diff options
Diffstat (limited to 'include/xen/interface/io')
| -rw-r--r-- | include/xen/interface/io/blkif.h | 79 | ||||
| -rw-r--r-- | include/xen/interface/io/netif.h | 106 | ||||
| -rw-r--r-- | include/xen/interface/io/protocols.h | 6 | ||||
| -rw-r--r-- | include/xen/interface/io/ring.h | 5 | ||||
| -rw-r--r-- | include/xen/interface/io/tpmif.h | 52 | ||||
| -rw-r--r-- | include/xen/interface/io/xs_wire.h | 3 |
6 files changed, 233 insertions, 18 deletions
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index ee338bfde18..c33e1c489eb 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -9,8 +9,8 @@ #ifndef __XEN_PUBLIC_IO_BLKIF_H__ #define __XEN_PUBLIC_IO_BLKIF_H__ -#include "ring.h" -#include "../grant_table.h" +#include <xen/interface/io/ring.h> +#include <xen/interface/grant_table.h> /* * Front->back notifications: When enqueuing a new request, sending a @@ -86,7 +86,7 @@ typedef uint64_t blkif_sector_t; * Interface%20manuals/100293068c.pdf * The backend can optionally provide three extra XenBus attributes to * further optimize the discard functionality: - * 'discard-aligment' - Devices that support discard functionality may + * 'discard-alignment' - Devices that support discard functionality may * internally allocate space in units that are bigger than the exported * logical block size. The discard-alignment parameter indicates how many bytes * the beginning of the partition is offset from the internal allocation unit's @@ -103,33 +103,61 @@ typedef uint64_t blkif_sector_t; #define BLKIF_OP_DISCARD 5 /* + * Recognized if "feature-max-indirect-segments" in present in the backend + * xenbus info. The "feature-max-indirect-segments" node contains the maximum + * number of segments allowed by the backend per request. If the node is + * present, the frontend might use blkif_request_indirect structs in order to + * issue requests with more than BLKIF_MAX_SEGMENTS_PER_REQUEST (11). The + * maximum number of indirect segments is fixed by the backend, but the + * frontend can issue requests with any number of indirect segments as long as + * it's less than the number provided by the backend. The indirect_grefs field + * in blkif_request_indirect should be filled by the frontend with the + * grant references of the pages that are holding the indirect segments. + * These pages are filled with an array of blkif_request_segment that hold the + * information about the segments. The number of indirect pages to use is + * determined by the number of segments an indirect request contains. Every + * indirect page can contain a maximum of + * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to + * calculate the number of indirect pages to use we have to do + * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))). + * + * If a backend does not recognize BLKIF_OP_INDIRECT, it should *not* + * create the "feature-max-indirect-segments" node! + */ +#define BLKIF_OP_INDIRECT 6 + +/* * Maximum scatter/gather segments per request. * This is carefully chosen so that sizeof(struct blkif_ring) <= PAGE_SIZE. * NB. This could be 12 if the ring indexes weren't stored in the same page. */ #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11 +#define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8 + +struct blkif_request_segment { + grant_ref_t gref; /* reference to I/O buffer frame */ + /* @first_sect: first sector in frame to transfer (inclusive). */ + /* @last_sect: last sector in frame to transfer (inclusive). */ + uint8_t first_sect, last_sect; +}; + struct blkif_request_rw { uint8_t nr_segments; /* number of segments */ blkif_vdev_t handle; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad1; /* offsetof(blkif_request,u.rw.id) == 8 */ #endif uint64_t id; /* private guest value, echoed in resp */ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ - struct blkif_request_segment { - grant_ref_t gref; /* reference to I/O buffer frame */ - /* @first_sect: first sector in frame to transfer (inclusive). */ - /* @last_sect: last sector in frame to transfer (inclusive). */ - uint8_t first_sect, last_sect; - } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; } __attribute__((__packed__)); struct blkif_request_discard { uint8_t flag; /* BLKIF_DISCARD_SECURE or zero. */ #define BLKIF_DISCARD_SECURE (1<<0) /* ignored if discard-secure=0 */ blkif_vdev_t _pad1; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#ifndef CONFIG_X86_32 uint32_t _pad2; /* offsetof(blkif_req..,u.discard.id)==8*/ #endif uint64_t id; /* private guest value, echoed in resp */ @@ -138,11 +166,40 @@ struct blkif_request_discard { uint8_t _pad3; } __attribute__((__packed__)); +struct blkif_request_other { + uint8_t _pad1; + blkif_vdev_t _pad2; /* only for read/write requests */ +#ifndef CONFIG_X86_32 + uint32_t _pad3; /* offsetof(blkif_req..,u.other.id)==8*/ +#endif + uint64_t id; /* private guest value, echoed in resp */ +} __attribute__((__packed__)); + +struct blkif_request_indirect { + uint8_t indirect_op; + uint16_t nr_segments; +#ifndef CONFIG_X86_32 + uint32_t _pad1; /* offsetof(blkif_...,u.indirect.id) == 8 */ +#endif + uint64_t id; + blkif_sector_t sector_number; + blkif_vdev_t handle; + uint16_t _pad2; + grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST]; +#ifndef CONFIG_X86_32 + uint32_t _pad3; /* make it 64 byte aligned */ +#else + uint64_t _pad3; /* make it 64 byte aligned */ +#endif +} __attribute__((__packed__)); + struct blkif_request { uint8_t operation; /* BLKIF_OP_??? */ union { struct blkif_request_rw rw; struct blkif_request_discard discard; + struct blkif_request_other other; + struct blkif_request_indirect indirect; } u; } __attribute__((__packed__)); diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h index cb94668f6e9..70054cc0708 100644 --- a/include/xen/interface/io/netif.h +++ b/include/xen/interface/io/netif.h @@ -9,8 +9,26 @@ #ifndef __XEN_PUBLIC_IO_NETIF_H__ #define __XEN_PUBLIC_IO_NETIF_H__ -#include "ring.h" -#include "../grant_table.h" +#include <xen/interface/io/ring.h> +#include <xen/interface/grant_table.h> + +/* + * Older implementation of Xen network frontend / backend has an + * implicit dependency on the MAX_SKB_FRAGS as the maximum number of + * ring slots a skb can use. Netfront / netback may not work as + * expected when frontend and backend have different MAX_SKB_FRAGS. + * + * A better approach is to add mechanism for netfront / netback to + * negotiate this value. However we cannot fix all possible + * frontends, so we need to define a value which states the minimum + * slots backend must support. + * + * The minimum value derives from older Linux kernel's MAX_SKB_FRAGS + * (18), which is proved to work with most frontends. Any new backend + * which doesn't negotiate with frontend should expect frontend to + * send a valid packet using slots up to this value. + */ +#define XEN_NETIF_NR_SLOTS_MIN 18 /* * Notifications after enqueuing any type of message should be conditional on @@ -20,6 +38,85 @@ * that it cannot safely queue packets (as it may not be kicked to send them). */ + /* + * "feature-split-event-channels" is introduced to separate guest TX + * and RX notificaion. Backend either doesn't support this feature or + * advertise it via xenstore as 0 (disabled) or 1 (enabled). + * + * To make use of this feature, frontend should allocate two event + * channels for TX and RX, advertise them to backend as + * "event-channel-tx" and "event-channel-rx" respectively. If frontend + * doesn't want to use this feature, it just writes "event-channel" + * node as before. + */ + +/* + * Multiple transmit and receive queues: + * If supported, the backend will write the key "multi-queue-max-queues" to + * the directory for that vif, and set its value to the maximum supported + * number of queues. + * Frontends that are aware of this feature and wish to use it can write the + * key "multi-queue-num-queues", set to the number they wish to use, which + * must be greater than zero, and no more than the value reported by the backend + * in "multi-queue-max-queues". + * + * Queues replicate the shared rings and event channels. + * "feature-split-event-channels" may optionally be used when using + * multiple queues, but is not mandatory. + * + * Each queue consists of one shared ring pair, i.e. there must be the same + * number of tx and rx rings. + * + * For frontends requesting just one queue, the usual event-channel and + * ring-ref keys are written as before, simplifying the backend processing + * to avoid distinguishing between a frontend that doesn't understand the + * multi-queue feature, and one that does, but requested only one queue. + * + * Frontends requesting two or more queues must not write the toplevel + * event-channel (or event-channel-{tx,rx}) and {tx,rx}-ring-ref keys, + * instead writing those keys under sub-keys having the name "queue-N" where + * N is the integer ID of the queue for which those keys belong. Queues + * are indexed from zero. For example, a frontend with two queues and split + * event channels must write the following set of queue-related keys: + * + * /local/domain/1/device/vif/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vif/0/queue-0 = "" + * /local/domain/1/device/vif/0/queue-0/tx-ring-ref = "<ring-ref-tx0>" + * /local/domain/1/device/vif/0/queue-0/rx-ring-ref = "<ring-ref-rx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-tx = "<evtchn-tx0>" + * /local/domain/1/device/vif/0/queue-0/event-channel-rx = "<evtchn-rx0>" + * /local/domain/1/device/vif/0/queue-1 = "" + * /local/domain/1/device/vif/0/queue-1/tx-ring-ref = "<ring-ref-tx1>" + * /local/domain/1/device/vif/0/queue-1/rx-ring-ref = "<ring-ref-rx1" + * /local/domain/1/device/vif/0/queue-1/event-channel-tx = "<evtchn-tx1>" + * /local/domain/1/device/vif/0/queue-1/event-channel-rx = "<evtchn-rx1>" + * + * If there is any inconsistency in the XenStore data, the backend may + * choose not to connect any queues, instead treating the request as an + * error. This includes scenarios where more (or fewer) queues were + * requested than the frontend provided details for. + * + * Mapping of packets to queues is considered to be a function of the + * transmitting system (backend or frontend) and is not negotiated + * between the two. Guests are free to transmit packets on any queue + * they choose, provided it has been set up correctly. Guests must be + * prepared to receive packets on any queue they have requested be set up. + */ + +/* + * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum + * offload off or on. If it is missing then the feature is assumed to be on. + * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum + * offload on or off. If it is missing then the feature is assumed to be off. + */ + +/* + * "feature-gso-tcpv4" and "feature-gso-tcpv6" advertise the capability to + * handle large TCP packets (in IPv4 or IPv6 form respectively). Neither + * frontends nor backends are assumed to be capable unless the flags are + * present. + */ + /* * This is the 'wire' format for packets: * Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags) @@ -47,6 +144,7 @@ #define _XEN_NETTXF_extra_info (3) #define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info) +#define XEN_NETIF_MAX_TX_SIZE 0xFFFF struct xen_netif_tx_request { grant_ref_t gref; /* Reference to buffer page */ uint16_t offset; /* Offset within buffer page */ @@ -64,8 +162,10 @@ struct xen_netif_tx_request { #define _XEN_NETIF_EXTRA_FLAG_MORE (0) #define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE) -/* GSO types - only TCPv4 currently supported. */ +/* GSO types */ +#define XEN_NETIF_GSO_TYPE_NONE (0) #define XEN_NETIF_GSO_TYPE_TCPV4 (1) +#define XEN_NETIF_GSO_TYPE_TCPV6 (2) /* * This structure needs to fit within both netif_tx_request and diff --git a/include/xen/interface/io/protocols.h b/include/xen/interface/io/protocols.h index 01fc8ae5f0b..545a14ba0bb 100644 --- a/include/xen/interface/io/protocols.h +++ b/include/xen/interface/io/protocols.h @@ -3,17 +3,17 @@ #define XEN_IO_PROTO_ABI_X86_32 "x86_32-abi" #define XEN_IO_PROTO_ABI_X86_64 "x86_64-abi" -#define XEN_IO_PROTO_ABI_IA64 "ia64-abi" #define XEN_IO_PROTO_ABI_POWERPC64 "powerpc64-abi" +#define XEN_IO_PROTO_ABI_ARM "arm-abi" #if defined(__i386__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32 #elif defined(__x86_64__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_64 -#elif defined(__ia64__) -# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_IA64 #elif defined(__powerpc64__) # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_POWERPC64 +#elif defined(__arm__) || defined(__aarch64__) +# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_ARM #else # error arch fixup needed here #endif diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 75271b9a8f6..7d28aff605c 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -188,6 +188,11 @@ struct __name##_back_ring { \ #define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) +/* Ill-behaved frontend determination: Can there be this many requests? */ +#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r)) + + #define RING_PUSH_REQUESTS(_r) do { \ wmb(); /* back sees requests /before/ updated producer index */ \ (_r)->sring->req_prod = (_r)->req_prod_pvt; \ diff --git a/include/xen/interface/io/tpmif.h b/include/xen/interface/io/tpmif.h new file mode 100644 index 00000000000..28e7dcd75e8 --- /dev/null +++ b/include/xen/interface/io/tpmif.h @@ -0,0 +1,52 @@ +/****************************************************************************** + * tpmif.h + * + * TPM I/O interface for Xen guest OSes, v2 + * + * This file is in the public domain. + * + */ + +#ifndef __XEN_PUBLIC_IO_TPMIF_H__ +#define __XEN_PUBLIC_IO_TPMIF_H__ + +/* + * Xenbus state machine + * + * Device open: + * 1. Both ends start in XenbusStateInitialising + * 2. Backend transitions to InitWait (frontend does not wait on this step) + * 3. Frontend populates ring-ref, event-channel, feature-protocol-v2 + * 4. Frontend transitions to Initialised + * 5. Backend maps grant and event channel, verifies feature-protocol-v2 + * 6. Backend transitions to Connected + * 7. Frontend verifies feature-protocol-v2, transitions to Connected + * + * Device close: + * 1. State is changed to XenbusStateClosing + * 2. Frontend transitions to Closed + * 3. Backend unmaps grant and event, changes state to InitWait + */ + +enum vtpm_shared_page_state { + VTPM_STATE_IDLE, /* no contents / vTPM idle / cancel complete */ + VTPM_STATE_SUBMIT, /* request ready / vTPM working */ + VTPM_STATE_FINISH, /* response ready / vTPM idle */ + VTPM_STATE_CANCEL, /* cancel requested / vTPM working */ +}; +/* The backend should only change state to IDLE or FINISH, while the + * frontend should only change to SUBMIT or CANCEL. */ + + +struct vtpm_shared_page { + uint32_t length; /* request/response length in bytes */ + + uint8_t state; /* enum vtpm_shared_page_state */ + uint8_t locality; /* for the current request */ + uint8_t pad; + + uint8_t nr_extra_pages; /* extra pages for long packets; may be zero */ + uint32_t extra_pages[0]; /* grant IDs; length in nr_extra_pages */ +}; + +#endif diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index 7cdfca24eaf..794deb07eb5 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -29,7 +29,8 @@ enum xsd_sockmsg_type XS_IS_DOMAIN_INTRODUCED, XS_RESUME, XS_SET_TARGET, - XS_RESTRICT + XS_RESTRICT, + XS_RESET_WATCHES, }; #define XS_WRITE_NONE "NONE" |