNGConf VirtIORNGConf;
     DEFINE_PROP_BIT64("notify_on_empty", _state, _field,  \
                       VIRTIO_F_NOTIFY_ON_EMPTY, true), \
     DEFINE_PROP_BIT64("any_layout", _state, _field, \
-                      VIRTIO_F_ANY_LAYOUT, true)
+                      VIRTIO_F_ANY_LAYOUT, true), \
+    DEFINE_PROP_BIT64("iommu_platform", _state, _field, \
+                      VIRTIO_F_IOMMU_PLATFORM, false)
 
 hwaddr virtio_queue_get_desc_addr(VirtIODevice *vdev, int n);
 hwaddr virtio_queue_get_avail_addr(VirtIODevice *vdev, int n);
@@ -266,6 +270,7 @@ hwaddr virtio_queue_get_used_size(VirtIODevice *vdev, int n);
 uint16_t virtio_queue_get_last_avail_idx(VirtIODevice *vdev, int n);
 void virtio_queue_set_last_avail_idx(VirtIODevice *vdev, int n, uint16_t idx);
 void virtio_queue_invalidate_signalled_used(VirtIODevice *vdev, int n);
+void virtio_queue_update_used_idx(VirtIODevice *vdev, int n);
 VirtQueue *virtio_get_queue(VirtIODevice *vdev, int n);
 uint16_t virtio_get_queue_index(VirtQueue *vq);
 EventNotifier *virtio_queue_get_guest_notifier(VirtQueue *vq);
diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h
index 1638ee57f7..2125829a16 100644
--- a/include/migration/vmstate.h
+++ b/include/migration/vmstate.h
@@ -186,6 +186,12 @@ enum VMStateFlags {
     VMS_MULTIPLY_ELEMENTS = 0x4000,
 };
 
+typedef enum {
+    MIG_PRI_DEFAULT = 0,
+    MIG_PRI_IOMMU,              /* Must happen before PCI devices */
+    MIG_PRI_MAX,
+} MigrationPriority;
+
 typedef struct {
     const char *name;
     size_t offset;
@@ -207,6 +213,7 @@ struct VMStateDescription {
     int version_id;
     int minimum_version_id;
     int minimum_version_id_old;
+    MigrationPriority priority;
     LoadStateHandler *load_state_old;
     int (*pre_load)(void *opaque);
     int (*post_load)(void *opaque, int version_id);
diff --git a/include/net/vhost_net.h b/include/net/vhost_net.h
index 5a08efffef..afc1499eb9 100644
--- a/include/net/vhost_net.h
+++ b/include/net/vhost_net.h
@@ -35,4 +35,6 @@ int vhost_set_vring_enable(NetClientState * nc, int enable);
 
 uint64_t vhost_net_get_acked_features(VHostNetState *net);
 
+int vhost_net_set_mtu(struct vhost_net *net, uint16_t mtu);
+
 #endif
diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h
index e5a2e68b22..be5b066aa4 100644
--- a/include/standard-headers/linux/pci_regs.h
+++ b/include/standard-headers/linux/pci_regs.h
@@ -678,6 +678,7 @@
 #define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_PTM
 
 #define PCI_EXT_CAP_DSN_SIZEOF	12
+#define PCI_EXT_CAP_ATS_SIZEOF	8
 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40
 
 /* Advanced Error Reporting */
diff --git a/include/sysemu/cryptodev.h b/include/sysemu/cryptodev.h
index 84526c0d35..a9d0d1ee25 100644
--- a/include/sysemu/cryptodev.h
+++ b/include/sysemu/cryptodev.h
@@ -202,6 +202,8 @@ struct CryptoDevBackend {
     Object parent_obj;
 
     bool ready;
+    /* Tag the cryptodev backend is used by virtio-crypto or not */
+    bool is_used;
     CryptoDevBackendConf conf;
 };
 
@@ -295,4 +297,44 @@ int cryptodev_backend_crypto_operation(
                  void *opaque,
                  uint32_t queue_index, Error **errp);
 
+/**
+ * cryptodev_backend_set_used:
+ * @backend: the cryptodev backend object
+ * @used: ture or false
+ *
+ * Set the cryptodev backend is used by virtio-crypto or not
+ */
+void cryptodev_backend_set_used(CryptoDevBackend *backend, bool used);
+
+/**
+ * cryptodev_backend_is_used:
+ * @backend: the cryptodev backend object
+ *
+ * Return the status that the cryptodev backend is used
+ * by virtio-crypto or not
+ *
+ * Returns: true on used, or false on not used
+ */
+bool cryptodev_backend_is_used(CryptoDevBackend *backend);
+
+/**
+ * cryptodev_backend_set_ready:
+ * @backend: the cryptodev backend object
+ * @ready: ture or false
+ *
+ * Set the cryptodev backend is ready or not, which is called
+ * by the children of the cryptodev banckend interface.
+ */
+void cryptodev_backend_set_ready(CryptoDevBackend *backend, bool ready);
+
+/**
+ * cryptodev_backend_is_ready:
+ * @backend: the cryptodev backend object
+ *
+ * Return the status that the cryptodev backend is ready or not
+ *
+ * Returns: true on ready, or false on not ready
+ */
+bool cryptodev_backend_is_ready(CryptoDevBackend *backend);
+
 #endif /* CRYPTODEV_H */