diff options
Diffstat (limited to 'include/rdma/ib_verbs.h')
| -rw-r--r-- | include/rdma/ib_verbs.h | 304 |
1 files changed, 200 insertions, 104 deletions
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bbc5cfb57cd2..ef2f3986c493 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -100,7 +100,8 @@ void ibdev_notice(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_info(const struct ib_device *ibdev, const char *format, ...); -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define ibdev_dbg(__dev, format, args...) \ dynamic_ibdev_dbg(__dev, format, ##args) #else @@ -133,7 +134,8 @@ do { \ #define ibdev_info_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__) -#if defined(CONFIG_DYNAMIC_DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define ibdev_dbg_ratelimited(ibdev, fmt, ...) \ do { \ @@ -305,7 +307,7 @@ enum ib_device_cap_flags { IB_DEVICE_VIRTUAL_FUNCTION = (1ULL << 33), /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34), - IB_DEVICE_RDMA_NETDEV_OPA_VNIC = (1ULL << 35), + IB_DEVICE_RDMA_NETDEV_OPA = (1ULL << 35), /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = (1ULL << 36), IB_DEVICE_ALLOW_USER_UNREG = (1ULL << 37), @@ -430,8 +432,6 @@ struct ib_device_attr { int max_mcast_qp_attach; int max_total_mcast_qp_attach; int max_ah; - int max_fmr; - int max_map_per_fmr; int max_srq; int max_srq_wr; int max_srq_sge; @@ -462,6 +462,11 @@ enum ib_mtu { IB_MTU_4096 = 5 }; +enum opa_mtu { + OPA_MTU_8192 = 6, + OPA_MTU_10240 = 7 +}; + static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) { switch (mtu) { @@ -488,6 +493,28 @@ static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) return IB_MTU_256; } +static inline int opa_mtu_enum_to_int(enum opa_mtu mtu) +{ + switch (mtu) { + case OPA_MTU_8192: + return 8192; + case OPA_MTU_10240: + return 10240; + default: + return(ib_mtu_enum_to_int((enum ib_mtu)mtu)); + } +} + +static inline enum opa_mtu opa_mtu_int_to_enum(int mtu) +{ + if (mtu >= 10240) + return OPA_MTU_10240; + else if (mtu >= 8192) + return OPA_MTU_8192; + else + return ((enum opa_mtu)ib_mtu_int_to_enum(mtu)); +} + enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, @@ -651,6 +678,7 @@ struct ib_port_attr { enum ib_port_state state; enum ib_mtu max_mtu; enum ib_mtu active_mtu; + u32 phys_mtu; int gid_tbl_len; unsigned int ip_gids:1; /* This is the value from PortInfo CapabilityMask, defined by IBA */ @@ -880,6 +908,12 @@ struct ib_mr_status { */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); +struct rdma_ah_init_attr { + struct rdma_ah_attr *ah_attr; + u32 flags; + struct net_device *xmit_slave; +}; + enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, @@ -1006,9 +1040,9 @@ enum ib_cq_notify_flags { }; enum ib_srq_type { - IB_SRQT_BASIC, - IB_SRQT_XRC, - IB_SRQT_TM, + IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC, + IB_SRQT_XRC = IB_UVERBS_SRQT_XRC, + IB_SRQT_TM = IB_UVERBS_SRQT_TM, }; static inline bool ib_srq_has_cq(enum ib_srq_type srq_type) @@ -1077,16 +1111,16 @@ enum ib_qp_type { IB_QPT_SMI, IB_QPT_GSI, - IB_QPT_RC, - IB_QPT_UC, - IB_QPT_UD, + IB_QPT_RC = IB_UVERBS_QPT_RC, + IB_QPT_UC = IB_UVERBS_QPT_UC, + IB_QPT_UD = IB_UVERBS_QPT_UD, IB_QPT_RAW_IPV6, IB_QPT_RAW_ETHERTYPE, - IB_QPT_RAW_PACKET = 8, - IB_QPT_XRC_INI = 9, - IB_QPT_XRC_TGT, + IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET, + IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI, + IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT, IB_QPT_MAX, - IB_QPT_DRIVER = 0xFF, + IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER, /* Reserve a range for qp types internal to the low level driver. * These qp types will not be visible at the IB core layer, so the * IB_QPT_MAX usages should not be affected in the core layer @@ -1105,17 +1139,21 @@ enum ib_qp_type { enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, - IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = 1 << 1, + IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = + IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, IB_QP_CREATE_CROSS_CHANNEL = 1 << 2, IB_QP_CREATE_MANAGED_SEND = 1 << 3, IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_INTEGRITY_EN = 1 << 6, - /* FREE = 1 << 7, */ - IB_QP_CREATE_SCATTER_FCS = 1 << 8, - IB_QP_CREATE_CVLAN_STRIPPING = 1 << 9, + IB_QP_CREATE_NETDEV_USE = 1 << 7, + IB_QP_CREATE_SCATTER_FCS = + IB_UVERBS_QP_CREATE_SCATTER_FCS, + IB_QP_CREATE_CVLAN_STRIPPING = + IB_UVERBS_QP_CREATE_CVLAN_STRIPPING, IB_QP_CREATE_SOURCE_QPN = 1 << 10, - IB_QP_CREATE_PCI_WRITE_END_PADDING = 1 << 11, + IB_QP_CREATE_PCI_WRITE_END_PADDING = + IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, @@ -1267,6 +1305,7 @@ struct ib_qp_attr { u8 alt_port_num; u8 alt_timeout; u32 rate_limit; + struct net_device *xmit_slave; }; enum ib_wr_opcode { @@ -1436,12 +1475,6 @@ enum ib_mr_rereg_flags { IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; -struct ib_fmr_attr { - int max_pages; - int max_maps; - u8 page_shift; -}; - struct ib_umem; enum rdma_remove_reason { @@ -1456,6 +1489,11 @@ enum rdma_remove_reason { RDMA_REMOVE_DRIVER_REMOVE, /* uobj is being cleaned-up before being committed */ RDMA_REMOVE_ABORT, + /* + * uobj has been fully created, with the uobj->object set, but is being + * cleaned up before being comitted + */ + RDMA_REMOVE_ABORT_HWOBJ, }; struct ib_rdmacg_object { @@ -1544,10 +1582,12 @@ struct ib_ah { typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context); enum ib_poll_context { - IB_POLL_DIRECT, /* caller context, no hw completions */ IB_POLL_SOFTIRQ, /* poll from softirq context */ IB_POLL_WORKQUEUE, /* poll from workqueue */ IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */ + IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE, + + IB_POLL_DIRECT, /* caller context, no hw completions */ }; struct ib_cq { @@ -1557,9 +1597,11 @@ struct ib_cq { void (*event_handler)(struct ib_event *, void *); void *cq_context; int cqe; + unsigned int cqe_used; atomic_t usecnt; /* count number of work queues */ enum ib_poll_context poll_ctx; struct ib_wc *wc; + struct list_head pool_entry; union { struct irq_poll iop; struct work_struct work; @@ -1569,7 +1611,9 @@ struct ib_cq { /* updated only by trace points */ ktime_t timestamp; - bool interrupt; + u8 interrupt:1; + u8 shared:1; + unsigned int comp_vector; /* * Implementation details of the RDMA core, don't use in drivers: @@ -1614,7 +1658,7 @@ enum ib_raw_packet_caps { }; enum ib_wq_type { - IB_WQT_RQ + IB_WQT_RQ = IB_UVERBS_WQT_RQ, }; enum ib_wq_state { @@ -1637,10 +1681,11 @@ struct ib_wq { }; enum ib_wq_flags { - IB_WQ_FLAGS_CVLAN_STRIPPING = 1 << 0, - IB_WQ_FLAGS_SCATTER_FCS = 1 << 1, - IB_WQ_FLAGS_DELAY_DROP = 1 << 2, - IB_WQ_FLAGS_PCI_WRITE_END_PADDING = 1 << 3, + IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING, + IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS, + IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP, + IB_WQ_FLAGS_PCI_WRITE_END_PADDING = + IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING, }; struct ib_wq_init_attr { @@ -1804,14 +1849,6 @@ struct ib_mw { enum ib_mw_type type; }; -struct ib_fmr { - struct ib_device *device; - struct ib_pd *pd; - struct list_head list; - u32 lkey; - u32 rkey; -}; - /* Supported steering options */ enum ib_flow_attr_type { /* steering according to rule specifications */ @@ -2198,6 +2235,7 @@ struct rdma_netdev { void *clnt_priv; struct ib_device *hca; u8 port_num; + int mtu; /* * cleanup function must be specified. @@ -2403,8 +2441,8 @@ struct ib_device_ops { void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); void (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); - int (*create_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata); + int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, + struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); void (*destroy_ah)(struct ib_ah *ah, u32 flags); @@ -2453,12 +2491,6 @@ struct ib_device_ops { struct ib_mw *(*alloc_mw)(struct ib_pd *pd, enum ib_mw_type type, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); - struct ib_fmr *(*alloc_fmr)(struct ib_pd *pd, int mr_access_flags, - struct ib_fmr_attr *fmr_attr); - int (*map_phys_fmr)(struct ib_fmr *fmr, u64 *page_list, int list_len, - u64 iova); - int (*unmap_fmr)(struct list_head *fmr_list); - int (*dealloc_fmr)(struct ib_fmr *fmr); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); struct ib_xrcd *(*alloc_xrcd)(struct ib_device *device, @@ -2687,6 +2719,10 @@ struct ib_device { #endif u32 index; + + spinlock_t cq_pools_lock; + struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1]; + struct rdma_restrack_root *res; const struct uapi_definition *driver_def; @@ -2709,12 +2745,13 @@ struct ib_device { /* Used by iWarp CM */ char iw_ifname[IFNAMSIZ]; u32 iw_driver_flags; + u32 lag_flags; }; struct ib_client_nl_info; struct ib_client { const char *name; - void (*add) (struct ib_device *); + int (*add)(struct ib_device *ibdev); void (*remove)(struct ib_device *, void *client_data); void (*rename)(struct ib_device *dev, void *client_data); int (*get_nl_info)(struct ib_device *ibdev, void *client_data, @@ -3355,6 +3392,55 @@ static inline unsigned int rdma_find_pg_bit(unsigned long addr, return __fls(pgsz); } +/** + * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not. + * @device: Device + * @port_num: 1 based Port number + * + * Return true if port is an Intel OPA port , false if not + */ +static inline bool rdma_core_cap_opa_port(struct ib_device *device, + u32 port_num) +{ + return (device->port_data[port_num].immutable.core_cap_flags & + RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA; +} + +/** + * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value. + * @device: Device + * @port_num: Port number + * @mtu: enum value of MTU + * + * Return the MTU size supported by the port as an integer value. Will return + * -1 if enum value of mtu is not supported. + */ +static inline int rdma_mtu_enum_to_int(struct ib_device *device, u8 port, + int mtu) +{ + if (rdma_core_cap_opa_port(device, port)) + return opa_mtu_enum_to_int((enum opa_mtu)mtu); + else + return ib_mtu_enum_to_int((enum ib_mtu)mtu); +} + +/** + * rdma_mtu_from_attr - Return the mtu of the port from the port attribute. + * @device: Device + * @port_num: Port number + * @attr: port attribute + * + * Return the MTU size supported by the port as an integer value. + */ +static inline int rdma_mtu_from_attr(struct ib_device *device, u8 port, + struct ib_port_attr *attr) +{ + if (rdma_core_cap_opa_port(device, port)) + return attr->phys_mtu; + else + return ib_mtu_enum_to_int(attr->max_mtu); +} + int ib_set_vf_link_state(struct ib_device *device, int vf, u8 port, int state); int ib_get_vf_config(struct ib_device *device, int vf, u8 port, @@ -3551,21 +3637,18 @@ static inline int rdma_destroy_ah(struct ib_ah *ah, u32 flags) return rdma_destroy_ah_user(ah, flags, NULL); } -/** - * ib_create_srq - Creates a SRQ associated with the specified protection - * domain. - * @pd: The protection domain associated with the SRQ. - * @srq_init_attr: A list of initial attributes required to create the - * SRQ. If SRQ creation succeeds, then the attributes are updated to - * the actual capabilities of the created SRQ. - * - * srq_attr->max_wr and srq_attr->max_sge are read the determine the - * requested size of the SRQ, and set to the actual values allocated - * on return. If ib_create_srq() succeeds, then max_wr and max_sge - * will always be at least as large as the requested values. - */ -struct ib_srq *ib_create_srq(struct ib_pd *pd, - struct ib_srq_init_attr *srq_init_attr); +struct ib_srq *ib_create_srq_user(struct ib_pd *pd, + struct ib_srq_init_attr *srq_init_attr, + struct ib_usrq_object *uobject, + struct ib_udata *udata); +static inline struct ib_srq * +ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr) +{ + if (!pd->device->ops.create_srq) + return ERR_PTR(-EOPNOTSUPP); + + return ib_create_srq_user(pd, srq_init_attr, NULL, NULL); +} /** * ib_modify_srq - Modifies the attributes for the specified SRQ. @@ -3816,6 +3899,8 @@ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, * ib_free_cq_user - Free kernel/user CQ * @cq: The CQ to free * @udata: Valid user data or NULL for kernel objects + * + * NOTE: This function shouldn't be called on shared CQs. */ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata); @@ -3941,6 +4026,12 @@ static inline int ib_req_notify_cq(struct ib_cq *cq, return cq->device->ops.req_notify_cq(cq, flags); } +struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe, + int comp_vector_hint, + enum ib_poll_context poll_ctx); + +void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe); + /** * ib_req_ncomp_notif - Request completion notification when there are * at least the specified number of unreaped completions on the CQ. @@ -4209,45 +4300,6 @@ static inline u32 ib_inc_rkey(u32 rkey) } /** - * ib_alloc_fmr - Allocates a unmapped fast memory region. - * @pd: The protection domain associated with the unmapped region. - * @mr_access_flags: Specifies the memory access rights. - * @fmr_attr: Attributes of the unmapped region. - * - * A fast memory region must be mapped before it can be used as part of - * a work request. - */ -struct ib_fmr *ib_alloc_fmr(struct ib_pd *pd, - int mr_access_flags, - struct ib_fmr_attr *fmr_attr); - -/** - * ib_map_phys_fmr - Maps a list of physical pages to a fast memory region. - * @fmr: The fast memory region to associate with the pages. - * @page_list: An array of physical pages to map to the fast memory region. - * @list_len: The number of pages in page_list. - * @iova: The I/O virtual address to use with the mapped region. - */ -static inline int ib_map_phys_fmr(struct ib_fmr *fmr, - u64 *page_list, int list_len, - u64 iova) -{ - return fmr->device->ops.map_phys_fmr(fmr, page_list, list_len, iova); -} - -/** - * ib_unmap_fmr - Removes the mapping from a list of fast memory regions. - * @fmr_list: A linked list of fast memory regions to unmap. - */ -int ib_unmap_fmr(struct list_head *fmr_list); - -/** - * ib_dealloc_fmr - Deallocates a fast memory region. - * @fmr: The fast memory region to deallocate. - */ -int ib_dealloc_fmr(struct ib_fmr *fmr); - -/** * ib_attach_mcast - Attaches the specified QP to a multicast group. * @qp: QP to attach to the multicast group. The QP must be type * IB_QPT_UD. @@ -4701,4 +4753,48 @@ static inline struct ib_device *rdma_device_to_ibdev(struct device *device) bool rdma_dev_access_netns(const struct ib_device *device, const struct net *net); + +#define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000) +#define IB_GRH_FLOWLABEL_MASK (0x000FFFFF) + +/** + * rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based + * on the flow_label + * + * This function will convert the 20 bit flow_label input to a valid RoCE v2 + * UDP src port 14 bit value. All RoCE V2 drivers should use this same + * convention. + */ +static inline u16 rdma_flow_label_to_udp_sport(u32 fl) +{ + u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000; + + fl_low ^= fl_high >> 14; + return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN); +} + +/** + * rdma_calc_flow_label - generate a RDMA symmetric flow label value based on + * local and remote qpn values + * + * This function folded the multiplication results of two qpns, 24 bit each, + * fields, and converts it to a 20 bit results. + * + * This function will create symmetric flow_label value based on the local + * and remote qpn values. this will allow both the requester and responder + * to calculate the same flow_label for a given connection. + * + * This helper function should be used by driver in case the upper layer + * provide a zero flow_label value. This is to improve entropy of RDMA + * traffic in the network. + */ +static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn) +{ + u64 v = (u64)lqpn * rqpn; + + v ^= v >> 20; + v ^= v >> 40; + + return (u32)(v & IB_GRH_FLOWLABEL_MASK); +} #endif /* IB_VERBS_H */ |