diff options
Diffstat (limited to 'include/rdma/ib_verbs.h')
| -rw-r--r-- | include/rdma/ib_verbs.h | 356 |
1 files changed, 200 insertions, 156 deletions
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 120da1d7f57e..284b00c8fea4 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -49,13 +49,19 @@ #include <linux/scatterlist.h> #include <linux/workqueue.h> #include <linux/socket.h> +#include <linux/irq_poll.h> #include <uapi/linux/if_ether.h> +#include <net/ipv6.h> +#include <net/ip.h> +#include <linux/string.h> +#include <linux/slab.h> #include <linux/atomic.h> #include <linux/mmu_notifier.h> #include <asm/uaccess.h> extern struct workqueue_struct *ib_wq; +extern struct workqueue_struct *ib_comp_wq; union ib_gid { u8 raw[16]; @@ -67,7 +73,17 @@ union ib_gid { extern union ib_gid zgid; +enum ib_gid_type { + /* If link layer is Ethernet, this is RoCE V1 */ + IB_GID_TYPE_IB = 0, + IB_GID_TYPE_ROCE = 0, + IB_GID_TYPE_ROCE_UDP_ENCAP = 1, + IB_GID_TYPE_SIZE +}; + +#define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { + enum ib_gid_type gid_type; struct net_device *ndev; }; @@ -98,6 +114,35 @@ enum rdma_protocol_type { __attribute_const__ enum rdma_transport_type rdma_node_get_transport(enum rdma_node_type node_type); +enum rdma_network_type { + RDMA_NETWORK_IB, + RDMA_NETWORK_ROCE_V1 = RDMA_NETWORK_IB, + RDMA_NETWORK_IPV4, + RDMA_NETWORK_IPV6 +}; + +static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type) +{ + if (network_type == RDMA_NETWORK_IPV4 || + network_type == RDMA_NETWORK_IPV6) + return IB_GID_TYPE_ROCE_UDP_ENCAP; + + /* IB_GID_TYPE_IB same as RDMA_NETWORK_ROCE_V1 */ + return IB_GID_TYPE_IB; +} + +static inline enum rdma_network_type ib_gid_to_network_type(enum ib_gid_type gid_type, + union ib_gid *gid) +{ + if (gid_type == IB_GID_TYPE_IB) + return RDMA_NETWORK_IB; + + if (ipv6_addr_v4mapped((struct in6_addr *)gid)) + return RDMA_NETWORK_IPV4; + else + return RDMA_NETWORK_IPV6; +} + enum rdma_link_layer { IB_LINK_LAYER_UNSPECIFIED, IB_LINK_LAYER_INFINIBAND, @@ -105,24 +150,32 @@ enum rdma_link_layer { }; enum ib_device_cap_flags { - IB_DEVICE_RESIZE_MAX_WR = 1, - IB_DEVICE_BAD_PKEY_CNTR = (1<<1), - IB_DEVICE_BAD_QKEY_CNTR = (1<<2), - IB_DEVICE_RAW_MULTI = (1<<3), - IB_DEVICE_AUTO_PATH_MIG = (1<<4), - IB_DEVICE_CHANGE_PHY_PORT = (1<<5), - IB_DEVICE_UD_AV_PORT_ENFORCE = (1<<6), - IB_DEVICE_CURR_QP_STATE_MOD = (1<<7), - IB_DEVICE_SHUTDOWN_PORT = (1<<8), - IB_DEVICE_INIT_TYPE = (1<<9), - IB_DEVICE_PORT_ACTIVE_EVENT = (1<<10), - IB_DEVICE_SYS_IMAGE_GUID = (1<<11), - IB_DEVICE_RC_RNR_NAK_GEN = (1<<12), - IB_DEVICE_SRQ_RESIZE = (1<<13), - IB_DEVICE_N_NOTIFY_CQ = (1<<14), - IB_DEVICE_LOCAL_DMA_LKEY = (1<<15), - IB_DEVICE_RESERVED = (1<<16), /* old SEND_W_INV */ - IB_DEVICE_MEM_WINDOW = (1<<17), + IB_DEVICE_RESIZE_MAX_WR = (1 << 0), + IB_DEVICE_BAD_PKEY_CNTR = (1 << 1), + IB_DEVICE_BAD_QKEY_CNTR = (1 << 2), + IB_DEVICE_RAW_MULTI = (1 << 3), + IB_DEVICE_AUTO_PATH_MIG = (1 << 4), + IB_DEVICE_CHANGE_PHY_PORT = (1 << 5), + IB_DEVICE_UD_AV_PORT_ENFORCE = (1 << 6), + IB_DEVICE_CURR_QP_STATE_MOD = (1 << 7), + IB_DEVICE_SHUTDOWN_PORT = (1 << 8), + IB_DEVICE_INIT_TYPE = (1 << 9), + IB_DEVICE_PORT_ACTIVE_EVENT = (1 << 10), + IB_DEVICE_SYS_IMAGE_GUID = (1 << 11), + IB_DEVICE_RC_RNR_NAK_GEN = (1 << 12), + IB_DEVICE_SRQ_RESIZE = (1 << 13), + IB_DEVICE_N_NOTIFY_CQ = (1 << 14), + + /* + * This device supports a per-device lkey or stag that can be + * used without performing a memory registration for the local + * memory. Note that ULPs should never check this flag, but + * instead of use the local_dma_lkey flag in the ib_pd structure, + * which will always contain a usable lkey. + */ + IB_DEVICE_LOCAL_DMA_LKEY = (1 << 15), + IB_DEVICE_RESERVED /* old SEND_W_INV */ = (1 << 16), + IB_DEVICE_MEM_WINDOW = (1 << 17), /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB @@ -130,18 +183,35 @@ enum ib_device_cap_flags { * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ - IB_DEVICE_UD_IP_CSUM = (1<<18), - IB_DEVICE_UD_TSO = (1<<19), - IB_DEVICE_XRC = (1<<20), - IB_DEVICE_MEM_MGT_EXTENSIONS = (1<<21), - IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1<<22), - IB_DEVICE_MEM_WINDOW_TYPE_2A = (1<<23), - IB_DEVICE_MEM_WINDOW_TYPE_2B = (1<<24), - IB_DEVICE_RC_IP_CSUM = (1<<25), - IB_DEVICE_RAW_IP_CSUM = (1<<26), - IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29), - IB_DEVICE_SIGNATURE_HANDOVER = (1<<30), - IB_DEVICE_ON_DEMAND_PAGING = (1<<31), + IB_DEVICE_UD_IP_CSUM = (1 << 18), + IB_DEVICE_UD_TSO = (1 << 19), + IB_DEVICE_XRC = (1 << 20), + + /* + * This device supports the IB "base memory management extension", + * which includes support for fast registrations (IB_WR_REG_MR, + * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should + * also be set by any iWarp device which must support FRs to comply + * to the iWarp verbs spec. iWarp devices also support the + * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the + * stag. + */ + IB_DEVICE_MEM_MGT_EXTENSIONS = (1 << 21), + IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1 << 22), + IB_DEVICE_MEM_WINDOW_TYPE_2A = (1 << 23), + IB_DEVICE_MEM_WINDOW_TYPE_2B = (1 << 24), + IB_DEVICE_RC_IP_CSUM = (1 << 25), + IB_DEVICE_RAW_IP_CSUM = (1 << 26), + /* + * Devices should set IB_DEVICE_CROSS_CHANNEL if they + * support execution of WQEs that involve synchronization + * of I/O operations with single completion queue managed + * by hardware. + */ + 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), }; enum ib_signature_prot_cap { @@ -184,6 +254,7 @@ struct ib_odp_caps { enum ib_cq_creation_flags { IB_CQ_FLAGS_TIMESTAMP_COMPLETION = 1 << 0, + IB_CQ_FLAGS_IGNORE_OVERRUN = 1 << 1, }; struct ib_cq_init_attr { @@ -393,6 +464,7 @@ union rdma_protocol_stats { #define RDMA_CORE_CAP_PROT_IB 0x00100000 #define RDMA_CORE_CAP_PROT_ROCE 0x00200000 #define RDMA_CORE_CAP_PROT_IWARP 0x00400000 +#define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000 #define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ | RDMA_CORE_CAP_IB_MAD \ @@ -405,6 +477,12 @@ union rdma_protocol_stats { | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) +#define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \ + (RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \ + | RDMA_CORE_CAP_IB_MAD \ + | RDMA_CORE_CAP_IB_CM \ + | RDMA_CORE_CAP_AF_IB \ + | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ | RDMA_CORE_CAP_IW_CM) #define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \ @@ -519,6 +597,17 @@ struct ib_grh { union ib_gid dgid; }; +union rdma_network_hdr { + struct ib_grh ibgrh; + struct { + /* The IB spec states that if it's IPv4, the header + * is located in the last 20 bytes of the header. + */ + u8 reserved[20]; + struct iphdr roce4grh; + }; +}; + enum { IB_MULTICAST_QPN = 0xffffff }; @@ -734,7 +823,6 @@ enum ib_wc_opcode { IB_WC_RDMA_READ, IB_WC_COMP_SWAP, IB_WC_FETCH_ADD, - IB_WC_BIND_MW, IB_WC_LSO, IB_WC_LOCAL_INV, IB_WC_REG_MR, @@ -755,10 +843,14 @@ enum ib_wc_flags { IB_WC_IP_CSUM_OK = (1<<3), IB_WC_WITH_SMAC = (1<<4), IB_WC_WITH_VLAN = (1<<5), + IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6), }; struct ib_wc { - u64 wr_id; + union { + u64 wr_id; + struct ib_cqe *wr_cqe; + }; enum ib_wc_status status; enum ib_wc_opcode opcode; u32 vendor_err; @@ -777,6 +869,7 @@ struct ib_wc { u8 port_num; /* valid only for DR SMPs on switches */ u8 smac[ETH_ALEN]; u16 vlan_id; + u8 network_hdr_type; }; enum ib_cq_notify_flags { @@ -866,6 +959,9 @@ 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_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_SIGNATURE_EN = 1 << 6, IB_QP_CREATE_USE_GFP_NOIO = 1 << 7, @@ -1027,7 +1123,6 @@ enum ib_wr_opcode { IB_WR_REG_MR, IB_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD, - IB_WR_BIND_MW, IB_WR_REG_SIG_MR, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. @@ -1062,26 +1157,16 @@ struct ib_sge { u32 lkey; }; -/** - * struct ib_mw_bind_info - Parameters for a memory window bind operation. - * @mr: A memory region to bind the memory window to. - * @addr: The address where the memory window should begin. - * @length: The length of the memory window, in bytes. - * @mw_access_flags: Access flags from enum ib_access_flags for the window. - * - * This struct contains the shared parameters for type 1 and type 2 - * memory window bind operations. - */ -struct ib_mw_bind_info { - struct ib_mr *mr; - u64 addr; - u64 length; - int mw_access_flags; +struct ib_cqe { + void (*done)(struct ib_cq *cq, struct ib_wc *wc); }; struct ib_send_wr { struct ib_send_wr *next; - u64 wr_id; + union { + u64 wr_id; + struct ib_cqe *wr_cqe; + }; struct ib_sge *sg_list; int num_sge; enum ib_wr_opcode opcode; @@ -1147,19 +1232,6 @@ static inline struct ib_reg_wr *reg_wr(struct ib_send_wr *wr) return container_of(wr, struct ib_reg_wr, wr); } -struct ib_bind_mw_wr { - struct ib_send_wr wr; - struct ib_mw *mw; - /* The new rkey for the memory window. */ - u32 rkey; - struct ib_mw_bind_info bind_info; -}; - -static inline struct ib_bind_mw_wr *bind_mw_wr(struct ib_send_wr *wr) -{ - return container_of(wr, struct ib_bind_mw_wr, wr); -} - struct ib_sig_handover_wr { struct ib_send_wr wr; struct ib_sig_attrs *sig_attrs; @@ -1175,7 +1247,10 @@ static inline struct ib_sig_handover_wr *sig_handover_wr(struct ib_send_wr *wr) struct ib_recv_wr { struct ib_recv_wr *next; - u64 wr_id; + union { + u64 wr_id; + struct ib_cqe *wr_cqe; + }; struct ib_sge *sg_list; int num_sge; }; @@ -1190,20 +1265,10 @@ enum ib_access_flags { IB_ACCESS_ON_DEMAND = (1<<6), }; -struct ib_phys_buf { - u64 addr; - u64 size; -}; - -struct ib_mr_attr { - struct ib_pd *pd; - u64 device_virt_addr; - u64 size; - int mr_access_flags; - u32 lkey; - u32 rkey; -}; - +/* + * XXX: these are apparently used for ->rereg_user_mr, no idea why they + * are hidden here instead of a uapi header! + */ enum ib_mr_rereg_flags { IB_MR_REREG_TRANS = 1, IB_MR_REREG_PD = (1<<1), @@ -1211,18 +1276,6 @@ enum ib_mr_rereg_flags { IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; -/** - * struct ib_mw_bind - Parameters for a type 1 memory window bind operation. - * @wr_id: Work request id. - * @send_flags: Flags from ib_send_flags enum. - * @bind_info: More parameters of the bind operation. - */ -struct ib_mw_bind { - u64 wr_id; - int send_flags; - struct ib_mw_bind_info bind_info; -}; - struct ib_fmr_attr { int max_pages; int max_maps; @@ -1307,6 +1360,12 @@ 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 */ +}; + struct ib_cq { struct ib_device *device; struct ib_uobject *uobject; @@ -1315,6 +1374,12 @@ struct ib_cq { void *cq_context; int cqe; atomic_t usecnt; /* count number of work queues */ + enum ib_poll_context poll_ctx; + struct ib_wc *wc; + union { + struct irq_poll iop; + struct work_struct work; + }; }; struct ib_srq { @@ -1363,7 +1428,6 @@ struct ib_mr { u64 iova; u32 length; unsigned int page_size; - atomic_t usecnt; /* count number of MWs */ }; struct ib_mw { @@ -1724,11 +1788,6 @@ struct ib_device { int wc_cnt); struct ib_mr * (*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); - struct ib_mr * (*reg_phys_mr)(struct ib_pd *pd, - struct ib_phys_buf *phys_buf_array, - int num_phys_buf, - int mr_access_flags, - u64 *iova_start); struct ib_mr * (*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, @@ -1741,8 +1800,6 @@ struct ib_device { int mr_access_flags, struct ib_pd *pd, struct ib_udata *udata); - int (*query_mr)(struct ib_mr *mr, - struct ib_mr_attr *mr_attr); int (*dereg_mr)(struct ib_mr *mr); struct ib_mr * (*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type, @@ -1750,18 +1807,8 @@ struct ib_device { int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents); - int (*rereg_phys_mr)(struct ib_mr *mr, - int mr_rereg_mask, - struct ib_pd *pd, - struct ib_phys_buf *phys_buf_array, - int num_phys_buf, - int mr_access_flags, - u64 *iova_start); struct ib_mw * (*alloc_mw)(struct ib_pd *pd, enum ib_mw_type type); - int (*bind_mw)(struct ib_qp *qp, - struct ib_mw *mw, - struct ib_mw_bind *mw_bind); int (*dealloc_mw)(struct ib_mw *mw); struct ib_fmr * (*alloc_fmr)(struct ib_pd *pd, int mr_access_flags, @@ -1823,6 +1870,7 @@ struct ib_device { u16 is_switch:1; u8 node_type; u8 phys_port_cnt; + struct ib_device_attr attrs; /** * The following mandatory functions are used only at device @@ -1888,6 +1936,31 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } +static inline bool ib_is_udata_cleared(struct ib_udata *udata, + size_t offset, + size_t len) +{ + const void __user *p = udata->inbuf + offset; + bool ret = false; + u8 *buf; + + if (len > USHRT_MAX) + return false; + + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return false; + + if (copy_from_user(buf, p, len)) + goto free; + + ret = !memchr_inv(buf, 0, len); + +free: + kfree(buf); + return ret; +} + /** * ib_modify_qp_is_ok - Check that the supplied attribute mask * contains all required attributes and no attributes not allowed for @@ -1912,9 +1985,6 @@ int ib_register_event_handler (struct ib_event_handler *event_handler); int ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(struct ib_event *event); -int ib_query_device(struct ib_device *device, - struct ib_device_attr *device_attr); - int ib_query_port(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr); @@ -1968,6 +2038,17 @@ static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num) static inline bool rdma_protocol_roce(const struct ib_device *device, u8 port_num) { + return device->port_immutable[port_num].core_cap_flags & + (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP); +} + +static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u8 port_num) +{ + return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP; +} + +static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u8 port_num) +{ return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; } @@ -1978,8 +2059,8 @@ static inline bool rdma_protocol_iwarp(const struct ib_device *device, u8 port_n static inline bool rdma_ib_or_roce(const struct ib_device *device, u8 port_num) { - return device->port_immutable[port_num].core_cap_flags & - (RDMA_CORE_CAP_PROT_IB | RDMA_CORE_CAP_PROT_ROCE); + return rdma_protocol_ib(device, port_num) || + rdma_protocol_roce(device, port_num); } /** @@ -2220,7 +2301,8 @@ int ib_modify_port(struct ib_device *device, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, - struct net_device *ndev, u8 *port_num, u16 *index); + enum ib_gid_type gid_type, struct net_device *ndev, + u8 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u8 port_num, u16 pkey, u16 *index); @@ -2454,6 +2536,11 @@ static inline int ib_post_recv(struct ib_qp *qp, return qp->device->post_recv(qp, recv_wr, bad_recv_wr); } +struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, + int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx); +void ib_free_cq(struct ib_cq *cq); +int ib_process_cq_direct(struct ib_cq *cq, int budget); + /** * ib_create_cq - Creates a CQ on the specified device. * @device: The device on which to create the CQ. @@ -2839,13 +2926,6 @@ static inline void ib_dma_free_coherent(struct ib_device *dev, } /** - * ib_query_mr - Retrieves information about a specific memory region. - * @mr: The memory region to retrieve information about. - * @mr_attr: The attributes of the specified memory region. - */ -int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr); - -/** * ib_dereg_mr - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. @@ -2882,42 +2962,6 @@ static inline u32 ib_inc_rkey(u32 rkey) } /** - * ib_alloc_mw - Allocates a memory window. - * @pd: The protection domain associated with the memory window. - * @type: The type of the memory window (1 or 2). - */ -struct ib_mw *ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type); - -/** - * ib_bind_mw - Posts a work request to the send queue of the specified - * QP, which binds the memory window to the given address range and - * remote access attributes. - * @qp: QP to post the bind work request on. - * @mw: The memory window to bind. - * @mw_bind: Specifies information about the memory window, including - * its address range, remote access rights, and associated memory region. - * - * If there is no immediate error, the function will update the rkey member - * of the mw parameter to its new value. The bind operation can still fail - * asynchronously. - */ -static inline int ib_bind_mw(struct ib_qp *qp, - struct ib_mw *mw, - struct ib_mw_bind *mw_bind) -{ - /* XXX reference counting in corresponding MR? */ - return mw->device->bind_mw ? - mw->device->bind_mw(qp, mw, mw_bind) : - -ENOSYS; -} - -/** - * ib_dealloc_mw - Deallocates a memory window. - * @mw: The memory window to deallocate. - */ -int ib_dealloc_mw(struct ib_mw *mw); - -/** * 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. |