diff options
Diffstat (limited to 'include/xen/interface/io/blkif.h')
| -rw-r--r-- | include/xen/interface/io/blkif.h | 116 |
1 files changed, 106 insertions, 10 deletions
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index ffd4652de91c..ba1e9f5b630e 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /****************************************************************************** * blkif.h * @@ -28,6 +29,54 @@ typedef uint16_t blkif_vdev_t; typedef uint64_t blkif_sector_t; /* + * Multiple hardware queues/rings: + * If supported, the backend will write the key "multi-queue-max-queues" to + * the directory for that vbd, 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" with 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". + * + * 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 and ring-ref keys, instead writing those keys under sub-keys + * having the name "queue-N" where N is the integer ID of the queue/ring for + * which those keys belong. Queues are indexed from zero. + * For example, a frontend with two queues must write the following set of + * queue-related keys: + * + * /local/domain/1/device/vbd/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vbd/0/queue-0 = "" + * /local/domain/1/device/vbd/0/queue-0/ring-ref = "<ring-ref#0>" + * /local/domain/1/device/vbd/0/queue-0/event-channel = "<evtchn#0>" + * /local/domain/1/device/vbd/0/queue-1 = "" + * /local/domain/1/device/vbd/0/queue-1/ring-ref = "<ring-ref#1>" + * /local/domain/1/device/vbd/0/queue-1/event-channel = "<evtchn#1>" + * + * It is also possible to use multiple queues/rings together with + * feature multi-page ring buffer. + * For example, a frontend requests two queues/rings and the size of each ring + * buffer is two pages must write the following set of related keys: + * + * /local/domain/1/device/vbd/0/multi-queue-num-queues = "2" + * /local/domain/1/device/vbd/0/ring-page-order = "1" + * /local/domain/1/device/vbd/0/queue-0 = "" + * /local/domain/1/device/vbd/0/queue-0/ring-ref0 = "<ring-ref#0>" + * /local/domain/1/device/vbd/0/queue-0/ring-ref1 = "<ring-ref#1>" + * /local/domain/1/device/vbd/0/queue-0/event-channel = "<evtchn#0>" + * /local/domain/1/device/vbd/0/queue-1 = "" + * /local/domain/1/device/vbd/0/queue-1/ring-ref0 = "<ring-ref#2>" + * /local/domain/1/device/vbd/0/queue-1/ring-ref1 = "<ring-ref#3>" + * /local/domain/1/device/vbd/0/queue-1/event-channel = "<evtchn#1>" + * + */ + +/* * REQUEST CODES. */ #define BLKIF_OP_READ 0 @@ -86,7 +135,7 @@ 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 +152,61 @@ 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 */ @@ -141,18 +218,37 @@ struct blkif_request_discard { struct blkif_request_other { uint8_t _pad1; blkif_vdev_t _pad2; /* only for read/write requests */ -#ifdef CONFIG_X86_64 +#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__)); |