diff options
Diffstat (limited to 'include/rdma/ib_verbs.h')
| -rw-r--r-- | include/rdma/ib_verbs.h | 329 |
1 files changed, 241 insertions, 88 deletions
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index fb2cef4e9747..e1f96737c2a1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -217,9 +217,10 @@ enum ib_device_cap_flags { IB_DEVICE_CROSS_CHANNEL = (1 << 27), IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29), IB_DEVICE_SIGNATURE_HANDOVER = (1 << 30), - IB_DEVICE_ON_DEMAND_PAGING = (1 << 31), + IB_DEVICE_ON_DEMAND_PAGING = (1ULL << 31), IB_DEVICE_SG_GAPS_REG = (1ULL << 32), - IB_DEVICE_VIRTUAL_FUNCTION = ((u64)1 << 33), + IB_DEVICE_VIRTUAL_FUNCTION = (1ULL << 33), + IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34), }; enum ib_signature_prot_cap { @@ -402,56 +403,55 @@ enum ib_port_speed { IB_SPEED_EDR = 32 }; -struct ib_protocol_stats { - /* TBD... */ -}; - -struct iw_protocol_stats { - u64 ipInReceives; - u64 ipInHdrErrors; - u64 ipInTooBigErrors; - u64 ipInNoRoutes; - u64 ipInAddrErrors; - u64 ipInUnknownProtos; - u64 ipInTruncatedPkts; - u64 ipInDiscards; - u64 ipInDelivers; - u64 ipOutForwDatagrams; - u64 ipOutRequests; - u64 ipOutDiscards; - u64 ipOutNoRoutes; - u64 ipReasmTimeout; - u64 ipReasmReqds; - u64 ipReasmOKs; - u64 ipReasmFails; - u64 ipFragOKs; - u64 ipFragFails; - u64 ipFragCreates; - u64 ipInMcastPkts; - u64 ipOutMcastPkts; - u64 ipInBcastPkts; - u64 ipOutBcastPkts; - - u64 tcpRtoAlgorithm; - u64 tcpRtoMin; - u64 tcpRtoMax; - u64 tcpMaxConn; - u64 tcpActiveOpens; - u64 tcpPassiveOpens; - u64 tcpAttemptFails; - u64 tcpEstabResets; - u64 tcpCurrEstab; - u64 tcpInSegs; - u64 tcpOutSegs; - u64 tcpRetransSegs; - u64 tcpInErrs; - u64 tcpOutRsts; -}; - -union rdma_protocol_stats { - struct ib_protocol_stats ib; - struct iw_protocol_stats iw; -}; +/** + * struct rdma_hw_stats + * @timestamp - Used by the core code to track when the last update was + * @lifespan - Used by the core code to determine how old the counters + * should be before being updated again. Stored in jiffies, defaults + * to 10 milliseconds, drivers can override the default be specifying + * their own value during their allocation routine. + * @name - Array of pointers to static names used for the counters in + * directory. + * @num_counters - How many hardware counters there are. If name is + * shorter than this number, a kernel oops will result. Driver authors + * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) + * in their code to prevent this. + * @value - Array of u64 counters that are accessed by the sysfs code and + * filled in by the drivers get_stats routine + */ +struct rdma_hw_stats { + unsigned long timestamp; + unsigned long lifespan; + const char * const *names; + int num_counters; + u64 value[]; +}; + +#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 +/** + * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct + * for drivers. + * @names - Array of static const char * + * @num_counters - How many elements in array + * @lifespan - How many milliseconds between updates + */ +static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct( + const char * const *names, int num_counters, + unsigned long lifespan) +{ + struct rdma_hw_stats *stats; + + stats = kzalloc(sizeof(*stats) + num_counters * sizeof(u64), + GFP_KERNEL); + if (!stats) + return NULL; + stats->names = names; + stats->num_counters = num_counters; + stats->lifespan = msecs_to_jiffies(lifespan); + + return stats; +} + /* Define bits for the various functionality this port needs to be supported by * the core. @@ -562,6 +562,7 @@ enum ib_event_type { IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, + IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); @@ -572,6 +573,7 @@ struct ib_event { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; + struct ib_wq *wq; u8 port_num; } element; enum ib_event_type event; @@ -931,6 +933,13 @@ struct ib_qp_cap { u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; + + /* + * Maximum number of rdma_rw_ctx structures in flight at a time. + * ib_create_qp() will calculate the right amount of neededed WRs + * and MRs based on this. + */ + u32 max_rdma_ctxs; }; enum ib_sig_type { @@ -981,6 +990,7 @@ enum ib_qp_create_flags { IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_SIGNATURE_EN = 1 << 6, IB_QP_CREATE_USE_GFP_NOIO = 1 << 7, + IB_QP_CREATE_SCATTER_FCS = 1 << 8, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, @@ -1002,7 +1012,12 @@ struct ib_qp_init_attr { enum ib_sig_type sq_sig_type; enum ib_qp_type qp_type; enum ib_qp_create_flags create_flags; - u8 port_num; /* special QP types only */ + + /* + * Only needed for special QP types, or when using the RW API. + */ + u8 port_num; + struct ib_rwq_ind_table *rwq_ind_tbl; }; struct ib_qp_open_attr { @@ -1311,6 +1326,8 @@ struct ib_ucontext { struct list_head ah_list; struct list_head xrcd_list; struct list_head rule_list; + struct list_head wq_list; + struct list_head rwq_ind_tbl_list; int closing; struct pid *tgid; @@ -1416,14 +1433,80 @@ struct ib_srq { } ext; }; +enum ib_wq_type { + IB_WQT_RQ +}; + +enum ib_wq_state { + IB_WQS_RESET, + IB_WQS_RDY, + IB_WQS_ERR +}; + +struct ib_wq { + struct ib_device *device; + struct ib_uobject *uobject; + void *wq_context; + void (*event_handler)(struct ib_event *, void *); + struct ib_pd *pd; + struct ib_cq *cq; + u32 wq_num; + enum ib_wq_state state; + enum ib_wq_type wq_type; + atomic_t usecnt; +}; + +struct ib_wq_init_attr { + void *wq_context; + enum ib_wq_type wq_type; + u32 max_wr; + u32 max_sge; + struct ib_cq *cq; + void (*event_handler)(struct ib_event *, void *); +}; + +enum ib_wq_attr_mask { + IB_WQ_STATE = 1 << 0, + IB_WQ_CUR_STATE = 1 << 1, +}; + +struct ib_wq_attr { + enum ib_wq_state wq_state; + enum ib_wq_state curr_wq_state; +}; + +struct ib_rwq_ind_table { + struct ib_device *device; + struct ib_uobject *uobject; + atomic_t usecnt; + u32 ind_tbl_num; + u32 log_ind_tbl_size; + struct ib_wq **ind_tbl; +}; + +struct ib_rwq_ind_table_init_attr { + u32 log_ind_tbl_size; + /* Each entry is a pointer to Receive Work Queue */ + struct ib_wq **ind_tbl; +}; + +/* + * @max_write_sge: Maximum SGE elements per RDMA WRITE request. + * @max_read_sge: Maximum SGE elements per RDMA READ request. + */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; struct ib_cq *send_cq; struct ib_cq *recv_cq; + spinlock_t mr_lock; + int mrs_used; + struct list_head rdma_mrs; + struct list_head sig_mrs; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct list_head xrcd_list; + /* count times opened, mcast attaches, flow attaches */ atomic_t usecnt; struct list_head open_list; @@ -1432,18 +1515,25 @@ struct ib_qp { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; + u32 max_write_sge; + u32 max_read_sge; enum ib_qp_type qp_type; + struct ib_rwq_ind_table *rwq_ind_tbl; }; struct ib_mr { struct ib_device *device; struct ib_pd *pd; - struct ib_uobject *uobject; u32 lkey; u32 rkey; u64 iova; u32 length; unsigned int page_size; + bool need_inval; + union { + struct ib_uobject *uobject; /* user */ + struct list_head qp_entry; /* FR */ + }; }; struct ib_mw { @@ -1485,6 +1575,7 @@ enum ib_flow_spec_type { IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, + IB_FLOW_SPEC_IPV6 = 0x31, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41 @@ -1546,6 +1637,18 @@ struct ib_flow_spec_ipv4 { struct ib_flow_ipv4_filter mask; }; +struct ib_flow_ipv6_filter { + u8 src_ip[16]; + u8 dst_ip[16]; +}; + +struct ib_flow_spec_ipv6 { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_ipv6_filter val; + struct ib_flow_ipv6_filter mask; +}; + struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; @@ -1567,6 +1670,7 @@ union ib_flow_spec { struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; + struct ib_flow_spec_ipv6 ipv6; }; struct ib_flow_attr { @@ -1685,8 +1789,29 @@ struct ib_device { struct iw_cm_verbs *iwcm; - int (*get_protocol_stats)(struct ib_device *device, - union rdma_protocol_stats *stats); + /** + * alloc_hw_stats - Allocate a struct rdma_hw_stats and fill in the + * driver initialized data. The struct is kfree()'ed by the sysfs + * core when the device is removed. A lifespan of -1 in the return + * struct tells the core to set a default lifespan. + */ + struct rdma_hw_stats *(*alloc_hw_stats)(struct ib_device *device, + u8 port_num); + /** + * get_hw_stats - Fill in the counter value(s) in the stats struct. + * @index - The index in the value array we wish to have updated, or + * num_counters if we want all stats updated + * Return codes - + * < 0 - Error, no counters updated + * index - Updated the single counter pointed to by index + * num_counters - Updated all counters (will reset the timestamp + * and prevent further calls for lifespan milliseconds) + * Drivers are allowed to update all counters in leiu of just the + * one given in index at their option + */ + int (*get_hw_stats)(struct ib_device *device, + struct rdma_hw_stats *stats, + u8 port, int index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); @@ -1827,7 +1952,8 @@ struct ib_device { u32 max_num_sg); int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, - int sg_nents); + int sg_nents, + unsigned int *sg_offset); struct ib_mw * (*alloc_mw)(struct ib_pd *pd, enum ib_mw_type type, struct ib_udata *udata); @@ -1878,7 +2004,18 @@ struct ib_device { struct ifla_vf_stats *stats); int (*set_vf_guid)(struct ib_device *device, int vf, u8 port, u64 guid, int type); - + struct ib_wq * (*create_wq)(struct ib_pd *pd, + struct ib_wq_init_attr *init_attr, + struct ib_udata *udata); + int (*destroy_wq)(struct ib_wq *wq); + int (*modify_wq)(struct ib_wq *wq, + struct ib_wq_attr *attr, + u32 wq_attr_mask, + struct ib_udata *udata); + struct ib_rwq_ind_table * (*create_rwq_ind_table)(struct ib_device *device, + struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata); + int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dma_mapping_ops *dma_ops; struct module *owner; @@ -1903,6 +2040,8 @@ struct ib_device { u8 node_type; u8 phys_port_cnt; struct ib_device_attr attrs; + struct attribute_group *hw_stats_ag; + struct rdma_hw_stats *hw_stats; /** * The following mandatory functions are used only at device @@ -1911,6 +2050,7 @@ struct ib_device { * in fast paths. */ int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *); + void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len); }; struct ib_client { @@ -1946,6 +2086,8 @@ struct ib_client { struct ib_device *ib_alloc_device(size_t size); void ib_dealloc_device(struct ib_device *device); +void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len); + int ib_register_device(struct ib_device *device, int (*port_callback)(struct ib_device *, u8, struct kobject *)); @@ -1973,22 +2115,17 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t len) { const void __user *p = udata->inbuf + offset; - bool ret = false; + bool ret; u8 *buf; if (len > USHRT_MAX) return false; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) + buf = memdup_user(p, len); + if (IS_ERR(buf)) return false; - if (copy_from_user(buf, p, len)) - goto free; - ret = !memchr_inv(buf, 0, len); - -free: kfree(buf); return ret; } @@ -2317,6 +2454,18 @@ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device, device->add_gid && device->del_gid; } +/* + * Check if the device supports READ W/ INVALIDATE. + */ +static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) +{ + /* + * iWarp drivers must support READ W/ INVALIDATE. No other protocol + * has support for it yet. + */ + return rdma_protocol_iwarp(dev, port_num); +} + int ib_query_gid(struct ib_device *device, u8 port_num, int index, union ib_gid *gid, struct ib_gid_attr *attr); @@ -2762,19 +2911,19 @@ static inline void ib_dma_unmap_single(struct ib_device *dev, static inline u64 ib_dma_map_single_attrs(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { return dma_map_single_attrs(dev->dma_device, cpu_addr, size, - direction, attrs); + direction, dma_attrs); } static inline void ib_dma_unmap_single_attrs(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { return dma_unmap_single_attrs(dev->dma_device, addr, size, - direction, attrs); + direction, dma_attrs); } /** @@ -2849,17 +2998,18 @@ static inline void ib_dma_unmap_sg(struct ib_device *dev, static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { - return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, attrs); + return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, + dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { - dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, attrs); + dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_sg_dma_address - Return the DMA address from a scatter/gather entry @@ -3110,30 +3260,33 @@ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); - -int ib_map_mr_sg(struct ib_mr *mr, - struct scatterlist *sg, - int sg_nents, - unsigned int page_size); +struct ib_wq *ib_create_wq(struct ib_pd *pd, + struct ib_wq_init_attr *init_attr); +int ib_destroy_wq(struct ib_wq *wq); +int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr, + u32 wq_attr_mask); +struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device, + struct ib_rwq_ind_table_init_attr* + wq_ind_table_init_attr); +int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table); + +int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, + unsigned int *sg_offset, unsigned int page_size); static inline int -ib_map_mr_sg_zbva(struct ib_mr *mr, - struct scatterlist *sg, - int sg_nents, - unsigned int page_size) +ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, + unsigned int *sg_offset, unsigned int page_size) { int n; - n = ib_map_mr_sg(mr, sg, sg_nents, page_size); + n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size); mr->iova = 0; return n; } -int ib_sg_to_pages(struct ib_mr *mr, - struct scatterlist *sgl, - int sg_nents, - int (*set_page)(struct ib_mr *, u64)); +int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, + unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64)); void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); |