--- zzzz-none-000/linux-3.10.107/include/linux/hyperv.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/include/linux/hyperv.h 2021-02-04 17:41:59.000000000 +0000 @@ -25,317 +25,12 @@ #ifndef _HYPERV_H #define _HYPERV_H -#include - - -/* - * Implementation of host controlled snapshot of the guest. - */ - -#define VSS_OP_REGISTER 128 - -enum hv_vss_op { - VSS_OP_CREATE = 0, - VSS_OP_DELETE, - VSS_OP_HOT_BACKUP, - VSS_OP_GET_DM_INFO, - VSS_OP_BU_COMPLETE, - /* - * Following operations are only supported with IC version >= 5.0 - */ - VSS_OP_FREEZE, /* Freeze the file systems in the VM */ - VSS_OP_THAW, /* Unfreeze the file systems */ - VSS_OP_AUTO_RECOVER, - VSS_OP_COUNT /* Number of operations, must be last */ -}; - - -/* - * Header for all VSS messages. - */ -struct hv_vss_hdr { - __u8 operation; - __u8 reserved[7]; -} __attribute__((packed)); - - -/* - * Flag values for the hv_vss_check_feature. Linux supports only - * one value. - */ -#define VSS_HBU_NO_AUTO_RECOVERY 0x00000005 - -struct hv_vss_check_feature { - __u32 flags; -} __attribute__((packed)); - -struct hv_vss_check_dm_info { - __u32 flags; -} __attribute__((packed)); - -struct hv_vss_msg { - union { - struct hv_vss_hdr vss_hdr; - int error; - }; - union { - struct hv_vss_check_feature vss_cf; - struct hv_vss_check_dm_info dm_info; - }; -} __attribute__((packed)); - -/* - * An implementation of HyperV key value pair (KVP) functionality for Linux. - * - * - * Copyright (C) 2010, Novell, Inc. - * Author : K. Y. Srinivasan - * - */ - -/* - * Maximum value size - used for both key names and value data, and includes - * any applicable NULL terminators. - * - * Note: This limit is somewhat arbitrary, but falls easily within what is - * supported for all native guests (back to Win 2000) and what is reasonable - * for the IC KVP exchange functionality. Note that Windows Me/98/95 are - * limited to 255 character key names. - * - * MSDN recommends not storing data values larger than 2048 bytes in the - * registry. - * - * Note: This value is used in defining the KVP exchange message - this value - * cannot be modified without affecting the message size and compatibility. - */ - -/* - * bytes, including any null terminators - */ -#define HV_KVP_EXCHANGE_MAX_VALUE_SIZE (2048) - - -/* - * Maximum key size - the registry limit for the length of an entry name - * is 256 characters, including the null terminator - */ - -#define HV_KVP_EXCHANGE_MAX_KEY_SIZE (512) - -/* - * In Linux, we implement the KVP functionality in two components: - * 1) The kernel component which is packaged as part of the hv_utils driver - * is responsible for communicating with the host and responsible for - * implementing the host/guest protocol. 2) A user level daemon that is - * responsible for data gathering. - * - * Host/Guest Protocol: The host iterates over an index and expects the guest - * to assign a key name to the index and also return the value corresponding to - * the key. The host will have atmost one KVP transaction outstanding at any - * given point in time. The host side iteration stops when the guest returns - * an error. Microsoft has specified the following mapping of key names to - * host specified index: - * - * Index Key Name - * 0 FullyQualifiedDomainName - * 1 IntegrationServicesVersion - * 2 NetworkAddressIPv4 - * 3 NetworkAddressIPv6 - * 4 OSBuildNumber - * 5 OSName - * 6 OSMajorVersion - * 7 OSMinorVersion - * 8 OSVersion - * 9 ProcessorArchitecture - * - * The Windows host expects the Key Name and Key Value to be encoded in utf16. - * - * Guest Kernel/KVP Daemon Protocol: As noted earlier, we implement all of the - * data gathering functionality in a user mode daemon. The user level daemon - * is also responsible for binding the key name to the index as well. The - * kernel and user-level daemon communicate using a connector channel. - * - * The user mode component first registers with the - * the kernel component. Subsequently, the kernel component requests, data - * for the specified keys. In response to this message the user mode component - * fills in the value corresponding to the specified key. We overload the - * sequence field in the cn_msg header to define our KVP message types. - * - * - * The kernel component simply acts as a conduit for communication between the - * Windows host and the user-level daemon. The kernel component passes up the - * index received from the Host to the user-level daemon. If the index is - * valid (supported), the corresponding key as well as its - * value (both are strings) is returned. If the index is invalid - * (not supported), a NULL key string is returned. - */ +#include +#include - -/* - * Registry value types. - */ - -#define REG_SZ 1 -#define REG_U32 4 -#define REG_U64 8 - -/* - * As we look at expanding the KVP functionality to include - * IP injection functionality, we need to maintain binary - * compatibility with older daemons. - * - * The KVP opcodes are defined by the host and it was unfortunate - * that I chose to treat the registration operation as part of the - * KVP operations defined by the host. - * Here is the level of compatibility - * (between the user level daemon and the kernel KVP driver) that we - * will implement: - * - * An older daemon will always be supported on a newer driver. - * A given user level daemon will require a minimal version of the - * kernel driver. - * If we cannot handle the version differences, we will fail gracefully - * (this can happen when we have a user level daemon that is more - * advanced than the KVP driver. - * - * We will use values used in this handshake for determining if we have - * workable user level daemon and the kernel driver. We begin by taking the - * registration opcode out of the KVP opcode namespace. We will however, - * maintain compatibility with the existing user-level daemon code. - */ - -/* - * Daemon code not supporting IP injection (legacy daemon). - */ - -#define KVP_OP_REGISTER 4 - -/* - * Daemon code supporting IP injection. - * The KVP opcode field is used to communicate the - * registration information; so define a namespace that - * will be distinct from the host defined KVP opcode. - */ - -#define KVP_OP_REGISTER1 100 - -enum hv_kvp_exchg_op { - KVP_OP_GET = 0, - KVP_OP_SET, - KVP_OP_DELETE, - KVP_OP_ENUMERATE, - KVP_OP_GET_IP_INFO, - KVP_OP_SET_IP_INFO, - KVP_OP_COUNT /* Number of operations, must be last. */ -}; - -enum hv_kvp_exchg_pool { - KVP_POOL_EXTERNAL = 0, - KVP_POOL_GUEST, - KVP_POOL_AUTO, - KVP_POOL_AUTO_EXTERNAL, - KVP_POOL_AUTO_INTERNAL, - KVP_POOL_COUNT /* Number of pools, must be last. */ -}; - -/* - * Some Hyper-V status codes. - */ - -#define HV_S_OK 0x00000000 -#define HV_E_FAIL 0x80004005 -#define HV_S_CONT 0x80070103 -#define HV_ERROR_NOT_SUPPORTED 0x80070032 -#define HV_ERROR_MACHINE_LOCKED 0x800704F7 -#define HV_ERROR_DEVICE_NOT_CONNECTED 0x8007048F -#define HV_INVALIDARG 0x80070057 -#define HV_GUID_NOTFOUND 0x80041002 - -#define ADDR_FAMILY_NONE 0x00 -#define ADDR_FAMILY_IPV4 0x01 -#define ADDR_FAMILY_IPV6 0x02 - -#define MAX_ADAPTER_ID_SIZE 128 -#define MAX_IP_ADDR_SIZE 1024 -#define MAX_GATEWAY_SIZE 512 - - -struct hv_kvp_ipaddr_value { - __u16 adapter_id[MAX_ADAPTER_ID_SIZE]; - __u8 addr_family; - __u8 dhcp_enabled; - __u16 ip_addr[MAX_IP_ADDR_SIZE]; - __u16 sub_net[MAX_IP_ADDR_SIZE]; - __u16 gate_way[MAX_GATEWAY_SIZE]; - __u16 dns_addr[MAX_IP_ADDR_SIZE]; -} __attribute__((packed)); - - -struct hv_kvp_hdr { - __u8 operation; - __u8 pool; - __u16 pad; -} __attribute__((packed)); - -struct hv_kvp_exchg_msg_value { - __u32 value_type; - __u32 key_size; - __u32 value_size; - __u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; - union { - __u8 value[HV_KVP_EXCHANGE_MAX_VALUE_SIZE]; - __u32 value_u32; - __u64 value_u64; - }; -} __attribute__((packed)); - -struct hv_kvp_msg_enumerate { - __u32 index; - struct hv_kvp_exchg_msg_value data; -} __attribute__((packed)); - -struct hv_kvp_msg_get { - struct hv_kvp_exchg_msg_value data; -}; - -struct hv_kvp_msg_set { - struct hv_kvp_exchg_msg_value data; -}; - -struct hv_kvp_msg_delete { - __u32 key_size; - __u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; -}; - -struct hv_kvp_register { - __u8 version[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; -}; - -struct hv_kvp_msg { - union { - struct hv_kvp_hdr kvp_hdr; - int error; - }; - union { - struct hv_kvp_msg_get kvp_get; - struct hv_kvp_msg_set kvp_set; - struct hv_kvp_msg_delete kvp_delete; - struct hv_kvp_msg_enumerate kvp_enum_data; - struct hv_kvp_ipaddr_value kvp_ip_val; - struct hv_kvp_register kvp_register; - } body; -} __attribute__((packed)); - -struct hv_kvp_ip_msg { - __u8 operation; - __u8 pool; - struct hv_kvp_ipaddr_value kvp_ip_val; -} __attribute__((packed)); - -#ifdef __KERNEL__ +#include #include #include -#include #include #include #include @@ -343,7 +38,7 @@ #include -#define MAX_PAGE_BUFFER_COUNT 19 +#define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ #pragma pack(push, 1) @@ -363,6 +58,18 @@ u64 pfn_array[MAX_MULTIPAGE_BUFFER_COUNT]; }; +/* + * Multiple-page buffer array; the pfn array is variable size: + * The number of entries in the PFN array is determined by + * "len" and "offset". + */ +struct hv_mpb_array { + /* Length and Offset determines the # of pfns in the array */ + u32 len; + u32 offset; + u64 pfn_array[]; +}; + /* 0x18 includes the proprietary packet header */ #define MAX_PAGE_BUFFER_PACKET (0x18 + \ (sizeof(struct hv_page_buffer) * \ @@ -421,15 +128,6 @@ u32 ring_data_startoffset; }; -struct hv_ring_buffer_debug_info { - u32 current_interrupt_mask; - u32 current_read_index; - u32 current_write_index; - u32 bytes_avail_toread; - u32 bytes_avail_towrite; -}; - - /* * * hv_get_ringbuffer_availbytes() @@ -455,27 +153,6 @@ *read = dsize - *write; } - -/* - * We use the same version numbering for all Hyper-V modules. - * - * Definition of versioning is as follows; - * - * Major Number Changes for these scenarios; - * 1. When a new version of Windows Hyper-V - * is released. - * 2. A Major change has occurred in the - * Linux IC's. - * (For example the merge for the first time - * into the kernel) Every time the Major Number - * changes, the Revision number is reset to 0. - * Minor Number Changes when new functionality is added - * to the Linux IC's that is not a bug fix. - * - * 3.1 - Added completed hv_utils driver. Shutdown/Heartbeat/Timesync - */ -#define HV_DRV_VERSION "3.1" - /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. @@ -484,17 +161,18 @@ * 1 . 1 (Windows 7) * 2 . 4 (Windows 8) * 3 . 0 (Windows 8 R2) + * 4 . 0 (Windows 10) */ #define VERSION_WS2008 ((0 << 16) | (13)) #define VERSION_WIN7 ((1 << 16) | (1)) #define VERSION_WIN8 ((2 << 16) | (4)) #define VERSION_WIN8_1 ((3 << 16) | (0)) - +#define VERSION_WIN10 ((4 << 16) | (0)) #define VERSION_INVAL -1 -#define VERSION_CURRENT VERSION_WIN8_1 +#define VERSION_CURRENT VERSION_WIN10 /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) @@ -714,10 +392,7 @@ CHANNELMSG_INITIATE_CONTACT = 14, CHANNELMSG_VERSION_RESPONSE = 15, CHANNELMSG_UNLOAD = 16, -#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD - CHANNELMSG_VIEWRANGE_ADD = 17, - CHANNELMSG_VIEWRANGE_REMOVE = 18, -#endif + CHANNELMSG_UNLOAD_RESPONSE = 17, CHANNELMSG_COUNT }; @@ -874,21 +549,6 @@ u32 gpadl; } __packed; -#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD -struct vmbus_channel_view_range_add { - struct vmbus_channel_message_header header; - PHYSICAL_ADDRESS viewrange_base; - u64 viewrange_length; - u32 child_relid; -} __packed; - -struct vmbus_channel_view_range_remove { - struct vmbus_channel_message_header header; - PHYSICAL_ADDRESS viewrange_base; - u32 child_relid; -} __packed; -#endif - struct vmbus_channel_relid_released { struct vmbus_channel_message_header header; u32 child_relid; @@ -912,23 +572,7 @@ CHANNEL_OFFER_STATE, CHANNEL_OPENING_STATE, CHANNEL_OPEN_STATE, -}; - -struct vmbus_channel_debug_info { - u32 relid; - enum vmbus_channel_state state; - uuid_le interfacetype; - uuid_le interface_instance; - u32 monitorid; - u32 servermonitor_pending; - u32 servermonitor_latency; - u32 servermonitor_connectionid; - u32 clientmonitor_pending; - u32 clientmonitor_latency; - u32 clientmonitor_connectionid; - - struct hv_ring_buffer_debug_info inbound; - struct hv_ring_buffer_debug_info outbound; + CHANNEL_OPENED_STATE, }; /* @@ -986,13 +630,19 @@ struct hv_input_signal_event event; }; +enum hv_signal_policy { + HV_SIGNAL_POLICY_DEFAULT = 0, + HV_SIGNAL_POLICY_EXPLICIT, +}; + struct vmbus_channel { + /* Unique channel id */ + int id; + struct list_head listentry; struct hv_device *device_obj; - struct work_struct work; - enum vmbus_channel_state state; struct vmbus_channel_offer_channel offermsg; @@ -1003,6 +653,8 @@ u8 monitor_grp; u8 monitor_bit; + bool rescind; /* got rescind msg */ + u32 ringbuffer_gpadlhandle; /* Allocated memory for ring buffer */ @@ -1011,7 +663,6 @@ struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ spinlock_t inbound_lock; - struct workqueue_struct *controlwq; struct vmbus_close_msg close_msg; @@ -1049,17 +700,130 @@ * preserve the earlier behavior. */ u32 target_vp; + /* The corresponding CPUID in the guest */ + u32 target_cpu; + /* + * State to manage the CPU affiliation of channels. + */ + struct cpumask alloced_cpus_in_node; + int numa_node; + /* + * Support for sub-channels. For high performance devices, + * it will be useful to have multiple sub-channels to support + * a scalable communication infrastructure with the host. + * The support for sub-channels is implemented as an extention + * to the current infrastructure. + * The initial offer is considered the primary channel and this + * offer message will indicate if the host supports sub-channels. + * The guest is free to ask for sub-channels to be offerred and can + * open these sub-channels as a normal "primary" channel. However, + * all sub-channels will have the same type and instance guids as the + * primary channel. Requests sent on a given channel will result in a + * response on the same channel. + */ + + /* + * Sub-channel creation callback. This callback will be called in + * process context when a sub-channel offer is received from the host. + * The guest can open the sub-channel in the context of this callback. + */ + void (*sc_creation_callback)(struct vmbus_channel *new_sc); + + /* + * The spinlock to protect the structure. It is being used to protect + * test-and-set access to various attributes of the structure as well + * as all sc_list operations. + */ + spinlock_t lock; + /* + * All Sub-channels of a primary channel are linked here. + */ + struct list_head sc_list; + /* + * Current number of sub-channels. + */ + int num_sc; + /* + * Number of a sub-channel (position within sc_list) which is supposed + * to be used as the next outgoing channel. + */ + int next_oc; + /* + * The primary channel this sub-channel belongs to. + * This will be NULL for the primary channel. + */ + struct vmbus_channel *primary_channel; + /* + * Support per-channel state for use by vmbus drivers. + */ + void *per_channel_state; + /* + * To support per-cpu lookup mapping of relid to channel, + * link up channels based on their CPU affinity. + */ + struct list_head percpu_list; + /* + * Host signaling policy: The default policy will be + * based on the ring buffer state. We will also support + * a policy where the client driver can have explicit + * signaling control. + */ + enum hv_signal_policy signal_policy; }; +static inline void set_channel_signal_state(struct vmbus_channel *c, + enum hv_signal_policy policy) +{ + c->signal_policy = policy; +} + static inline void set_channel_read_state(struct vmbus_channel *c, bool state) { c->batched_reading = state; } +static inline void set_per_channel_state(struct vmbus_channel *c, void *s) +{ + c->per_channel_state = s; +} + +static inline void *get_per_channel_state(struct vmbus_channel *c) +{ + return c->per_channel_state; +} + void vmbus_onmessage(void *context); int vmbus_request_offers(void); +/* + * APIs for managing sub-channels. + */ + +void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, + void (*sc_cr_cb)(struct vmbus_channel *new_sc)); + +/* + * Retrieve the (sub) channel on which to send an outgoing request. + * When a primary channel has multiple sub-channels, we choose a + * channel whose VCPU binding is closest to the VCPU on which + * this call is being made. + */ +struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary); + +/* + * Check if sub-channels have already been offerred. This API will be useful + * when the driver is unloaded after establishing sub-channels. In this case, + * when the driver is re-loaded, the driver would have to check if the + * subchannels have already been established before attempting to request + * the creation of sub-channels. + * This function returns TRUE to indicate that subchannels have already been + * created. + * This function should be invoked after setting the callback function for + * sub-channel creation. + */ +bool vmbus_are_subchannels_present(struct vmbus_channel *primary); + /* The format must be the same as struct vmdata_gpa_direct */ struct vmbus_channel_packet_page_buffer { u16 type; @@ -1084,6 +848,18 @@ struct hv_multipage_buffer range; } __packed; +/* The format must be the same as struct vmdata_gpa_direct */ +struct vmbus_packet_mpb_array { + u16 type; + u16 dataoffset8; + u16 length8; + u16 flags; + u64 transactionid; + u32 reserved; + u32 rangecount; /* Always 1 in this case */ + struct hv_mpb_array range; +} __packed; + extern int vmbus_open(struct vmbus_channel *channel, u32 send_ringbuffersize, @@ -1096,12 +872,20 @@ extern void vmbus_close(struct vmbus_channel *channel); extern int vmbus_sendpacket(struct vmbus_channel *channel, - const void *buffer, + void *buffer, u32 bufferLen, u64 requestid, enum vmbus_packet_type type, u32 flags); +extern int vmbus_sendpacket_ctl(struct vmbus_channel *channel, + void *buffer, + u32 bufferLen, + u64 requestid, + enum vmbus_packet_type type, + u32 flags, + bool kick_q); + extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, struct hv_page_buffer pagebuffers[], u32 pagecount, @@ -1109,12 +893,28 @@ u32 bufferlen, u64 requestid); +extern int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, + struct hv_page_buffer pagebuffers[], + u32 pagecount, + void *buffer, + u32 bufferlen, + u64 requestid, + u32 flags, + bool kick_q); + extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, struct hv_multipage_buffer *mpb, void *buffer, u32 bufferlen, u64 requestid); +extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, + struct vmbus_packet_mpb_array *mpb, + u32 desc_size, + void *buffer, + u32 bufferlen, + u64 requestid); + extern int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, u32 size, @@ -1136,19 +936,8 @@ u64 *requestid); -extern void vmbus_get_debug_info(struct vmbus_channel *channel, - struct vmbus_channel_debug_info *debug); - extern void vmbus_ontimer(unsigned long data); -struct hv_dev_port_info { - u32 int_mask; - u32 read_idx; - u32 write_idx; - u32 bytes_avail_toread; - u32 bytes_avail_towrite; -}; - /* Base driver object */ struct hv_driver { const char *name; @@ -1207,6 +996,11 @@ const char *mod_name); void vmbus_driver_unregister(struct hv_driver *hv_driver); +int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, + resource_size_t min, resource_size_t max, + resource_size_t size, resource_size_t align, + bool fb_overlap_ok); + /** * VMBUS_DEVICE - macro used to describe a specific hyperv vmbus device * @@ -1330,6 +1124,36 @@ 0x8e, 0x77, 0x05, 0x58, 0xeb, 0x10, 0x73, 0xf8 \ } +/* + * Synthetic FC GUID + * {2f9bcc4a-0069-4af3-b76b-6fd0be528cda} + */ +#define HV_SYNTHFC_GUID \ + .guid = { \ + 0x4A, 0xCC, 0x9B, 0x2F, 0x69, 0x00, 0xF3, 0x4A, \ + 0xB7, 0x6B, 0x6F, 0xD0, 0xBE, 0x52, 0x8C, 0xDA \ + } + +/* + * Guest File Copy Service + * {34D14BE3-DEE4-41c8-9AE7-6B174977C192} + */ + +#define HV_FCOPY_GUID \ + .guid = { \ + 0xE3, 0x4B, 0xD1, 0x34, 0xE4, 0xDE, 0xC8, 0x41, \ + 0x9A, 0xE7, 0x6B, 0x17, 0x49, 0x77, 0xC1, 0x92 \ + } + +/* + * NetworkDirect. This is the guest RDMA service. + * {8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501} + */ +#define HV_ND_GUID \ + .guid = { \ + 0x3d, 0xaf, 0x2e, 0x8c, 0xa7, 0x32, 0x09, 0x4b, \ + 0xab, 0x99, 0xbd, 0x1f, 0x1c, 0x86, 0xb5, 0x01 \ + } /* * Common header for Hyper-V ICs @@ -1427,17 +1251,11 @@ }; #define MAX_SRV_VER 0x7ffffff -extern void vmbus_prep_negotiate_resp(struct icmsg_hdr *, +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, struct icmsg_negotiate *, u8 *, int, int); -int hv_kvp_init(struct hv_util_service *); -void hv_kvp_deinit(void); -void hv_kvp_onchannelcallback(void *); - -int hv_vss_init(struct hv_util_service *); -void hv_vss_deinit(void); -void hv_vss_onchannelcallback(void *); +void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); /* * Negotiated version with the Host. @@ -1445,5 +1263,4 @@ extern __u32 vmbus_proto_version; -#endif /* __KERNEL__ */ #endif /* _HYPERV_H */