X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Frte_vhost.h;h=7b5dc87c2e7ab9a566ab0babfba7e484e6882976;hb=5a5793a5ffa2231ae759de824fb8bfc970e5d4f7;hp=671ea505311f14ac491b562ce6dc6c0a61716389;hpb=2e28f45b6939ba75d7adff9f99d87a9bc8b8f8a6;p=dpdk.git diff --git a/lib/librte_vhost/rte_vhost.h b/lib/librte_vhost/rte_vhost.h index 671ea50531..7b5dc87c2e 100644 --- a/lib/librte_vhost/rte_vhost.h +++ b/lib/librte_vhost/rte_vhost.h @@ -23,11 +23,17 @@ extern "C" { /* These are not C++-aware. */ #include #include +#include #define RTE_VHOST_USER_CLIENT (1ULL << 0) #define RTE_VHOST_USER_NO_RECONNECT (1ULL << 1) #define RTE_VHOST_USER_DEQUEUE_ZERO_COPY (1ULL << 2) #define RTE_VHOST_USER_IOMMU_SUPPORT (1ULL << 3) +#define RTE_VHOST_USER_POSTCOPY_SUPPORT (1ULL << 4) +/* support mbuf with external buffer attached */ +#define RTE_VHOST_USER_EXTBUF_SUPPORT (1ULL << 5) +/* support only linear buffers (no chained mbufs) */ +#define RTE_VHOST_USER_LINEARBUF_SUPPORT (1ULL << 6) /** Protocol features. */ #ifndef VHOST_USER_PROTOCOL_F_MQ @@ -54,6 +60,26 @@ extern "C" { #define VHOST_USER_PROTOCOL_F_SLAVE_REQ 5 #endif +#ifndef VHOST_USER_PROTOCOL_F_CRYPTO_SESSION +#define VHOST_USER_PROTOCOL_F_CRYPTO_SESSION 7 +#endif + +#ifndef VHOST_USER_PROTOCOL_F_PAGEFAULT +#define VHOST_USER_PROTOCOL_F_PAGEFAULT 8 +#endif + +#ifndef VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD +#define VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD 10 +#endif + +#ifndef VHOST_USER_PROTOCOL_F_HOST_NOTIFIER +#define VHOST_USER_PROTOCOL_F_HOST_NOTIFIER 11 +#endif + +#ifndef VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD +#define VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD 12 +#endif + /** Indicate whether protocol features negotiation is supported. */ #ifndef VHOST_USER_F_PROTOCOL_FEATURES #define VHOST_USER_F_PROTOCOL_FEATURES 30 @@ -81,10 +107,81 @@ struct rte_vhost_memory { struct rte_vhost_mem_region regions[]; }; +struct rte_vhost_inflight_desc_split { + uint8_t inflight; + uint8_t padding[5]; + uint16_t next; + uint64_t counter; +}; + +struct rte_vhost_inflight_info_split { + uint64_t features; + uint16_t version; + uint16_t desc_num; + uint16_t last_inflight_io; + uint16_t used_idx; + struct rte_vhost_inflight_desc_split desc[0]; +}; + +struct rte_vhost_inflight_desc_packed { + uint8_t inflight; + uint8_t padding; + uint16_t next; + uint16_t last; + uint16_t num; + uint64_t counter; + uint16_t id; + uint16_t flags; + uint32_t len; + uint64_t addr; +}; + +struct rte_vhost_inflight_info_packed { + uint64_t features; + uint16_t version; + uint16_t desc_num; + uint16_t free_head; + uint16_t old_free_head; + uint16_t used_idx; + uint16_t old_used_idx; + uint8_t used_wrap_counter; + uint8_t old_used_wrap_counter; + uint8_t padding[7]; + struct rte_vhost_inflight_desc_packed desc[0]; +}; + +struct rte_vhost_resubmit_desc { + uint16_t index; + uint64_t counter; +}; + +struct rte_vhost_resubmit_info { + struct rte_vhost_resubmit_desc *resubmit_list; + uint16_t resubmit_num; +}; + +struct rte_vhost_ring_inflight { + union { + struct rte_vhost_inflight_info_split *inflight_split; + struct rte_vhost_inflight_info_packed *inflight_packed; + }; + + struct rte_vhost_resubmit_info *resubmit_inflight; +}; + struct rte_vhost_vring { - struct vring_desc *desc; - struct vring_avail *avail; - struct vring_used *used; + union { + struct vring_desc *desc; + struct vring_packed_desc *desc_packed; + }; + union { + struct vring_avail *avail; + struct vring_packed_desc_event *driver_event; + }; + union { + struct vring_used *used; + struct vring_packed_desc_event *device_event; + }; uint64_t log_guest_addr; /** Deprecated, use rte_vhost_vring_call() instead. */ @@ -94,6 +191,46 @@ struct rte_vhost_vring { uint16_t size; }; +/** + * Possible results of the vhost user message handling callbacks + */ +enum rte_vhost_msg_result { + /* Message handling failed */ + RTE_VHOST_MSG_RESULT_ERR = -1, + /* Message handling successful */ + RTE_VHOST_MSG_RESULT_OK = 0, + /* Message handling successful and reply prepared */ + RTE_VHOST_MSG_RESULT_REPLY = 1, + /* Message not handled */ + RTE_VHOST_MSG_RESULT_NOT_HANDLED, +}; + +/** + * Function prototype for the vhost backend to handle specific vhost user + * messages. + * + * @param vid + * vhost device id + * @param msg + * Message pointer. + * @return + * RTE_VHOST_MSG_RESULT_OK on success, + * RTE_VHOST_MSG_RESULT_REPLY on success with reply, + * RTE_VHOST_MSG_RESULT_ERR on failure, + * RTE_VHOST_MSG_RESULT_NOT_HANDLED if message was not handled. + */ +typedef enum rte_vhost_msg_result (*rte_vhost_msg_handle)(int vid, void *msg); + +/** + * Optional vhost user message handlers. + */ +struct rte_vhost_user_extern_ops { + /* Called prior to the master message handling. */ + rte_vhost_msg_handle pre_msg_handle; + /* Called after the master message handling. */ + rte_vhost_msg_handle post_msg_handle; +}; + /** * Device and vring operations. */ @@ -114,12 +251,25 @@ struct vhost_device_ops { int (*new_connection)(int vid); void (*destroy_connection)(int vid); - void *reserved[2]; /**< Reserved for future extension */ + /** + * This callback gets called each time a guest gets notified + * about waiting packets. This is the interrupt handling trough + * the eventfd_write(callfd), which can be used for counting these + * "slow" syscalls. + */ + void (*guest_notified)(int vid); + + void *reserved[1]; /**< Reserved for future extension */ }; /** * Convert guest physical address to host virtual address * + * This function is deprecated because unsafe. + * New rte_vhost_va_from_guest_pa() should be used instead to ensure + * guest physical ranges are fully and contiguously mapped into + * process virtual address space. + * * @param mem * the guest memory regions * @param gpa @@ -127,6 +277,7 @@ struct vhost_device_ops { * @return * the host virtual address on success, 0 on failure */ +__rte_deprecated static __rte_always_inline uint64_t rte_vhost_gpa_to_vva(struct rte_vhost_memory *mem, uint64_t gpa) { @@ -145,6 +296,47 @@ rte_vhost_gpa_to_vva(struct rte_vhost_memory *mem, uint64_t gpa) return 0; } +/** + * Convert guest physical address to host virtual address safely + * + * This variant of rte_vhost_gpa_to_vva() takes care all the + * requested length is mapped and contiguous in process address + * space. + * + * @param mem + * the guest memory regions + * @param gpa + * the guest physical address for querying + * @param len + * the size of the requested area to map, updated with actual size mapped + * @return + * the host virtual address on success, 0 on failure + */ +__rte_experimental +static __rte_always_inline uint64_t +rte_vhost_va_from_guest_pa(struct rte_vhost_memory *mem, + uint64_t gpa, uint64_t *len) +{ + struct rte_vhost_mem_region *r; + uint32_t i; + + for (i = 0; i < mem->nregions; i++) { + r = &mem->regions[i]; + if (gpa >= r->guest_phys_addr && + gpa < r->guest_phys_addr + r->size) { + + if (unlikely(*len > r->guest_phys_addr + r->size - gpa)) + *len = r->guest_phys_addr + r->size - gpa; + + return gpa - r->guest_phys_addr + + r->host_user_addr; + } + } + *len = 0; + + return 0; +} + #define RTE_VHOST_NEED_LOG(features) ((features) & (1ULL << VHOST_F_LOG_ALL)) /** @@ -161,7 +353,7 @@ rte_vhost_gpa_to_vva(struct rte_vhost_memory *mem, uint64_t gpa) * @param vid * vhost device ID * @param addr - * the starting address for write + * the starting address for write (in guest physical address space) * @param len * the length to write */ @@ -199,6 +391,44 @@ int rte_vhost_driver_register(const char *path, uint64_t flags); /* Unregister vhost driver. This is only meaningful to vhost user. */ int rte_vhost_driver_unregister(const char *path); +/** + * Set the vdpa device id, enforce single connection per socket + * + * @param path + * The vhost-user socket file path + * @param did + * Device id + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_driver_attach_vdpa_device(const char *path, int did); + +/** + * Unset the vdpa device id + * + * @param path + * The vhost-user socket file path + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_driver_detach_vdpa_device(const char *path); + +/** + * Get the device id + * + * @param path + * The vhost-user socket file path + * @return + * Device id, -1 on failure + */ +__rte_experimental +int +rte_vhost_driver_get_vdpa_device_id(const char *path); + /** * Set the feature bits the vhost-user driver supports. * @@ -254,6 +484,50 @@ int rte_vhost_driver_disable_features(const char *path, uint64_t features); */ int rte_vhost_driver_get_features(const char *path, uint64_t *features); +/** + * Set the protocol feature bits before feature negotiation. + * + * @param path + * The vhost-user socket file path + * @param protocol_features + * Supported protocol features + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_driver_set_protocol_features(const char *path, + uint64_t protocol_features); + +/** + * Get the protocol feature bits before feature negotiation. + * + * @param path + * The vhost-user socket file path + * @param protocol_features + * A pointer to store the queried protocol feature bits + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_driver_get_protocol_features(const char *path, + uint64_t *protocol_features); + +/** + * Get the queue number bits before feature negotiation. + * + * @param path + * The vhost-user socket file path + * @param queue_num + * A pointer to store the queried queue number bits + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_driver_get_queue_num(const char *path, uint32_t *queue_num); + /** * Get the feature bits after negotiation * @@ -363,7 +637,7 @@ int rte_vhost_get_ifname(int vid, char *buf, size_t len); * virtio queue index * * @return - * num of avail entires left + * num of avail entries left */ uint16_t rte_vhost_avail_entries(int vid, uint16_t queue_id); @@ -411,7 +685,7 @@ uint16_t rte_vhost_dequeue_burst(int vid, uint16_t queue_id, /** * Get guest mem table: a list of memory regions. * - * An rte_vhost_vhost_memory object will be allocated internaly, to hold the + * An rte_vhost_vhost_memory object will be allocated internally, to hold the * guest memory regions. Application should free it at destroy_device() * callback. * @@ -439,6 +713,139 @@ int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem); int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx, struct rte_vhost_vring *vring); +/** + * Get guest inflight vring info, including inflight ring and resubmit list. + * + * @param vid + * vhost device ID + * @param vring_idx + * vring index + * @param vring + * the structure to hold the requested inflight vring info + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_get_vhost_ring_inflight(int vid, uint16_t vring_idx, + struct rte_vhost_ring_inflight *vring); + +/** + * Set split inflight descriptor. + * + * This function save descriptors that has been comsumed in available + * ring + * + * @param vid + * vhost device ID + * @param vring_idx + * vring index + * @param idx + * inflight entry index + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_set_inflight_desc_split(int vid, uint16_t vring_idx, + uint16_t idx); + +/** + * Set packed inflight descriptor and get corresponding inflight entry + * + * This function save descriptors that has been comsumed + * + * @param vid + * vhost device ID + * @param vring_idx + * vring index + * @param head + * head of descriptors + * @param last + * last of descriptors + * @param inflight_entry + * corresponding inflight entry + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_set_inflight_desc_packed(int vid, uint16_t vring_idx, + uint16_t head, uint16_t last, uint16_t *inflight_entry); + +/** + * Save the head of list that the last batch of used descriptors. + * + * @param vid + * vhost device ID + * @param vring_idx + * vring index + * @param idx + * descriptor entry index + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_set_last_inflight_io_split(int vid, + uint16_t vring_idx, uint16_t idx); + +/** + * Update the inflight free_head, used_idx and used_wrap_counter. + * + * This function will update status first before updating descriptors + * to used + * + * @param vid + * vhost device ID + * @param vring_idx + * vring index + * @param head + * head of descriptors + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_set_last_inflight_io_packed(int vid, + uint16_t vring_idx, uint16_t head); + +/** + * Clear the split inflight status. + * + * @param vid + * vhost device ID + * @param vring_idx + * vring index + * @param last_used_idx + * last used idx of used ring + * @param idx + * inflight entry index + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_clr_inflight_desc_split(int vid, uint16_t vring_idx, + uint16_t last_used_idx, uint16_t idx); + +/** + * Clear the packed inflight status. + * + * @param vid + * vhost device ID + * @param vring_idx + * vring index + * @param head + * inflight entry index + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_clr_inflight_desc_packed(int vid, uint16_t vring_idx, + uint16_t head); + /** * Notify the guest that used descriptors have been added to the vring. This * function acts as a memory barrier. @@ -464,6 +871,112 @@ int rte_vhost_vring_call(int vid, uint16_t vring_idx); */ uint32_t rte_vhost_rx_queue_count(int vid, uint16_t qid); +/** + * Get log base and log size of the vhost device + * + * @param vid + * vhost device ID + * @param log_base + * vhost log base + * @param log_size + * vhost log size + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_get_log_base(int vid, uint64_t *log_base, uint64_t *log_size); + +/** + * Get last_avail/used_idx of the vhost virtqueue + * + * @param vid + * vhost device ID + * @param queue_id + * vhost queue index + * @param last_avail_idx + * vhost last_avail_idx to get + * @param last_used_idx + * vhost last_used_idx to get + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_get_vring_base(int vid, uint16_t queue_id, + uint16_t *last_avail_idx, uint16_t *last_used_idx); + +/** + * Get last_avail/last_used of the vhost virtqueue + * + * This function is designed for the reconnection and it's specific for + * the packed ring as we can get the two parameters from the inflight + * queueregion + * + * @param vid + * vhost device ID + * @param queue_id + * vhost queue index + * @param last_avail_idx + * vhost last_avail_idx to get + * @param last_used_idx + * vhost last_used_idx to get + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_get_vring_base_from_inflight(int vid, + uint16_t queue_id, uint16_t *last_avail_idx, uint16_t *last_used_idx); + +/** + * Set last_avail/used_idx of the vhost virtqueue + * + * @param vid + * vhost device ID + * @param queue_id + * vhost queue index + * @param last_avail_idx + * last_avail_idx to set + * @param last_used_idx + * last_used_idx to set + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_set_vring_base(int vid, uint16_t queue_id, + uint16_t last_avail_idx, uint16_t last_used_idx); + +/** + * Register external message handling callbacks + * + * @param vid + * vhost device ID + * @param ops + * virtio external callbacks to register + * @param ctx + * additional context passed to the callbacks + * @return + * 0 on success, -1 on failure + */ +__rte_experimental +int +rte_vhost_extern_callback_register(int vid, + struct rte_vhost_user_extern_ops const * const ops, void *ctx); + +/** + * Get vdpa device id for vhost device. + * + * @param vid + * vhost device id + * @return + * device id + */ +__rte_experimental +int +rte_vhost_get_vdpa_device_id(int vid); + #ifdef __cplusplus } #endif