![Linus Torvalds](/assets/img/avatar_default.png)
Pull networking updates from David Miller: 1) BBR TCP congestion control, from Neal Cardwell, Yuchung Cheng and co. at Google. https://lwn.net/Articles/701165/ 2) Do TCP Small Queues for retransmits, from Eric Dumazet. 3) Support collect_md mode for all IPV4 and IPV6 tunnels, from Alexei Starovoitov. 4) Allow cls_flower to classify packets in ip tunnels, from Amir Vadai. 5) Support DSA tagging in older mv88e6xxx switches, from Andrew Lunn. 6) Support GMAC protocol in iwlwifi mwm, from Ayala Beker. 7) Support ndo_poll_controller in mlx5, from Calvin Owens. 8) Move VRF processing to an output hook and allow l3mdev to be loopback, from David Ahern. 9) Support SOCK_DESTROY for UDP sockets. Also from David Ahern. 10) Congestion control in RXRPC, from David Howells. 11) Support geneve RX offload in ixgbe, from Emil Tantilov. 12) When hitting pressure for new incoming TCP data SKBs, perform a partial rathern than a full purge of the OFO queue (which could be huge). From Eric Dumazet. 13) Convert XFRM state and policy lookups to RCU, from Florian Westphal. 14) Support RX network flow classification to igb, from Gangfeng Huang. 15) Hardware offloading of eBPF in nfp driver, from Jakub Kicinski. 16) New skbmod packet action, from Jamal Hadi Salim. 17) Remove some inefficiencies in snmp proc output, from Jia He. 18) Add FIB notifications to properly propagate route changes to hardware which is doing forwarding offloading. From Jiri Pirko. 19) New dsa driver for qca8xxx chips, from John Crispin. 20) Implement RFC7559 ipv6 router solicitation backoff, from Maciej Żenczykowski. 21) Add L3 mode to ipvlan, from Mahesh Bandewar. 22) Support 802.1ad in mlx4, from Moshe Shemesh. 23) Support hardware LRO in mediatek driver, from Nelson Chang. 24) Add TC offloading to mlx5, from Or Gerlitz. 25) Convert various drivers to ethtool ksettings interfaces, from Philippe Reynes. 26) TX max rate limiting for cxgb4, from Rahul Lakkireddy. 27) NAPI support for ath10k, from Rajkumar Manoharan. 28) Support XDP in mlx5, from Rana Shahout and Saeed Mahameed. 29) UDP replicast support in TIPC, from Richard Alpe. 30) Per-queue statistics for qed driver, from Sudarsana Reddy Kalluru. 31) Support BQL in thunderx driver, from Sunil Goutham. 32) TSO support in alx driver, from Tobias Regnery. 33) Add stream parser engine and use it in kcm. 34) Support async DHCP replies in ipconfig module, from Uwe Kleine-König. 35) DSA port fast aging for mv88e6xxx driver, from Vivien Didelot. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1715 commits) mlxsw: switchx2: Fix misuse of hard_header_len mlxsw: spectrum: Fix misuse of hard_header_len net/faraday: Stop NCSI device on shutdown net/ncsi: Introduce ncsi_stop_dev() net/ncsi: Rework the channel monitoring net/ncsi: Allow to extend NCSI request properties net/ncsi: Rework request index allocation net/ncsi: Don't probe on the reserved channel ID (0x1f) net/ncsi: Introduce NCSI_RESERVED_CHANNEL net/ncsi: Avoid unused-value build warning from ia64-linux-gcc net: Add netdev all_adj_list refcnt propagation to fix panic net: phy: Add Edge-rate driver for Microsemi PHYs. vmxnet3: Wake queue from reset work i40e: avoid NULL pointer dereference and recursive errors on early PCI error qed: Add RoCE ll2 & GSI support qed: Add support for memory registeration verbs qed: Add support for QP verbs qed: PD,PKEY and CQ verb support qed: Add support for RoCE hw init qede: Add qedr framework ...
1605 lines
42 KiB
C
1605 lines
42 KiB
C
/*
|
|
*
|
|
* Copyright (c) 2011, Microsoft Corporation.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program; if not, write to the Free Software Foundation, Inc., 59 Temple
|
|
* Place - Suite 330, Boston, MA 02111-1307 USA.
|
|
*
|
|
* Authors:
|
|
* Haiyang Zhang <haiyangz@microsoft.com>
|
|
* Hank Janssen <hjanssen@microsoft.com>
|
|
* K. Y. Srinivasan <kys@microsoft.com>
|
|
*
|
|
*/
|
|
|
|
#ifndef _HYPERV_H
|
|
#define _HYPERV_H
|
|
|
|
#include <uapi/linux/hyperv.h>
|
|
#include <uapi/asm/hyperv.h>
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/scatterlist.h>
|
|
#include <linux/list.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/device.h>
|
|
#include <linux/mod_devicetable.h>
|
|
|
|
|
|
#define MAX_PAGE_BUFFER_COUNT 32
|
|
#define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */
|
|
|
|
#pragma pack(push, 1)
|
|
|
|
/* Single-page buffer */
|
|
struct hv_page_buffer {
|
|
u32 len;
|
|
u32 offset;
|
|
u64 pfn;
|
|
};
|
|
|
|
/* Multiple-page buffer */
|
|
struct hv_multipage_buffer {
|
|
/* Length and Offset determines the # of pfns in the array */
|
|
u32 len;
|
|
u32 offset;
|
|
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) * \
|
|
MAX_PAGE_BUFFER_COUNT))
|
|
#define MAX_MULTIPAGE_BUFFER_PACKET (0x18 + \
|
|
sizeof(struct hv_multipage_buffer))
|
|
|
|
|
|
#pragma pack(pop)
|
|
|
|
struct hv_ring_buffer {
|
|
/* Offset in bytes from the start of ring data below */
|
|
u32 write_index;
|
|
|
|
/* Offset in bytes from the start of ring data below */
|
|
u32 read_index;
|
|
|
|
u32 interrupt_mask;
|
|
|
|
/*
|
|
* Win8 uses some of the reserved bits to implement
|
|
* interrupt driven flow management. On the send side
|
|
* we can request that the receiver interrupt the sender
|
|
* when the ring transitions from being full to being able
|
|
* to handle a message of size "pending_send_sz".
|
|
*
|
|
* Add necessary state for this enhancement.
|
|
*/
|
|
u32 pending_send_sz;
|
|
|
|
u32 reserved1[12];
|
|
|
|
union {
|
|
struct {
|
|
u32 feat_pending_send_sz:1;
|
|
};
|
|
u32 value;
|
|
} feature_bits;
|
|
|
|
/* Pad it to PAGE_SIZE so that data starts on page boundary */
|
|
u8 reserved2[4028];
|
|
|
|
/*
|
|
* Ring data starts here + RingDataStartOffset
|
|
* !!! DO NOT place any fields below this !!!
|
|
*/
|
|
u8 buffer[0];
|
|
} __packed;
|
|
|
|
struct hv_ring_buffer_info {
|
|
struct hv_ring_buffer *ring_buffer;
|
|
u32 ring_size; /* Include the shared header */
|
|
spinlock_t ring_lock;
|
|
|
|
u32 ring_datasize; /* < ring_size */
|
|
u32 ring_data_startoffset;
|
|
u32 priv_write_index;
|
|
u32 priv_read_index;
|
|
};
|
|
|
|
/*
|
|
*
|
|
* hv_get_ringbuffer_availbytes()
|
|
*
|
|
* Get number of bytes available to read and to write to
|
|
* for the specified ring buffer
|
|
*/
|
|
static inline void
|
|
hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi,
|
|
u32 *read, u32 *write)
|
|
{
|
|
u32 read_loc, write_loc, dsize;
|
|
|
|
/* Capture the read/write indices before they changed */
|
|
read_loc = rbi->ring_buffer->read_index;
|
|
write_loc = rbi->ring_buffer->write_index;
|
|
dsize = rbi->ring_datasize;
|
|
|
|
*write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
|
|
read_loc - write_loc;
|
|
*read = dsize - *write;
|
|
}
|
|
|
|
static inline u32 hv_get_bytes_to_read(struct hv_ring_buffer_info *rbi)
|
|
{
|
|
u32 read_loc, write_loc, dsize, read;
|
|
|
|
dsize = rbi->ring_datasize;
|
|
read_loc = rbi->ring_buffer->read_index;
|
|
write_loc = READ_ONCE(rbi->ring_buffer->write_index);
|
|
|
|
read = write_loc >= read_loc ? (write_loc - read_loc) :
|
|
(dsize - read_loc) + write_loc;
|
|
|
|
return read;
|
|
}
|
|
|
|
static inline u32 hv_get_bytes_to_write(struct hv_ring_buffer_info *rbi)
|
|
{
|
|
u32 read_loc, write_loc, dsize, write;
|
|
|
|
dsize = rbi->ring_datasize;
|
|
read_loc = READ_ONCE(rbi->ring_buffer->read_index);
|
|
write_loc = rbi->ring_buffer->write_index;
|
|
|
|
write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
|
|
read_loc - write_loc;
|
|
return write;
|
|
}
|
|
|
|
/*
|
|
* VMBUS version is 32 bit entity broken up into
|
|
* two 16 bit quantities: major_number. minor_number.
|
|
*
|
|
* 0 . 13 (Windows Server 2008)
|
|
* 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_WIN10
|
|
|
|
/* Make maximum size of pipe payload of 16K */
|
|
#define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384)
|
|
|
|
/* Define PipeMode values. */
|
|
#define VMBUS_PIPE_TYPE_BYTE 0x00000000
|
|
#define VMBUS_PIPE_TYPE_MESSAGE 0x00000004
|
|
|
|
/* The size of the user defined data buffer for non-pipe offers. */
|
|
#define MAX_USER_DEFINED_BYTES 120
|
|
|
|
/* The size of the user defined data buffer for pipe offers. */
|
|
#define MAX_PIPE_USER_DEFINED_BYTES 116
|
|
|
|
/*
|
|
* At the center of the Channel Management library is the Channel Offer. This
|
|
* struct contains the fundamental information about an offer.
|
|
*/
|
|
struct vmbus_channel_offer {
|
|
uuid_le if_type;
|
|
uuid_le if_instance;
|
|
|
|
/*
|
|
* These two fields are not currently used.
|
|
*/
|
|
u64 reserved1;
|
|
u64 reserved2;
|
|
|
|
u16 chn_flags;
|
|
u16 mmio_megabytes; /* in bytes * 1024 * 1024 */
|
|
|
|
union {
|
|
/* Non-pipes: The user has MAX_USER_DEFINED_BYTES bytes. */
|
|
struct {
|
|
unsigned char user_def[MAX_USER_DEFINED_BYTES];
|
|
} std;
|
|
|
|
/*
|
|
* Pipes:
|
|
* The following sructure is an integrated pipe protocol, which
|
|
* is implemented on top of standard user-defined data. Pipe
|
|
* clients have MAX_PIPE_USER_DEFINED_BYTES left for their own
|
|
* use.
|
|
*/
|
|
struct {
|
|
u32 pipe_mode;
|
|
unsigned char user_def[MAX_PIPE_USER_DEFINED_BYTES];
|
|
} pipe;
|
|
} u;
|
|
/*
|
|
* The sub_channel_index is defined in win8.
|
|
*/
|
|
u16 sub_channel_index;
|
|
u16 reserved3;
|
|
} __packed;
|
|
|
|
/* Server Flags */
|
|
#define VMBUS_CHANNEL_ENUMERATE_DEVICE_INTERFACE 1
|
|
#define VMBUS_CHANNEL_SERVER_SUPPORTS_TRANSFER_PAGES 2
|
|
#define VMBUS_CHANNEL_SERVER_SUPPORTS_GPADLS 4
|
|
#define VMBUS_CHANNEL_NAMED_PIPE_MODE 0x10
|
|
#define VMBUS_CHANNEL_LOOPBACK_OFFER 0x100
|
|
#define VMBUS_CHANNEL_PARENT_OFFER 0x200
|
|
#define VMBUS_CHANNEL_REQUEST_MONITORED_NOTIFICATION 0x400
|
|
#define VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER 0x2000
|
|
|
|
struct vmpacket_descriptor {
|
|
u16 type;
|
|
u16 offset8;
|
|
u16 len8;
|
|
u16 flags;
|
|
u64 trans_id;
|
|
} __packed;
|
|
|
|
struct vmpacket_header {
|
|
u32 prev_pkt_start_offset;
|
|
struct vmpacket_descriptor descriptor;
|
|
} __packed;
|
|
|
|
struct vmtransfer_page_range {
|
|
u32 byte_count;
|
|
u32 byte_offset;
|
|
} __packed;
|
|
|
|
struct vmtransfer_page_packet_header {
|
|
struct vmpacket_descriptor d;
|
|
u16 xfer_pageset_id;
|
|
u8 sender_owns_set;
|
|
u8 reserved;
|
|
u32 range_cnt;
|
|
struct vmtransfer_page_range ranges[1];
|
|
} __packed;
|
|
|
|
struct vmgpadl_packet_header {
|
|
struct vmpacket_descriptor d;
|
|
u32 gpadl;
|
|
u32 reserved;
|
|
} __packed;
|
|
|
|
struct vmadd_remove_transfer_page_set {
|
|
struct vmpacket_descriptor d;
|
|
u32 gpadl;
|
|
u16 xfer_pageset_id;
|
|
u16 reserved;
|
|
} __packed;
|
|
|
|
/*
|
|
* This structure defines a range in guest physical space that can be made to
|
|
* look virtually contiguous.
|
|
*/
|
|
struct gpa_range {
|
|
u32 byte_count;
|
|
u32 byte_offset;
|
|
u64 pfn_array[0];
|
|
};
|
|
|
|
/*
|
|
* This is the format for an Establish Gpadl packet, which contains a handle by
|
|
* which this GPADL will be known and a set of GPA ranges associated with it.
|
|
* This can be converted to a MDL by the guest OS. If there are multiple GPA
|
|
* ranges, then the resulting MDL will be "chained," representing multiple VA
|
|
* ranges.
|
|
*/
|
|
struct vmestablish_gpadl {
|
|
struct vmpacket_descriptor d;
|
|
u32 gpadl;
|
|
u32 range_cnt;
|
|
struct gpa_range range[1];
|
|
} __packed;
|
|
|
|
/*
|
|
* This is the format for a Teardown Gpadl packet, which indicates that the
|
|
* GPADL handle in the Establish Gpadl packet will never be referenced again.
|
|
*/
|
|
struct vmteardown_gpadl {
|
|
struct vmpacket_descriptor d;
|
|
u32 gpadl;
|
|
u32 reserved; /* for alignment to a 8-byte boundary */
|
|
} __packed;
|
|
|
|
/*
|
|
* This is the format for a GPA-Direct packet, which contains a set of GPA
|
|
* ranges, in addition to commands and/or data.
|
|
*/
|
|
struct vmdata_gpa_direct {
|
|
struct vmpacket_descriptor d;
|
|
u32 reserved;
|
|
u32 range_cnt;
|
|
struct gpa_range range[1];
|
|
} __packed;
|
|
|
|
/* This is the format for a Additional Data Packet. */
|
|
struct vmadditional_data {
|
|
struct vmpacket_descriptor d;
|
|
u64 total_bytes;
|
|
u32 offset;
|
|
u32 byte_cnt;
|
|
unsigned char data[1];
|
|
} __packed;
|
|
|
|
union vmpacket_largest_possible_header {
|
|
struct vmpacket_descriptor simple_hdr;
|
|
struct vmtransfer_page_packet_header xfer_page_hdr;
|
|
struct vmgpadl_packet_header gpadl_hdr;
|
|
struct vmadd_remove_transfer_page_set add_rm_xfer_page_hdr;
|
|
struct vmestablish_gpadl establish_gpadl_hdr;
|
|
struct vmteardown_gpadl teardown_gpadl_hdr;
|
|
struct vmdata_gpa_direct data_gpa_direct_hdr;
|
|
};
|
|
|
|
#define VMPACKET_DATA_START_ADDRESS(__packet) \
|
|
(void *)(((unsigned char *)__packet) + \
|
|
((struct vmpacket_descriptor)__packet)->offset8 * 8)
|
|
|
|
#define VMPACKET_DATA_LENGTH(__packet) \
|
|
((((struct vmpacket_descriptor)__packet)->len8 - \
|
|
((struct vmpacket_descriptor)__packet)->offset8) * 8)
|
|
|
|
#define VMPACKET_TRANSFER_MODE(__packet) \
|
|
(((struct IMPACT)__packet)->type)
|
|
|
|
enum vmbus_packet_type {
|
|
VM_PKT_INVALID = 0x0,
|
|
VM_PKT_SYNCH = 0x1,
|
|
VM_PKT_ADD_XFER_PAGESET = 0x2,
|
|
VM_PKT_RM_XFER_PAGESET = 0x3,
|
|
VM_PKT_ESTABLISH_GPADL = 0x4,
|
|
VM_PKT_TEARDOWN_GPADL = 0x5,
|
|
VM_PKT_DATA_INBAND = 0x6,
|
|
VM_PKT_DATA_USING_XFER_PAGES = 0x7,
|
|
VM_PKT_DATA_USING_GPADL = 0x8,
|
|
VM_PKT_DATA_USING_GPA_DIRECT = 0x9,
|
|
VM_PKT_CANCEL_REQUEST = 0xa,
|
|
VM_PKT_COMP = 0xb,
|
|
VM_PKT_DATA_USING_ADDITIONAL_PKT = 0xc,
|
|
VM_PKT_ADDITIONAL_DATA = 0xd
|
|
};
|
|
|
|
#define VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED 1
|
|
|
|
|
|
/* Version 1 messages */
|
|
enum vmbus_channel_message_type {
|
|
CHANNELMSG_INVALID = 0,
|
|
CHANNELMSG_OFFERCHANNEL = 1,
|
|
CHANNELMSG_RESCIND_CHANNELOFFER = 2,
|
|
CHANNELMSG_REQUESTOFFERS = 3,
|
|
CHANNELMSG_ALLOFFERS_DELIVERED = 4,
|
|
CHANNELMSG_OPENCHANNEL = 5,
|
|
CHANNELMSG_OPENCHANNEL_RESULT = 6,
|
|
CHANNELMSG_CLOSECHANNEL = 7,
|
|
CHANNELMSG_GPADL_HEADER = 8,
|
|
CHANNELMSG_GPADL_BODY = 9,
|
|
CHANNELMSG_GPADL_CREATED = 10,
|
|
CHANNELMSG_GPADL_TEARDOWN = 11,
|
|
CHANNELMSG_GPADL_TORNDOWN = 12,
|
|
CHANNELMSG_RELID_RELEASED = 13,
|
|
CHANNELMSG_INITIATE_CONTACT = 14,
|
|
CHANNELMSG_VERSION_RESPONSE = 15,
|
|
CHANNELMSG_UNLOAD = 16,
|
|
CHANNELMSG_UNLOAD_RESPONSE = 17,
|
|
CHANNELMSG_18 = 18,
|
|
CHANNELMSG_19 = 19,
|
|
CHANNELMSG_20 = 20,
|
|
CHANNELMSG_TL_CONNECT_REQUEST = 21,
|
|
CHANNELMSG_COUNT
|
|
};
|
|
|
|
struct vmbus_channel_message_header {
|
|
enum vmbus_channel_message_type msgtype;
|
|
u32 padding;
|
|
} __packed;
|
|
|
|
/* Query VMBus Version parameters */
|
|
struct vmbus_channel_query_vmbus_version {
|
|
struct vmbus_channel_message_header header;
|
|
u32 version;
|
|
} __packed;
|
|
|
|
/* VMBus Version Supported parameters */
|
|
struct vmbus_channel_version_supported {
|
|
struct vmbus_channel_message_header header;
|
|
u8 version_supported;
|
|
} __packed;
|
|
|
|
/* Offer Channel parameters */
|
|
struct vmbus_channel_offer_channel {
|
|
struct vmbus_channel_message_header header;
|
|
struct vmbus_channel_offer offer;
|
|
u32 child_relid;
|
|
u8 monitorid;
|
|
/*
|
|
* win7 and beyond splits this field into a bit field.
|
|
*/
|
|
u8 monitor_allocated:1;
|
|
u8 reserved:7;
|
|
/*
|
|
* These are new fields added in win7 and later.
|
|
* Do not access these fields without checking the
|
|
* negotiated protocol.
|
|
*
|
|
* If "is_dedicated_interrupt" is set, we must not set the
|
|
* associated bit in the channel bitmap while sending the
|
|
* interrupt to the host.
|
|
*
|
|
* connection_id is to be used in signaling the host.
|
|
*/
|
|
u16 is_dedicated_interrupt:1;
|
|
u16 reserved1:15;
|
|
u32 connection_id;
|
|
} __packed;
|
|
|
|
/* Rescind Offer parameters */
|
|
struct vmbus_channel_rescind_offer {
|
|
struct vmbus_channel_message_header header;
|
|
u32 child_relid;
|
|
} __packed;
|
|
|
|
/*
|
|
* Request Offer -- no parameters, SynIC message contains the partition ID
|
|
* Set Snoop -- no parameters, SynIC message contains the partition ID
|
|
* Clear Snoop -- no parameters, SynIC message contains the partition ID
|
|
* All Offers Delivered -- no parameters, SynIC message contains the partition
|
|
* ID
|
|
* Flush Client -- no parameters, SynIC message contains the partition ID
|
|
*/
|
|
|
|
/* Open Channel parameters */
|
|
struct vmbus_channel_open_channel {
|
|
struct vmbus_channel_message_header header;
|
|
|
|
/* Identifies the specific VMBus channel that is being opened. */
|
|
u32 child_relid;
|
|
|
|
/* ID making a particular open request at a channel offer unique. */
|
|
u32 openid;
|
|
|
|
/* GPADL for the channel's ring buffer. */
|
|
u32 ringbuffer_gpadlhandle;
|
|
|
|
/*
|
|
* Starting with win8, this field will be used to specify
|
|
* the target virtual processor on which to deliver the interrupt for
|
|
* the host to guest communication.
|
|
* Prior to win8, incoming channel interrupts would only
|
|
* be delivered on cpu 0. Setting this value to 0 would
|
|
* preserve the earlier behavior.
|
|
*/
|
|
u32 target_vp;
|
|
|
|
/*
|
|
* The upstream ring buffer begins at offset zero in the memory
|
|
* described by RingBufferGpadlHandle. The downstream ring buffer
|
|
* follows it at this offset (in pages).
|
|
*/
|
|
u32 downstream_ringbuffer_pageoffset;
|
|
|
|
/* User-specific data to be passed along to the server endpoint. */
|
|
unsigned char userdata[MAX_USER_DEFINED_BYTES];
|
|
} __packed;
|
|
|
|
/* Open Channel Result parameters */
|
|
struct vmbus_channel_open_result {
|
|
struct vmbus_channel_message_header header;
|
|
u32 child_relid;
|
|
u32 openid;
|
|
u32 status;
|
|
} __packed;
|
|
|
|
/* Close channel parameters; */
|
|
struct vmbus_channel_close_channel {
|
|
struct vmbus_channel_message_header header;
|
|
u32 child_relid;
|
|
} __packed;
|
|
|
|
/* Channel Message GPADL */
|
|
#define GPADL_TYPE_RING_BUFFER 1
|
|
#define GPADL_TYPE_SERVER_SAVE_AREA 2
|
|
#define GPADL_TYPE_TRANSACTION 8
|
|
|
|
/*
|
|
* The number of PFNs in a GPADL message is defined by the number of
|
|
* pages that would be spanned by ByteCount and ByteOffset. If the
|
|
* implied number of PFNs won't fit in this packet, there will be a
|
|
* follow-up packet that contains more.
|
|
*/
|
|
struct vmbus_channel_gpadl_header {
|
|
struct vmbus_channel_message_header header;
|
|
u32 child_relid;
|
|
u32 gpadl;
|
|
u16 range_buflen;
|
|
u16 rangecount;
|
|
struct gpa_range range[0];
|
|
} __packed;
|
|
|
|
/* This is the followup packet that contains more PFNs. */
|
|
struct vmbus_channel_gpadl_body {
|
|
struct vmbus_channel_message_header header;
|
|
u32 msgnumber;
|
|
u32 gpadl;
|
|
u64 pfn[0];
|
|
} __packed;
|
|
|
|
struct vmbus_channel_gpadl_created {
|
|
struct vmbus_channel_message_header header;
|
|
u32 child_relid;
|
|
u32 gpadl;
|
|
u32 creation_status;
|
|
} __packed;
|
|
|
|
struct vmbus_channel_gpadl_teardown {
|
|
struct vmbus_channel_message_header header;
|
|
u32 child_relid;
|
|
u32 gpadl;
|
|
} __packed;
|
|
|
|
struct vmbus_channel_gpadl_torndown {
|
|
struct vmbus_channel_message_header header;
|
|
u32 gpadl;
|
|
} __packed;
|
|
|
|
struct vmbus_channel_relid_released {
|
|
struct vmbus_channel_message_header header;
|
|
u32 child_relid;
|
|
} __packed;
|
|
|
|
struct vmbus_channel_initiate_contact {
|
|
struct vmbus_channel_message_header header;
|
|
u32 vmbus_version_requested;
|
|
u32 target_vcpu; /* The VCPU the host should respond to */
|
|
u64 interrupt_page;
|
|
u64 monitor_page1;
|
|
u64 monitor_page2;
|
|
} __packed;
|
|
|
|
/* Hyper-V socket: guest's connect()-ing to host */
|
|
struct vmbus_channel_tl_connect_request {
|
|
struct vmbus_channel_message_header header;
|
|
uuid_le guest_endpoint_id;
|
|
uuid_le host_service_id;
|
|
} __packed;
|
|
|
|
struct vmbus_channel_version_response {
|
|
struct vmbus_channel_message_header header;
|
|
u8 version_supported;
|
|
} __packed;
|
|
|
|
enum vmbus_channel_state {
|
|
CHANNEL_OFFER_STATE,
|
|
CHANNEL_OPENING_STATE,
|
|
CHANNEL_OPEN_STATE,
|
|
CHANNEL_OPENED_STATE,
|
|
};
|
|
|
|
/*
|
|
* Represents each channel msg on the vmbus connection This is a
|
|
* variable-size data structure depending on the msg type itself
|
|
*/
|
|
struct vmbus_channel_msginfo {
|
|
/* Bookkeeping stuff */
|
|
struct list_head msglistentry;
|
|
|
|
/* So far, this is only used to handle gpadl body message */
|
|
struct list_head submsglist;
|
|
|
|
/* Synchronize the request/response if needed */
|
|
struct completion waitevent;
|
|
union {
|
|
struct vmbus_channel_version_supported version_supported;
|
|
struct vmbus_channel_open_result open_result;
|
|
struct vmbus_channel_gpadl_torndown gpadl_torndown;
|
|
struct vmbus_channel_gpadl_created gpadl_created;
|
|
struct vmbus_channel_version_response version_response;
|
|
} response;
|
|
|
|
u32 msgsize;
|
|
/*
|
|
* The channel message that goes out on the "wire".
|
|
* It will contain at minimum the VMBUS_CHANNEL_MESSAGE_HEADER header
|
|
*/
|
|
unsigned char msg[0];
|
|
};
|
|
|
|
struct vmbus_close_msg {
|
|
struct vmbus_channel_msginfo info;
|
|
struct vmbus_channel_close_channel msg;
|
|
};
|
|
|
|
/* Define connection identifier type. */
|
|
union hv_connection_id {
|
|
u32 asu32;
|
|
struct {
|
|
u32 id:24;
|
|
u32 reserved:8;
|
|
} u;
|
|
};
|
|
|
|
/* Definition of the hv_signal_event hypercall input structure. */
|
|
struct hv_input_signal_event {
|
|
union hv_connection_id connectionid;
|
|
u16 flag_number;
|
|
u16 rsvdz;
|
|
};
|
|
|
|
struct hv_input_signal_event_buffer {
|
|
u64 align8;
|
|
struct hv_input_signal_event event;
|
|
};
|
|
|
|
enum hv_signal_policy {
|
|
HV_SIGNAL_POLICY_DEFAULT = 0,
|
|
HV_SIGNAL_POLICY_EXPLICIT,
|
|
};
|
|
|
|
enum hv_numa_policy {
|
|
HV_BALANCED = 0,
|
|
HV_LOCALIZED,
|
|
};
|
|
|
|
enum vmbus_device_type {
|
|
HV_IDE = 0,
|
|
HV_SCSI,
|
|
HV_FC,
|
|
HV_NIC,
|
|
HV_ND,
|
|
HV_PCIE,
|
|
HV_FB,
|
|
HV_KBD,
|
|
HV_MOUSE,
|
|
HV_KVP,
|
|
HV_TS,
|
|
HV_HB,
|
|
HV_SHUTDOWN,
|
|
HV_FCOPY,
|
|
HV_BACKUP,
|
|
HV_DM,
|
|
HV_UNKOWN,
|
|
};
|
|
|
|
struct vmbus_device {
|
|
u16 dev_type;
|
|
uuid_le guid;
|
|
bool perf_device;
|
|
};
|
|
|
|
struct vmbus_channel {
|
|
struct list_head listentry;
|
|
|
|
struct hv_device *device_obj;
|
|
|
|
enum vmbus_channel_state state;
|
|
|
|
struct vmbus_channel_offer_channel offermsg;
|
|
/*
|
|
* These are based on the OfferMsg.MonitorId.
|
|
* Save it here for easy access.
|
|
*/
|
|
u8 monitor_grp;
|
|
u8 monitor_bit;
|
|
|
|
bool rescind; /* got rescind msg */
|
|
|
|
u32 ringbuffer_gpadlhandle;
|
|
|
|
/* Allocated memory for ring buffer */
|
|
void *ringbuffer_pages;
|
|
u32 ringbuffer_pagecount;
|
|
struct hv_ring_buffer_info outbound; /* send to parent */
|
|
struct hv_ring_buffer_info inbound; /* receive from parent */
|
|
spinlock_t inbound_lock;
|
|
|
|
struct vmbus_close_msg close_msg;
|
|
|
|
/* Channel callback are invoked in this workqueue context */
|
|
/* HANDLE dataWorkQueue; */
|
|
|
|
void (*onchannel_callback)(void *context);
|
|
void *channel_callback_context;
|
|
|
|
/*
|
|
* A channel can be marked for efficient (batched)
|
|
* reading:
|
|
* If batched_reading is set to "true", we read until the
|
|
* channel is empty and hold off interrupts from the host
|
|
* during the entire read process.
|
|
* If batched_reading is set to "false", the client is not
|
|
* going to perform batched reading.
|
|
*
|
|
* By default we will enable batched reading; specific
|
|
* drivers that don't want this behavior can turn it off.
|
|
*/
|
|
|
|
bool batched_reading;
|
|
|
|
bool is_dedicated_interrupt;
|
|
struct hv_input_signal_event_buffer sig_buf;
|
|
struct hv_input_signal_event *sig_event;
|
|
|
|
/*
|
|
* Starting with win8, this field will be used to specify
|
|
* the target virtual processor on which to deliver the interrupt for
|
|
* the host to guest communication.
|
|
* Prior to win8, incoming channel interrupts would only
|
|
* be delivered on cpu 0. Setting this value to 0 would
|
|
* 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);
|
|
|
|
/*
|
|
* Channel rescind callback. Some channels (the hvsock ones), need to
|
|
* register a callback which is invoked in vmbus_onoffer_rescind().
|
|
*/
|
|
void (*chn_rescind_callback)(struct vmbus_channel *channel);
|
|
|
|
/*
|
|
* 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;
|
|
/*
|
|
* On the channel send side, many of the VMBUS
|
|
* device drivers explicity serialize access to the
|
|
* outgoing ring buffer. Give more control to the
|
|
* VMBUS device drivers in terms how to serialize
|
|
* accesss to the outgoing ring buffer.
|
|
* The default behavior will be to aquire the
|
|
* ring lock to preserve the current behavior.
|
|
*/
|
|
bool acquire_ring_lock;
|
|
/*
|
|
* For performance critical channels (storage, networking
|
|
* etc,), Hyper-V has a mechanism to enhance the throughput
|
|
* at the expense of latency:
|
|
* When the host is to be signaled, we just set a bit in a shared page
|
|
* and this bit will be inspected by the hypervisor within a certain
|
|
* window and if the bit is set, the host will be signaled. The window
|
|
* of time is the monitor latency - currently around 100 usecs. This
|
|
* mechanism improves throughput by:
|
|
*
|
|
* A) Making the host more efficient - each time it wakes up,
|
|
* potentially it will process morev number of packets. The
|
|
* monitor latency allows a batch to build up.
|
|
* B) By deferring the hypercall to signal, we will also minimize
|
|
* the interrupts.
|
|
*
|
|
* Clearly, these optimizations improve throughput at the expense of
|
|
* latency. Furthermore, since the channel is shared for both
|
|
* control and data messages, control messages currently suffer
|
|
* unnecessary latency adversley impacting performance and boot
|
|
* time. To fix this issue, permit tagging the channel as being
|
|
* in "low latency" mode. In this mode, we will bypass the monitor
|
|
* mechanism.
|
|
*/
|
|
bool low_latency;
|
|
|
|
/*
|
|
* NUMA distribution policy:
|
|
* We support teo policies:
|
|
* 1) Balanced: Here all performance critical channels are
|
|
* distributed evenly amongst all the NUMA nodes.
|
|
* This policy will be the default policy.
|
|
* 2) Localized: All channels of a given instance of a
|
|
* performance critical service will be assigned CPUs
|
|
* within a selected NUMA node.
|
|
*/
|
|
enum hv_numa_policy affinity_policy;
|
|
|
|
};
|
|
|
|
static inline void set_channel_lock_state(struct vmbus_channel *c, bool state)
|
|
{
|
|
c->acquire_ring_lock = state;
|
|
}
|
|
|
|
static inline bool is_hvsock_channel(const struct vmbus_channel *c)
|
|
{
|
|
return !!(c->offermsg.offer.chn_flags &
|
|
VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER);
|
|
}
|
|
|
|
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_affinity_state(struct vmbus_channel *c,
|
|
enum hv_numa_policy policy)
|
|
{
|
|
c->affinity_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;
|
|
}
|
|
|
|
static inline void set_channel_pending_send_size(struct vmbus_channel *c,
|
|
u32 size)
|
|
{
|
|
c->outbound.ring_buffer->pending_send_sz = size;
|
|
}
|
|
|
|
static inline void set_low_latency_mode(struct vmbus_channel *c)
|
|
{
|
|
c->low_latency = true;
|
|
}
|
|
|
|
static inline void clear_low_latency_mode(struct vmbus_channel *c)
|
|
{
|
|
c->low_latency = false;
|
|
}
|
|
|
|
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));
|
|
|
|
void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel,
|
|
void (*chn_rescind_cb)(struct vmbus_channel *));
|
|
|
|
/*
|
|
* 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;
|
|
u16 dataoffset8;
|
|
u16 length8;
|
|
u16 flags;
|
|
u64 transactionid;
|
|
u32 reserved;
|
|
u32 rangecount;
|
|
struct hv_page_buffer range[MAX_PAGE_BUFFER_COUNT];
|
|
} __packed;
|
|
|
|
/* The format must be the same as struct vmdata_gpa_direct */
|
|
struct vmbus_channel_packet_multipage_buffer {
|
|
u16 type;
|
|
u16 dataoffset8;
|
|
u16 length8;
|
|
u16 flags;
|
|
u64 transactionid;
|
|
u32 reserved;
|
|
u32 rangecount; /* Always 1 in this case */
|
|
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,
|
|
u32 recv_ringbuffersize,
|
|
void *userdata,
|
|
u32 userdatalen,
|
|
void(*onchannel_callback)(void *context),
|
|
void *context);
|
|
|
|
extern void vmbus_close(struct vmbus_channel *channel);
|
|
|
|
extern int vmbus_sendpacket(struct vmbus_channel *channel,
|
|
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,
|
|
void *buffer,
|
|
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,
|
|
u32 *gpadl_handle);
|
|
|
|
extern int vmbus_teardown_gpadl(struct vmbus_channel *channel,
|
|
u32 gpadl_handle);
|
|
|
|
extern int vmbus_recvpacket(struct vmbus_channel *channel,
|
|
void *buffer,
|
|
u32 bufferlen,
|
|
u32 *buffer_actual_len,
|
|
u64 *requestid);
|
|
|
|
extern int vmbus_recvpacket_raw(struct vmbus_channel *channel,
|
|
void *buffer,
|
|
u32 bufferlen,
|
|
u32 *buffer_actual_len,
|
|
u64 *requestid);
|
|
|
|
|
|
extern void vmbus_ontimer(unsigned long data);
|
|
|
|
/* Base driver object */
|
|
struct hv_driver {
|
|
const char *name;
|
|
|
|
/*
|
|
* A hvsock offer, which has a VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER
|
|
* channel flag, actually doesn't mean a synthetic device because the
|
|
* offer's if_type/if_instance can change for every new hvsock
|
|
* connection.
|
|
*
|
|
* However, to facilitate the notification of new-offer/rescind-offer
|
|
* from vmbus driver to hvsock driver, we can handle hvsock offer as
|
|
* a special vmbus device, and hence we need the below flag to
|
|
* indicate if the driver is the hvsock driver or not: we need to
|
|
* specially treat the hvosck offer & driver in vmbus_match().
|
|
*/
|
|
bool hvsock;
|
|
|
|
/* the device type supported by this driver */
|
|
uuid_le dev_type;
|
|
const struct hv_vmbus_device_id *id_table;
|
|
|
|
struct device_driver driver;
|
|
|
|
int (*probe)(struct hv_device *, const struct hv_vmbus_device_id *);
|
|
int (*remove)(struct hv_device *);
|
|
void (*shutdown)(struct hv_device *);
|
|
|
|
};
|
|
|
|
/* Base device object */
|
|
struct hv_device {
|
|
/* the device type id of this device */
|
|
uuid_le dev_type;
|
|
|
|
/* the device instance id of this device */
|
|
uuid_le dev_instance;
|
|
u16 vendor_id;
|
|
u16 device_id;
|
|
|
|
struct device device;
|
|
|
|
struct vmbus_channel *channel;
|
|
};
|
|
|
|
|
|
static inline struct hv_device *device_to_hv_device(struct device *d)
|
|
{
|
|
return container_of(d, struct hv_device, device);
|
|
}
|
|
|
|
static inline struct hv_driver *drv_to_hv_drv(struct device_driver *d)
|
|
{
|
|
return container_of(d, struct hv_driver, driver);
|
|
}
|
|
|
|
static inline void hv_set_drvdata(struct hv_device *dev, void *data)
|
|
{
|
|
dev_set_drvdata(&dev->device, data);
|
|
}
|
|
|
|
static inline void *hv_get_drvdata(struct hv_device *dev)
|
|
{
|
|
return dev_get_drvdata(&dev->device);
|
|
}
|
|
|
|
/* Vmbus interface */
|
|
#define vmbus_driver_register(driver) \
|
|
__vmbus_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)
|
|
int __must_check __vmbus_driver_register(struct hv_driver *hv_driver,
|
|
struct module *owner,
|
|
const char *mod_name);
|
|
void vmbus_driver_unregister(struct hv_driver *hv_driver);
|
|
|
|
static inline const char *vmbus_dev_name(const struct hv_device *device_obj)
|
|
{
|
|
const struct kobject *kobj = &device_obj->device.kobj;
|
|
|
|
return kobj->name;
|
|
}
|
|
|
|
void vmbus_hvsock_device_unregister(struct vmbus_channel *channel);
|
|
|
|
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);
|
|
void vmbus_free_mmio(resource_size_t start, resource_size_t size);
|
|
int vmbus_cpu_number_to_vp_number(int cpu_number);
|
|
u64 hv_do_hypercall(u64 control, void *input, void *output);
|
|
|
|
/*
|
|
* GUID definitions of various offer types - services offered to the guest.
|
|
*/
|
|
|
|
/*
|
|
* Network GUID
|
|
* {f8615163-df3e-46c5-913f-f2d2f965ed0e}
|
|
*/
|
|
#define HV_NIC_GUID \
|
|
.guid = UUID_LE(0xf8615163, 0xdf3e, 0x46c5, 0x91, 0x3f, \
|
|
0xf2, 0xd2, 0xf9, 0x65, 0xed, 0x0e)
|
|
|
|
/*
|
|
* IDE GUID
|
|
* {32412632-86cb-44a2-9b5c-50d1417354f5}
|
|
*/
|
|
#define HV_IDE_GUID \
|
|
.guid = UUID_LE(0x32412632, 0x86cb, 0x44a2, 0x9b, 0x5c, \
|
|
0x50, 0xd1, 0x41, 0x73, 0x54, 0xf5)
|
|
|
|
/*
|
|
* SCSI GUID
|
|
* {ba6163d9-04a1-4d29-b605-72e2ffb1dc7f}
|
|
*/
|
|
#define HV_SCSI_GUID \
|
|
.guid = UUID_LE(0xba6163d9, 0x04a1, 0x4d29, 0xb6, 0x05, \
|
|
0x72, 0xe2, 0xff, 0xb1, 0xdc, 0x7f)
|
|
|
|
/*
|
|
* Shutdown GUID
|
|
* {0e0b6031-5213-4934-818b-38d90ced39db}
|
|
*/
|
|
#define HV_SHUTDOWN_GUID \
|
|
.guid = UUID_LE(0x0e0b6031, 0x5213, 0x4934, 0x81, 0x8b, \
|
|
0x38, 0xd9, 0x0c, 0xed, 0x39, 0xdb)
|
|
|
|
/*
|
|
* Time Synch GUID
|
|
* {9527E630-D0AE-497b-ADCE-E80AB0175CAF}
|
|
*/
|
|
#define HV_TS_GUID \
|
|
.guid = UUID_LE(0x9527e630, 0xd0ae, 0x497b, 0xad, 0xce, \
|
|
0xe8, 0x0a, 0xb0, 0x17, 0x5c, 0xaf)
|
|
|
|
/*
|
|
* Heartbeat GUID
|
|
* {57164f39-9115-4e78-ab55-382f3bd5422d}
|
|
*/
|
|
#define HV_HEART_BEAT_GUID \
|
|
.guid = UUID_LE(0x57164f39, 0x9115, 0x4e78, 0xab, 0x55, \
|
|
0x38, 0x2f, 0x3b, 0xd5, 0x42, 0x2d)
|
|
|
|
/*
|
|
* KVP GUID
|
|
* {a9a0f4e7-5a45-4d96-b827-8a841e8c03e6}
|
|
*/
|
|
#define HV_KVP_GUID \
|
|
.guid = UUID_LE(0xa9a0f4e7, 0x5a45, 0x4d96, 0xb8, 0x27, \
|
|
0x8a, 0x84, 0x1e, 0x8c, 0x03, 0xe6)
|
|
|
|
/*
|
|
* Dynamic memory GUID
|
|
* {525074dc-8985-46e2-8057-a307dc18a502}
|
|
*/
|
|
#define HV_DM_GUID \
|
|
.guid = UUID_LE(0x525074dc, 0x8985, 0x46e2, 0x80, 0x57, \
|
|
0xa3, 0x07, 0xdc, 0x18, 0xa5, 0x02)
|
|
|
|
/*
|
|
* Mouse GUID
|
|
* {cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a}
|
|
*/
|
|
#define HV_MOUSE_GUID \
|
|
.guid = UUID_LE(0xcfa8b69e, 0x5b4a, 0x4cc0, 0xb9, 0x8b, \
|
|
0x8b, 0xa1, 0xa1, 0xf3, 0xf9, 0x5a)
|
|
|
|
/*
|
|
* Keyboard GUID
|
|
* {f912ad6d-2b17-48ea-bd65-f927a61c7684}
|
|
*/
|
|
#define HV_KBD_GUID \
|
|
.guid = UUID_LE(0xf912ad6d, 0x2b17, 0x48ea, 0xbd, 0x65, \
|
|
0xf9, 0x27, 0xa6, 0x1c, 0x76, 0x84)
|
|
|
|
/*
|
|
* VSS (Backup/Restore) GUID
|
|
*/
|
|
#define HV_VSS_GUID \
|
|
.guid = UUID_LE(0x35fa2e29, 0xea23, 0x4236, 0x96, 0xae, \
|
|
0x3a, 0x6e, 0xba, 0xcb, 0xa4, 0x40)
|
|
/*
|
|
* Synthetic Video GUID
|
|
* {DA0A7802-E377-4aac-8E77-0558EB1073F8}
|
|
*/
|
|
#define HV_SYNTHVID_GUID \
|
|
.guid = UUID_LE(0xda0a7802, 0xe377, 0x4aac, 0x8e, 0x77, \
|
|
0x05, 0x58, 0xeb, 0x10, 0x73, 0xf8)
|
|
|
|
/*
|
|
* Synthetic FC GUID
|
|
* {2f9bcc4a-0069-4af3-b76b-6fd0be528cda}
|
|
*/
|
|
#define HV_SYNTHFC_GUID \
|
|
.guid = UUID_LE(0x2f9bcc4a, 0x0069, 0x4af3, 0xb7, 0x6b, \
|
|
0x6f, 0xd0, 0xbe, 0x52, 0x8c, 0xda)
|
|
|
|
/*
|
|
* Guest File Copy Service
|
|
* {34D14BE3-DEE4-41c8-9AE7-6B174977C192}
|
|
*/
|
|
|
|
#define HV_FCOPY_GUID \
|
|
.guid = UUID_LE(0x34d14be3, 0xdee4, 0x41c8, 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 = UUID_LE(0x8c2eaf3d, 0x32a7, 0x4b09, 0xab, 0x99, \
|
|
0xbd, 0x1f, 0x1c, 0x86, 0xb5, 0x01)
|
|
|
|
/*
|
|
* PCI Express Pass Through
|
|
* {44C4F61D-4444-4400-9D52-802E27EDE19F}
|
|
*/
|
|
|
|
#define HV_PCIE_GUID \
|
|
.guid = UUID_LE(0x44c4f61d, 0x4444, 0x4400, 0x9d, 0x52, \
|
|
0x80, 0x2e, 0x27, 0xed, 0xe1, 0x9f)
|
|
|
|
/*
|
|
* Linux doesn't support the 3 devices: the first two are for
|
|
* Automatic Virtual Machine Activation, and the third is for
|
|
* Remote Desktop Virtualization.
|
|
* {f8e65716-3cb3-4a06-9a60-1889c5cccab5}
|
|
* {3375baf4-9e15-4b30-b765-67acb10d607b}
|
|
* {276aacf4-ac15-426c-98dd-7521ad3f01fe}
|
|
*/
|
|
|
|
#define HV_AVMA1_GUID \
|
|
.guid = UUID_LE(0xf8e65716, 0x3cb3, 0x4a06, 0x9a, 0x60, \
|
|
0x18, 0x89, 0xc5, 0xcc, 0xca, 0xb5)
|
|
|
|
#define HV_AVMA2_GUID \
|
|
.guid = UUID_LE(0x3375baf4, 0x9e15, 0x4b30, 0xb7, 0x65, \
|
|
0x67, 0xac, 0xb1, 0x0d, 0x60, 0x7b)
|
|
|
|
#define HV_RDV_GUID \
|
|
.guid = UUID_LE(0x276aacf4, 0xac15, 0x426c, 0x98, 0xdd, \
|
|
0x75, 0x21, 0xad, 0x3f, 0x01, 0xfe)
|
|
|
|
/*
|
|
* Common header for Hyper-V ICs
|
|
*/
|
|
|
|
#define ICMSGTYPE_NEGOTIATE 0
|
|
#define ICMSGTYPE_HEARTBEAT 1
|
|
#define ICMSGTYPE_KVPEXCHANGE 2
|
|
#define ICMSGTYPE_SHUTDOWN 3
|
|
#define ICMSGTYPE_TIMESYNC 4
|
|
#define ICMSGTYPE_VSS 5
|
|
|
|
#define ICMSGHDRFLAG_TRANSACTION 1
|
|
#define ICMSGHDRFLAG_REQUEST 2
|
|
#define ICMSGHDRFLAG_RESPONSE 4
|
|
|
|
|
|
/*
|
|
* While we want to handle util services as regular devices,
|
|
* there is only one instance of each of these services; so
|
|
* we statically allocate the service specific state.
|
|
*/
|
|
|
|
struct hv_util_service {
|
|
u8 *recv_buffer;
|
|
void *channel;
|
|
void (*util_cb)(void *);
|
|
int (*util_init)(struct hv_util_service *);
|
|
void (*util_deinit)(void);
|
|
};
|
|
|
|
struct vmbuspipe_hdr {
|
|
u32 flags;
|
|
u32 msgsize;
|
|
} __packed;
|
|
|
|
struct ic_version {
|
|
u16 major;
|
|
u16 minor;
|
|
} __packed;
|
|
|
|
struct icmsg_hdr {
|
|
struct ic_version icverframe;
|
|
u16 icmsgtype;
|
|
struct ic_version icvermsg;
|
|
u16 icmsgsize;
|
|
u32 status;
|
|
u8 ictransaction_id;
|
|
u8 icflags;
|
|
u8 reserved[2];
|
|
} __packed;
|
|
|
|
struct icmsg_negotiate {
|
|
u16 icframe_vercnt;
|
|
u16 icmsg_vercnt;
|
|
u32 reserved;
|
|
struct ic_version icversion_data[1]; /* any size array */
|
|
} __packed;
|
|
|
|
struct shutdown_msg_data {
|
|
u32 reason_code;
|
|
u32 timeout_seconds;
|
|
u32 flags;
|
|
u8 display_message[2048];
|
|
} __packed;
|
|
|
|
struct heartbeat_msg_data {
|
|
u64 seq_num;
|
|
u32 reserved[8];
|
|
} __packed;
|
|
|
|
/* Time Sync IC defs */
|
|
#define ICTIMESYNCFLAG_PROBE 0
|
|
#define ICTIMESYNCFLAG_SYNC 1
|
|
#define ICTIMESYNCFLAG_SAMPLE 2
|
|
|
|
#ifdef __x86_64__
|
|
#define WLTIMEDELTA 116444736000000000L /* in 100ns unit */
|
|
#else
|
|
#define WLTIMEDELTA 116444736000000000LL
|
|
#endif
|
|
|
|
struct ictimesync_data {
|
|
u64 parenttime;
|
|
u64 childtime;
|
|
u64 roundtriptime;
|
|
u8 flags;
|
|
} __packed;
|
|
|
|
struct ictimesync_ref_data {
|
|
u64 parenttime;
|
|
u64 vmreferencetime;
|
|
u8 flags;
|
|
char leapflags;
|
|
char stratum;
|
|
u8 reserved[3];
|
|
} __packed;
|
|
|
|
struct hyperv_service_callback {
|
|
u8 msg_type;
|
|
char *log_msg;
|
|
uuid_le data;
|
|
struct vmbus_channel *channel;
|
|
void (*callback) (void *context);
|
|
};
|
|
|
|
#define MAX_SRV_VER 0x7ffffff
|
|
extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *,
|
|
struct icmsg_negotiate *, u8 *, int,
|
|
int);
|
|
|
|
void hv_event_tasklet_disable(struct vmbus_channel *channel);
|
|
void hv_event_tasklet_enable(struct vmbus_channel *channel);
|
|
|
|
void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
|
|
|
|
/*
|
|
* Negotiated version with the Host.
|
|
*/
|
|
|
|
extern __u32 vmbus_proto_version;
|
|
|
|
int vmbus_send_tl_connect_request(const uuid_le *shv_guest_servie_id,
|
|
const uuid_le *shv_host_servie_id);
|
|
void vmbus_set_event(struct vmbus_channel *channel);
|
|
|
|
/* Get the start of the ring buffer. */
|
|
static inline void *
|
|
hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info)
|
|
{
|
|
return (void *)ring_info->ring_buffer->buffer;
|
|
}
|
|
|
|
/*
|
|
* To optimize the flow management on the send-side,
|
|
* when the sender is blocked because of lack of
|
|
* sufficient space in the ring buffer, potential the
|
|
* consumer of the ring buffer can signal the producer.
|
|
* This is controlled by the following parameters:
|
|
*
|
|
* 1. pending_send_sz: This is the size in bytes that the
|
|
* producer is trying to send.
|
|
* 2. The feature bit feat_pending_send_sz set to indicate if
|
|
* the consumer of the ring will signal when the ring
|
|
* state transitions from being full to a state where
|
|
* there is room for the producer to send the pending packet.
|
|
*/
|
|
|
|
static inline bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi)
|
|
{
|
|
u32 cur_write_sz;
|
|
u32 pending_sz;
|
|
|
|
/*
|
|
* Issue a full memory barrier before making the signaling decision.
|
|
* Here is the reason for having this barrier:
|
|
* If the reading of the pend_sz (in this function)
|
|
* were to be reordered and read before we commit the new read
|
|
* index (in the calling function) we could
|
|
* have a problem. If the host were to set the pending_sz after we
|
|
* have sampled pending_sz and go to sleep before we commit the
|
|
* read index, we could miss sending the interrupt. Issue a full
|
|
* memory barrier to address this.
|
|
*/
|
|
virt_mb();
|
|
|
|
pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
|
|
/* If the other end is not blocked on write don't bother. */
|
|
if (pending_sz == 0)
|
|
return false;
|
|
|
|
cur_write_sz = hv_get_bytes_to_write(rbi);
|
|
|
|
if (cur_write_sz >= pending_sz)
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* An API to support in-place processing of incoming VMBUS packets.
|
|
*/
|
|
#define VMBUS_PKT_TRAILER 8
|
|
|
|
static inline struct vmpacket_descriptor *
|
|
get_next_pkt_raw(struct vmbus_channel *channel)
|
|
{
|
|
struct hv_ring_buffer_info *ring_info = &channel->inbound;
|
|
u32 read_loc = ring_info->priv_read_index;
|
|
void *ring_buffer = hv_get_ring_buffer(ring_info);
|
|
struct vmpacket_descriptor *cur_desc;
|
|
u32 packetlen;
|
|
u32 dsize = ring_info->ring_datasize;
|
|
u32 delta = read_loc - ring_info->ring_buffer->read_index;
|
|
u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta);
|
|
|
|
if (bytes_avail_toread < sizeof(struct vmpacket_descriptor))
|
|
return NULL;
|
|
|
|
if ((read_loc + sizeof(*cur_desc)) > dsize)
|
|
return NULL;
|
|
|
|
cur_desc = ring_buffer + read_loc;
|
|
packetlen = cur_desc->len8 << 3;
|
|
|
|
/*
|
|
* If the packet under consideration is wrapping around,
|
|
* return failure.
|
|
*/
|
|
if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > (dsize - 1))
|
|
return NULL;
|
|
|
|
return cur_desc;
|
|
}
|
|
|
|
/*
|
|
* A helper function to step through packets "in-place"
|
|
* This API is to be called after each successful call
|
|
* get_next_pkt_raw().
|
|
*/
|
|
static inline void put_pkt_raw(struct vmbus_channel *channel,
|
|
struct vmpacket_descriptor *desc)
|
|
{
|
|
struct hv_ring_buffer_info *ring_info = &channel->inbound;
|
|
u32 read_loc = ring_info->priv_read_index;
|
|
u32 packetlen = desc->len8 << 3;
|
|
u32 dsize = ring_info->ring_datasize;
|
|
|
|
if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize)
|
|
BUG();
|
|
/*
|
|
* Include the packet trailer.
|
|
*/
|
|
ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
|
|
}
|
|
|
|
/*
|
|
* This call commits the read index and potentially signals the host.
|
|
* Here is the pattern for using the "in-place" consumption APIs:
|
|
*
|
|
* while (get_next_pkt_raw() {
|
|
* process the packet "in-place";
|
|
* put_pkt_raw();
|
|
* }
|
|
* if (packets processed in place)
|
|
* commit_rd_index();
|
|
*/
|
|
static inline void commit_rd_index(struct vmbus_channel *channel)
|
|
{
|
|
struct hv_ring_buffer_info *ring_info = &channel->inbound;
|
|
/*
|
|
* Make sure all reads are done before we update the read index since
|
|
* the writer may start writing to the read area once the read index
|
|
* is updated.
|
|
*/
|
|
virt_rmb();
|
|
ring_info->ring_buffer->read_index = ring_info->priv_read_index;
|
|
|
|
if (hv_need_to_signal_on_read(ring_info))
|
|
vmbus_set_event(channel);
|
|
}
|
|
|
|
|
|
#endif /* _HYPERV_H */
|