diff options
Diffstat (limited to 'include/linux/hyperv.h')
| -rw-r--r-- | include/linux/hyperv.h | 786 |
1 files changed, 507 insertions, 279 deletions
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f0885cc01db6..dfc516c1c719 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1,25 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * * 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 @@ -27,6 +14,7 @@ #include <uapi/linux/hyperv.h> +#include <linux/mm.h> #include <linux/types.h> #include <linux/scatterlist.h> #include <linux/list.h> @@ -36,12 +24,55 @@ #include <linux/mod_devicetable.h> #include <linux/interrupt.h> #include <linux/reciprocal_div.h> +#include <hyperv/hvhdk.h> #define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ #pragma pack(push, 1) +/* + * Types for GPADL, decides is how GPADL header is created. + * + * It doesn't make much difference between BUFFER and RING if PAGE_SIZE is the + * same as HV_HYP_PAGE_SIZE. + * + * If PAGE_SIZE is bigger than HV_HYP_PAGE_SIZE, the headers of ring buffers + * will be of PAGE_SIZE, however, only the first HV_HYP_PAGE will be put + * into gpadl, therefore the number for HV_HYP_PAGE and the indexes of each + * HV_HYP_PAGE will be different between different types of GPADL, for example + * if PAGE_SIZE is 64K: + * + * BUFFER: + * + * gva: |-- 64k --|-- 64k --| ... | + * gpa: | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k | + * index: 0 1 2 15 16 17 18 .. 31 32 ... + * | | ... | | | ... | ... + * v V V V V V + * gpadl: | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k | ... | + * index: 0 1 2 ... 15 16 17 18 .. 31 32 ... + * + * RING: + * + * | header | data | header | data | + * gva: |-- 64k --|-- 64k --| ... |-- 64k --|-- 64k --| ... | + * gpa: | 4k | .. | 4k | 4k | ... | 4k | ... | 4k | .. | 4k | .. | ... | + * index: 0 1 16 17 18 31 ... n n+1 n+16 ... 2n + * | / / / | / / + * | / / / | / / + * | / / ... / ... | / ... / + * | / / / | / / + * | / / / | / / + * V V V V V V v + * gpadl: | 4k | 4k | ... | ... | 4k | 4k | ... | + * index: 0 1 2 ... 16 ... n-15 n-14 n-13 ... 2n-30 + */ +enum hv_gpadl_type { + HV_GPADL_BUFFER, + HV_GPADL_RING +}; + /* Single-page buffer */ struct hv_page_buffer { u32 len; @@ -124,15 +155,39 @@ struct hv_ring_buffer { } feature_bits; /* Pad it to PAGE_SIZE so that data starts on page boundary */ - u8 reserved2[4028]; + u8 reserved2[PAGE_SIZE - 68]; /* * Ring data starts here + RingDataStartOffset * !!! DO NOT place any fields below this !!! */ - u8 buffer[0]; + u8 buffer[]; } __packed; + +/* + * If the requested ring buffer size is at least 8 times the size of the + * header, steal space from the ring buffer for the header. Otherwise, add + * space for the header so that is doesn't take too much of the ring buffer + * space. + * + * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a + * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring + * buffer size (such as 128 Kbytes) and so end up making a nearly twice as + * large allocation that will be almost half wasted. As a contrasting example, + * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the + * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring. + * In this latter case, we must add 64 Kbytes for the header and not worry + * about what's wasted. + */ +#define VMBUS_HEADER_ADJ(payload_sz) \ + ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \ + 0 : sizeof(struct hv_ring_buffer)) + +/* Calculate the proper size of a ringbuffer, it must be page-aligned */ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \ + (payload_sz)) + struct hv_ring_buffer_info { struct hv_ring_buffer *ring_buffer; u32 ring_size; /* Include the shared header */ @@ -141,6 +196,15 @@ struct hv_ring_buffer_info { u32 ring_datasize; /* < ring_size */ u32 priv_read_index; + /* + * The ring buffer mutex lock. This lock prevents the ring buffer from + * being freed while the ring buffer is being accessed. + */ + struct mutex ring_buffer_mutex; + + /* Buffer that holds a copy of an incoming host packet */ + void *pkt_buffer; + u32 pkt_buffer_size; }; @@ -186,23 +250,33 @@ static inline u32 hv_get_avail_to_write_percent( * 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) + * 1 . 1 (Windows 7, WS2008 R2) + * 2 . 4 (Windows 8, WS2012) + * 3 . 0 (Windows 8.1, WS2012 R2) * 4 . 0 (Windows 10) + * 4 . 1 (Windows 10 RS3) * 5 . 0 (Newer Windows 10) + * 5 . 1 (Windows 10 RS4) + * 5 . 2 (Windows Server 2019, RS5) + * 5 . 3 (Windows Server 2022) + * + * The WS2008 and WIN7 versions are listed here for + * completeness but are no longer supported in the + * Linux kernel. */ -#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_WIN10_V5 ((5 << 16) | (0)) - -#define VERSION_INVAL -1 - -#define VERSION_CURRENT VERSION_WIN10_V5 +#define VMBUS_MAKE_VERSION(MAJ, MIN) ((((u32)MAJ) << 16) | (MIN)) +#define VERSION_WS2008 VMBUS_MAKE_VERSION(0, 13) +#define VERSION_WIN7 VMBUS_MAKE_VERSION(1, 1) +#define VERSION_WIN8 VMBUS_MAKE_VERSION(2, 4) +#define VERSION_WIN8_1 VMBUS_MAKE_VERSION(3, 0) +#define VERSION_WIN10 VMBUS_MAKE_VERSION(4, 0) +#define VERSION_WIN10_V4_1 VMBUS_MAKE_VERSION(4, 1) +#define VERSION_WIN10_V5 VMBUS_MAKE_VERSION(5, 0) +#define VERSION_WIN10_V5_1 VMBUS_MAKE_VERSION(5, 1) +#define VERSION_WIN10_V5_2 VMBUS_MAKE_VERSION(5, 2) +#define VERSION_WIN10_V5_3 VMBUS_MAKE_VERSION(5, 3) +#define VERSION_WIN10_V6_0 VMBUS_MAKE_VERSION(6, 0) /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) @@ -222,8 +296,8 @@ static inline u32 hv_get_avail_to_write_percent( * struct contains the fundamental information about an offer. */ struct vmbus_channel_offer { - uuid_le if_type; - uuid_le if_instance; + guid_t if_type; + guid_t if_instance; /* * These two fields are not currently used. @@ -242,7 +316,7 @@ struct vmbus_channel_offer { /* * Pipes: - * The following sructure is an integrated pipe protocol, which + * The following structure 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. @@ -253,21 +327,32 @@ struct vmbus_channel_offer { } pipe; } u; /* - * The sub_channel_index is defined in win8. + * The sub_channel_index is defined in Win8: a value of zero means a + * primary channel and a value of non-zero means a sub-channel. + * + * Before Win8, the field is reserved, meaning it's always zero. */ 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 +#define VMBUS_CHANNEL_ENUMERATE_DEVICE_INTERFACE 0x0001 +/* + * This flag indicates that the channel is offered by the paravisor, and must + * use encrypted memory for the channel ring buffer. + */ +#define VMBUS_CHANNEL_CONFIDENTIAL_RING_BUFFER 0x0002 +/* + * This flag indicates that the channel is offered by the paravisor, and must + * use encrypted memory for GPA direct packets and additional GPADLs. + */ +#define VMBUS_CHANNEL_CONFIDENTIAL_EXTERNAL_MEMORY 0x0004 +#define VMBUS_CHANNEL_NAMED_PIPE_MODE 0x0010 +#define VMBUS_CHANNEL_LOOPBACK_OFFER 0x0100 +#define VMBUS_CHANNEL_PARENT_OFFER 0x0200 +#define VMBUS_CHANNEL_REQUEST_MONITORED_NOTIFICATION 0x0400 +#define VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER 0x2000 struct vmpacket_descriptor { u16 type; @@ -293,20 +378,7 @@ struct vmtransfer_page_packet_header { 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; + struct vmtransfer_page_range ranges[]; } __packed; /* @@ -316,34 +388,10 @@ struct vmadd_remove_transfer_page_set { struct gpa_range { u32 byte_count; u32 byte_offset; - u64 pfn_array[0]; + u64 pfn_array[]; }; /* - * 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. */ @@ -354,25 +402,6 @@ struct vmdata_gpa_direct { 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) @@ -428,9 +457,15 @@ enum vmbus_channel_message_type { CHANNELMSG_19 = 19, CHANNELMSG_20 = 20, CHANNELMSG_TL_CONNECT_REQUEST = 21, + CHANNELMSG_MODIFYCHANNEL = 22, + CHANNELMSG_TL_CONNECT_RESULT = 23, + CHANNELMSG_MODIFYCHANNEL_RESPONSE = 24, CHANNELMSG_COUNT }; +/* Hyper-V supports about 2048 channels, and the RELIDs start with 1. */ +#define INVALID_RELID U32_MAX + struct vmbus_channel_message_header { enum vmbus_channel_message_type msgtype; u32 padding; @@ -481,12 +516,6 @@ struct vmbus_channel_rescind_offer { u32 child_relid; } __packed; -static inline u32 -hv_ringbuffer_pending_size(const struct hv_ring_buffer_info *rbi) -{ - return rbi->ring_buffer->pending_send_sz; -} - /* * Request Offer -- no parameters, SynIC message contains the partition ID * Set Snoop -- no parameters, SynIC message contains the partition ID @@ -538,6 +567,13 @@ struct vmbus_channel_open_result { u32 status; } __packed; +/* Modify Channel Result parameters */ +struct vmbus_channel_modifychannel_response { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 status; +} __packed; + /* Close channel parameters; */ struct vmbus_channel_close_channel { struct vmbus_channel_message_header header; @@ -561,7 +597,7 @@ struct vmbus_channel_gpadl_header { u32 gpadl; u16 range_buflen; u16 rangecount; - struct gpa_range range[0]; + struct gpa_range range[]; } __packed; /* This is the followup packet that contains more PFNs. */ @@ -569,7 +605,7 @@ struct vmbus_channel_gpadl_body { struct vmbus_channel_message_header header; u32 msgnumber; u32 gpadl; - u64 pfn[0]; + u64 pfn[]; } __packed; struct vmbus_channel_gpadl_created { @@ -595,6 +631,12 @@ struct vmbus_channel_relid_released { u32 child_relid; } __packed; +/* + * Used by the paravisor only, means that the encrypted ring buffers and + * the encrypted external memory are supported + */ +#define VMBUS_FEATURE_FLAG_CONFIDENTIAL_CHANNELS 0x10 + struct vmbus_channel_initiate_contact { struct vmbus_channel_message_header header; u32 vmbus_version_requested; @@ -603,8 +645,9 @@ struct vmbus_channel_initiate_contact { u64 interrupt_page; struct { u8 msg_sint; - u8 padding1[3]; - u32 padding2; + u8 msg_vtl; + u8 reserved[2]; + u32 feature_flags; /* VMBus version 6.0 */ }; }; u64 monitor_page1; @@ -614,8 +657,15 @@ struct vmbus_channel_initiate_contact { /* 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; + guid_t guest_endpoint_id; + guid_t host_service_id; +} __packed; + +/* Modify Channel parameters, cf. vmbus_send_modifychannel() */ +struct vmbus_channel_modifychannel { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 target_vp; } __packed; struct vmbus_channel_version_response { @@ -663,6 +713,7 @@ struct vmbus_channel_msginfo { struct vmbus_channel_gpadl_torndown gpadl_torndown; struct vmbus_channel_gpadl_created gpadl_created; struct vmbus_channel_version_response version_response; + struct vmbus_channel_modifychannel_response modify_response; } response; u32 msgsize; @@ -670,26 +721,7 @@ struct vmbus_channel_msginfo { * 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; -}; - -enum hv_numa_policy { - HV_BALANCED = 0, - HV_LOCALIZED, + unsigned char msg[]; }; enum vmbus_device_type { @@ -712,10 +744,44 @@ enum vmbus_device_type { HV_UNKNOWN, }; +/* + * Provides request ids for VMBus. Encapsulates guest memory + * addresses and stores the next available slot in req_arr + * to generate new ids in constant time. + */ +struct vmbus_requestor { + u64 *req_arr; + unsigned long *req_bitmap; /* is a given slot available? */ + u32 size; + u64 next_request_id; + spinlock_t req_lock; /* provides atomicity */ +}; + +#define VMBUS_NO_RQSTOR U64_MAX +#define VMBUS_RQST_ERROR (U64_MAX - 1) +#define VMBUS_RQST_ADDR_ANY U64_MAX +/* NetVSC-specific */ +#define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2) +/* StorVSC-specific */ +#define VMBUS_RQST_INIT (U64_MAX - 2) +#define VMBUS_RQST_RESET (U64_MAX - 3) + struct vmbus_device { + /* preferred ring buffer size in KB, 0 means no preferred size for this device */ + size_t pref_ring_size; u16 dev_type; - uuid_le guid; + guid_t guid; bool perf_device; + bool allowed_in_isolated; +}; + +#define VMBUS_DEFAULT_MAX_PKT_SIZE 4096 + +struct vmbus_gpadl { + u32 gpadl_handle; + u32 size; + void *buffer; + bool decrypted; }; struct vmbus_channel { @@ -734,9 +800,10 @@ struct vmbus_channel { u8 monitor_bit; bool rescind; /* got rescind msg */ + bool rescind_ref; /* got rescind msg, got channel reference */ struct completion rescind_event; - u32 ringbuffer_gpadlhandle; + struct vmbus_gpadl ringbuffer_gpadlhandle; /* Allocated memory for ring buffer */ struct page *ringbuffer_page; @@ -745,17 +812,39 @@ struct vmbus_channel { struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ - struct vmbus_close_msg close_msg; + struct vmbus_channel_close_channel close_msg; /* Statistics */ u64 interrupts; /* Host to Guest interrupts */ u64 sig_events; /* Guest to Host events */ + /* + * Guest to host interrupts caused by the outbound ring buffer changing + * from empty to not empty. + */ + u64 intr_out_empty; + + /* + * Indicates that a full outbound ring buffer was encountered. The flag + * is set to true when a full outbound ring buffer is encountered and + * set to false when a write to the outbound ring buffer is completed. + */ + bool out_full_flag; + /* Channel callback's invoked in softirq context */ struct tasklet_struct callback_event; void (*onchannel_callback)(void *context); void *channel_callback_context; + void (*change_target_cpu_callback)(struct vmbus_channel *channel, + u32 old, u32 new); + + /* + * Synchronize channel scheduling and channel removal; see the inline + * comments in vmbus_chan_sched() and vmbus_reset_channel_cb(). + */ + spinlock_t sched_lock; + /* * A channel can be marked for one of three modes of reading: * BATCHED - callback called from taslket and should read @@ -777,30 +866,24 @@ struct vmbus_channel { u64 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. + * Starting with win8, this field will be used to specify the + * target CPU 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 + * The support for sub-channels is implemented as an extension * 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 + * The guest is free to ask for sub-channels to be offered 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 @@ -821,12 +904,6 @@ struct vmbus_channel { 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; @@ -839,11 +916,6 @@ struct vmbus_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; /* * Defer freeing channel until after all cpu's have @@ -867,7 +939,7 @@ struct vmbus_channel { * mechanism improves throughput by: * * A) Making the host more efficient - each time it wakes up, - * potentially it will process morev number of packets. The + * potentially it will process more 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. @@ -875,26 +947,21 @@ struct vmbus_channel { * 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 + * unnecessary latency adversely 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; + bool probe_done; + /* - * NUMA distribution policy: - * We support two 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. + * Cache the device ID here for easy access; this is useful, in + * particular, in situations where the channel's device_obj has + * not been allocated/initialized yet. */ - enum hv_numa_policy affinity_policy; - - bool probe_done; + u16 device_id; /* * We must offload the handling of the primary/sub channels @@ -903,18 +970,107 @@ struct vmbus_channel { * vmbus_connection.work_queue and hang: see vmbus_process_offer(). */ struct work_struct add_channel_work; + + /* + * Guest to host interrupts caused by the inbound ring buffer changing + * from full to not full while a packet is waiting. + */ + u64 intr_in_full; + + /* + * The total number of write operations that encountered a full + * outbound ring buffer. + */ + u64 out_full_total; + + /* + * The number of write operations that were the first to encounter a + * full outbound ring buffer. + */ + u64 out_full_first; + + /* enabling/disabling fuzz testing on the channel (default is false)*/ + bool fuzz_testing_state; + + /* + * Interrupt delay will delay the guest from emptying the ring buffer + * for a specific amount of time. The delay is in microseconds and will + * be between 1 to a maximum of 1000, its default is 0 (no delay). + * The Message delay will delay guest reading on a per message basis + * in microseconds between 1 to 1000 with the default being 0 + * (no delay). + */ + u32 fuzz_testing_interrupt_delay; + u32 fuzz_testing_message_delay; + + /* callback to generate a request ID from a request address */ + u64 (*next_request_id_callback)(struct vmbus_channel *channel, u64 rqst_addr); + /* callback to retrieve a request address from a request ID */ + u64 (*request_addr_callback)(struct vmbus_channel *channel, u64 rqst_id); + + /* request/transaction ids for VMBus */ + struct vmbus_requestor requestor; + u32 rqstor_size; + + /* The max size of a packet on this channel */ + u32 max_pkt_size; + + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + + /* boolean to control visibility of sysfs for ring buffer */ + bool ring_sysfs_visible; + /* The ring buffer is encrypted */ + bool co_ring_buffer; + /* The external memory is encrypted */ + bool co_external_memory; }; +#define lock_requestor(channel, flags) \ +do { \ + struct vmbus_requestor *rqstor = &(channel)->requestor; \ + \ + spin_lock_irqsave(&rqstor->req_lock, flags); \ +} while (0) + +static __always_inline void unlock_requestor(struct vmbus_channel *channel, + unsigned long flags) +{ + struct vmbus_requestor *rqstor = &channel->requestor; + + spin_unlock_irqrestore(&rqstor->req_lock, flags); +} + +u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); +u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); +u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); +u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); + +static inline bool is_co_ring_buffer(const struct vmbus_channel_offer_channel *o) +{ + return !!(o->offer.chn_flags & VMBUS_CHANNEL_CONFIDENTIAL_RING_BUFFER); +} + +static inline bool is_co_external_memory(const struct vmbus_channel_offer_channel *o) +{ + return !!(o->offer.chn_flags & VMBUS_CHANNEL_CONFIDENTIAL_EXTERNAL_MEMORY); +} + +static inline bool is_hvsock_offer(const struct vmbus_channel_offer_channel *o) +{ + return !!(o->offer.chn_flags & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); +} + static inline bool is_hvsock_channel(const struct vmbus_channel *c) { - return !!(c->offermsg.offer.chn_flags & - VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); + return is_hvsock_offer(&c->offermsg); } -static inline void set_channel_affinity_state(struct vmbus_channel *c, - enum hv_numa_policy policy) +static inline bool is_sub_channel(const struct vmbus_channel *c) { - c->affinity_policy = policy; + return c->offermsg.offer.sub_channel_index != 0; } static inline void set_channel_read_mode(struct vmbus_channel *c, @@ -936,20 +1092,25 @@ static inline void *get_per_channel_state(struct vmbus_channel *c) static inline void set_channel_pending_send_size(struct vmbus_channel *c, u32 size) { - c->outbound.ring_buffer->pending_send_sz = size; -} + unsigned long flags; -static inline void set_low_latency_mode(struct vmbus_channel *c) -{ - c->low_latency = true; -} + if (size) { + spin_lock_irqsave(&c->outbound.ring_lock, flags); + ++c->out_full_total; -static inline void clear_low_latency_mode(struct vmbus_channel *c) -{ - c->low_latency = false; + if (!c->out_full_flag) { + ++c->out_full_first; + c->out_full_flag = true; + } + spin_unlock_irqrestore(&c->outbound.ring_lock, flags); + } else { + c->out_full_flag = false; + } + + c->outbound.ring_buffer->pending_send_sz = size; } -void vmbus_onmessage(void *context); +void vmbus_onmessage(struct vmbus_channel_message_header *hdr); int vmbus_request_offers(void); @@ -963,19 +1124,6 @@ void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel, void (*chn_rescind_cb)(struct vmbus_channel *)); -/* - * 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; @@ -1031,6 +1179,13 @@ extern int vmbus_open(struct vmbus_channel *channel, extern void vmbus_close(struct vmbus_channel *channel); +extern int vmbus_sendpacket_getid(struct vmbus_channel *channel, + void *buffer, + u32 bufferLen, + u64 requestid, + u64 *trans_id, + enum vmbus_packet_type type, + u32 flags); extern int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, u32 bufferLen, @@ -1038,13 +1193,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -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_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, @@ -1055,10 +1203,10 @@ extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, extern int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, u32 size, - u32 *gpadl_handle); + struct vmbus_gpadl *gpadl); extern int vmbus_teardown_gpadl(struct vmbus_channel *channel, - u32 gpadl_handle); + struct vmbus_gpadl *gpadl); void vmbus_reset_channel_cb(struct vmbus_channel *channel); @@ -1074,9 +1222,6 @@ extern int vmbus_recvpacket_raw(struct vmbus_channel *channel, u32 *buffer_actual_len, u64 *requestid); - -extern void vmbus_ontimer(unsigned long data); - /* Base driver object */ struct hv_driver { const char *name; @@ -1096,7 +1241,7 @@ struct hv_driver { bool hvsock; /* the device type supported by this driver */ - uuid_le dev_type; + guid_t dev_type; const struct hv_vmbus_device_id *id_table; struct device_driver driver; @@ -1108,38 +1253,44 @@ struct hv_driver { } dynids; int (*probe)(struct hv_device *, const struct hv_vmbus_device_id *); - int (*remove)(struct hv_device *); + void (*remove)(struct hv_device *dev); void (*shutdown)(struct hv_device *); + int (*suspend)(struct hv_device *); + int (*resume)(struct hv_device *); + }; /* Base device object */ struct hv_device { /* the device type id of this device */ - uuid_le dev_type; + guid_t dev_type; /* the device instance id of this device */ - uuid_le dev_instance; + guid_t dev_instance; u16 vendor_id; u16 device_id; struct device device; - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; struct vmbus_channel *channel; struct kset *channels_kset; -}; + struct device_dma_parameters dma_parms; + u64 dma_mask; + /* place holder to keep track of the dir for hv device in debugfs */ + struct dentry *debug_dir; -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); -} + +#define device_to_hv_device(d) container_of_const(d, struct hv_device, device) +#define drv_to_hv_drv(d) container_of_const(d, struct hv_driver, driver) static inline void hv_set_drvdata(struct hv_device *dev, void *data) { @@ -1151,6 +1302,8 @@ static inline void *hv_get_drvdata(struct hv_device *dev) return dev_get_drvdata(&dev->device); } +struct device *hv_get_vmbus_root_device(void); + struct hv_ring_buffer_debug_info { u32 current_interrupt_mask; u32 current_read_index; @@ -1159,8 +1312,11 @@ struct hv_ring_buffer_debug_info { u32 bytes_avail_towrite; }; -void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, - struct hv_ring_buffer_debug_info *debug_info); + +int hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, + struct hv_ring_buffer_debug_info *debug_info); + +bool hv_ringbuffer_spinlock_busy(struct vmbus_channel *channel); /* Vmbus interface */ #define vmbus_driver_register(driver) \ @@ -1187,102 +1343,102 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); * {f8615163-df3e-46c5-913f-f2d2f965ed0e} */ #define HV_NIC_GUID \ - .guid = UUID_LE(0xf8615163, 0xdf3e, 0x46c5, 0x91, 0x3f, \ - 0xf2, 0xd2, 0xf9, 0x65, 0xed, 0x0e) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(0x2f9bcc4a, 0x0069, 0x4af3, 0xb7, 0x6b, \ + 0x6f, 0xd0, 0xbe, 0x52, 0x8c, 0xda) /* * Guest File Copy Service @@ -1290,16 +1446,16 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); */ #define HV_FCOPY_GUID \ - .guid = UUID_LE(0x34d14be3, 0xdee4, 0x41c8, 0x9a, 0xe7, \ - 0x6b, 0x17, 0x49, 0x77, 0xc1, 0x92) + .guid = GUID_INIT(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) + .guid = GUID_INIT(0x8c2eaf3d, 0x32a7, 0x4b09, 0xab, 0x99, \ + 0xbd, 0x1f, 0x1c, 0x86, 0xb5, 0x01) /* * PCI Express Pass Through @@ -1307,29 +1463,35 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); */ #define HV_PCIE_GUID \ - .guid = UUID_LE(0x44c4f61d, 0x4444, 0x4400, 0x9d, 0x52, \ - 0x80, 0x2e, 0x27, 0xed, 0xe1, 0x9f) + .guid = GUID_INIT(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. + * Linux doesn't support these 4 devices: the first two are for + * Automatic Virtual Machine Activation, the third is for + * Remote Desktop Virtualization, and the fourth is Initial + * Machine Configuration (IMC) used only by Windows guests. * {f8e65716-3cb3-4a06-9a60-1889c5cccab5} * {3375baf4-9e15-4b30-b765-67acb10d607b} * {276aacf4-ac15-426c-98dd-7521ad3f01fe} + * {c376c1c3-d276-48d2-90a9-c04748072c60} */ #define HV_AVMA1_GUID \ - .guid = UUID_LE(0xf8e65716, 0x3cb3, 0x4a06, 0x9a, 0x60, \ - 0x18, 0x89, 0xc5, 0xcc, 0xca, 0xb5) + .guid = GUID_INIT(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) + .guid = GUID_INIT(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) + .guid = GUID_INIT(0x276aacf4, 0xac15, 0x426c, 0x98, 0xdd, \ + 0x75, 0x21, 0xad, 0x3f, 0x01, 0xfe) + +#define HV_IMC_GUID \ + .guid = GUID_INIT(0xc376c1c3, 0xd276, 0x48d2, 0x90, 0xa9, \ + 0xc0, 0x47, 0x48, 0x07, 0x2c, 0x60) /* * Common header for Hyper-V ICs @@ -1341,6 +1503,7 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); #define ICMSGTYPE_SHUTDOWN 3 #define ICMSGTYPE_TIMESYNC 4 #define ICMSGTYPE_VSS 5 +#define ICMSGTYPE_FCOPY 7 #define ICMSGHDRFLAG_TRANSACTION 1 #define ICMSGHDRFLAG_REQUEST 2 @@ -1358,7 +1521,10 @@ struct hv_util_service { void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); + int (*util_init_transport)(void); void (*util_deinit)(void); + int (*util_pre_suspend)(void); + int (*util_pre_resume)(void); }; struct vmbuspipe_hdr { @@ -1382,11 +1548,17 @@ struct icmsg_hdr { u8 reserved[2]; } __packed; +#define IC_VERSION_NEGOTIATION_MAX_VER_COUNT 100 +#define ICMSG_HDR (sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr)) +#define ICMSG_NEGOTIATE_PKT_SIZE(icframe_vercnt, icmsg_vercnt) \ + (ICMSG_HDR + sizeof(struct icmsg_negotiate) + \ + (((icframe_vercnt) + (icmsg_vercnt)) * sizeof(struct ic_version))) + struct icmsg_negotiate { u16 icframe_vercnt; u16 icmsg_vercnt; u32 reserved; - struct ic_version icversion_data[1]; /* any size array */ + struct ic_version icversion_data[]; /* any size array */ } __packed; struct shutdown_msg_data { @@ -1431,13 +1603,18 @@ struct ictimesync_ref_data { struct hyperv_service_callback { u8 msg_type; char *log_msg; - uuid_le data; + guid_t data; struct vmbus_channel *channel; void (*callback)(void *context); }; +struct hv_dma_range { + dma_addr_t dma; + u32 mapping_size; +}; + #define MAX_SRV_VER 0x7ffffff -extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen, const int *fw_version, int fw_vercnt, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); @@ -1451,9 +1628,11 @@ void vmbus_setevent(struct vmbus_channel *channel); 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); +int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id, + const guid_t *shv_host_servie_id); +int vmbus_send_modifychannel(struct vmbus_channel *channel, u32 target_vp); void vmbus_set_event(struct vmbus_channel *channel); +int vmbus_channel_set_cpu(struct vmbus_channel *channel, u32 target_cpu); /* Get the start of the ring buffer. */ static inline void * @@ -1508,6 +1687,11 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) return (desc->len8 << 3) - (desc->offset8 << 3); } +/* Get packet length associated with descriptor */ +static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc) +{ + return desc->len8 << 3; +} struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); @@ -1518,10 +1702,6 @@ __hv_pkt_iter_next(struct vmbus_channel *channel, void hv_pkt_iter_close(struct vmbus_channel *channel); -/* - * Get next packet descriptor from iterator - * If at end of list, return NULL and update host. - */ static inline struct vmpacket_descriptor * hv_pkt_iter_next(struct vmbus_channel *channel, const struct vmpacket_descriptor *pkt) @@ -1539,4 +1719,52 @@ hv_pkt_iter_next(struct vmbus_channel *channel, for (pkt = hv_pkt_iter_first(channel); pkt; \ pkt = hv_pkt_iter_next(channel, pkt)) +/* + * Interface for passing data between SR-IOV PF and VF drivers. The VF driver + * sends requests to read and write blocks. Each block must be 128 bytes or + * smaller. Optionally, the VF driver can register a callback function which + * will be invoked when the host says that one or more of the first 64 block + * IDs is "invalid" which means that the VF driver should reread them. + */ +#define HV_CONFIG_BLOCK_SIZE_MAX 128 + +int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned); +int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id); +int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)); + +struct hyperv_pci_block_ops { + int (*read_block)(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned); + int (*write_block)(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id); + int (*reg_blk_invalidate)(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)); +}; + +extern struct hyperv_pci_block_ops hvpci_block_ops; + +static inline unsigned long virt_to_hvpfn(void *addr) +{ + phys_addr_t paddr; + + if (is_vmalloc_addr(addr)) + paddr = page_to_phys(vmalloc_to_page(addr)) + + offset_in_page(addr); + else + paddr = __pa(addr); + + return paddr >> HV_HYP_PAGE_SHIFT; +} + +#define NR_HV_HYP_PAGES_IN_PAGE (PAGE_SIZE / HV_HYP_PAGE_SIZE) +#define offset_in_hvpage(ptr) ((unsigned long)(ptr) & ~HV_HYP_PAGE_MASK) +#define HVPFN_UP(x) (((x) + HV_HYP_PAGE_SIZE-1) >> HV_HYP_PAGE_SHIFT) +#define HVPFN_DOWN(x) ((x) >> HV_HYP_PAGE_SHIFT) +#define page_to_hvpfn(page) (page_to_pfn(page) * NR_HV_HYP_PAGES_IN_PAGE) + #endif /* _HYPERV_H */ |