/* SPDX-License-Identifier: GPL-2.0 */ /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Definitions for SMC Connections, Link Groups and Links * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun */ #ifndef _SMC_CORE_H #define _SMC_CORE_H #include #include #include "smc.h" #include "smc_ib.h" #define SMC_RMBS_PER_LGR_MAX 255 /* max. # of RMBs per link group */ struct smc_lgr_list { /* list of link group definition */ struct list_head list; spinlock_t lock; /* protects list of link groups */ u32 num; /* unique link group number */ }; enum smc_lgr_role { /* possible roles of a link group */ SMC_CLNT, /* client */ SMC_SERV /* server */ }; enum smc_link_state { /* possible states of a link */ SMC_LNK_UNUSED, /* link is unused */ SMC_LNK_INACTIVE, /* link is inactive */ SMC_LNK_ACTIVATING, /* link is being activated */ SMC_LNK_ACTIVE, /* link is active */ }; #define SMC_WR_BUF_SIZE 48 /* size of work request buffer */ struct smc_wr_buf { u8 raw[SMC_WR_BUF_SIZE]; }; #define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */ enum smc_wr_reg_state { POSTED, /* ib_wr_reg_mr request posted */ CONFIRMED, /* ib_wr_reg_mr response: successful */ FAILED /* ib_wr_reg_mr response: failure */ }; struct smc_rdma_sge { /* sges for RDMA writes */ struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; }; #define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per * message send */ struct smc_rdma_sges { /* sges per message send */ struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; }; struct smc_rdma_wr { /* work requests per message * send */ struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; }; struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ struct ib_pd *roce_pd; /* IB protection domain, * unique for every RoCE QP */ struct ib_qp *roce_qp; /* IB queue pair */ struct ib_qp_attr qp_attr; /* IB queue pair attributes */ struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ struct completion *wr_tx_compl; /* WR send CQE completion */ /* above four vectors have wr_tx_cnt elements and use the same index */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ atomic_long_t wr_tx_id; /* seq # of last sent WR */ unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */ struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */ struct ib_sge *wr_rx_sges; /* WR recv scatter meta data */ /* above three vectors have wr_rx_cnt elements and use the same index */ dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ u64 wr_rx_id; /* seq # of last recv WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */ u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/ u8 sgid_index; /* gid index for vlan id */ u32 peer_qpn; /* QP number of peer */ enum ib_mtu path_mtu; /* used mtu */ enum ib_mtu peer_mtu; /* mtu size of peer */ u32 psn_initial; /* QP tx initial packet seqno */ u32 peer_psn; /* QP rx initial packet seqno */ u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */ u8 peer_gid[SMC_GID_SIZE]; /* gid of peer*/ u8 link_id; /* unique # within link group */ u8 link_idx; /* index in lgr link array */ u8 link_is_asym; /* is link asymmetric? */ struct smc_link_group *lgr; /* parent link group */ struct work_struct link_down_wrk; /* wrk to bring link down */ enum smc_link_state state; /* state of link */ struct delayed_work llc_testlink_wrk; /* testlink worker */ struct completion llc_testlink_resp; /* wait for rx of testlink */ int llc_testlink_time; /* testlink interval */ }; /* For now we just allow one parallel link per link group. The SMC protocol * allows more (up to 8). */ #define SMC_LINKS_PER_LGR_MAX 3 #define SMC_SINGLE_LINK 0 #define SMC_FIRST_CONTACT 1 /* first contact to a peer */ #define SMC_REUSE_CONTACT 0 /* follow-on contact to a peer*/ /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */ struct smc_buf_desc { struct list_head list; void *cpu_addr; /* virtual address of buffer */ struct page *pages; int len; /* length of buffer */ u32 used; /* currently used / unused */ union { struct { /* SMC-R */ struct sg_table sgt[SMC_LINKS_PER_LGR_MAX]; /* virtual buffer */ struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; /* for rmb only: memory region * incl. rkey provided to peer */ u32 order; /* allocation order */ u8 is_conf_rkey; /* confirm_rkey done */ u8 is_reg_mr[SMC_LINKS_PER_LGR_MAX]; /* mem region registered */ u8 is_map_ib[SMC_LINKS_PER_LGR_MAX]; /* mem region mapped to lnk */ u8 is_reg_err; /* buffer registration err */ }; struct { /* SMC-D */ unsigned short sba_idx; /* SBA index number */ u64 token; /* DMB token number */ dma_addr_t dma_addr; /* DMA address */ }; }; }; struct smc_rtoken { /* address/key of remote RMB */ u64 dma_addr; u32 rkey; }; #define SMC_LGR_ID_SIZE 4 #define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */ #define SMC_RMBE_SIZES 16 /* number of distinct RMBE sizes */ /* theoretically, the RFC states that largest size would be 512K, * i.e. compressed 5 and thus 6 sizes (0..5), despite * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15) */ struct smcd_dev; enum smc_lgr_type { /* redundancy state of lgr */ SMC_LGR_NONE, /* no active links, lgr to be deleted */ SMC_LGR_SINGLE, /* 1 active RNIC on each peer */ SMC_LGR_SYMMETRIC, /* 2 active RNICs on each peer */ SMC_LGR_ASYMMETRIC_PEER, /* local has 2, peer 1 active RNICs */ SMC_LGR_ASYMMETRIC_LOCAL, /* local has 1, peer 2 active RNICs */ }; enum smc_llc_flowtype { SMC_LLC_FLOW_NONE = 0, SMC_LLC_FLOW_ADD_LINK = 2, SMC_LLC_FLOW_DEL_LINK = 4, SMC_LLC_FLOW_RKEY = 6, }; struct smc_llc_qentry; struct smc_llc_flow { enum smc_llc_flowtype type; struct smc_llc_qentry *qentry; }; struct smc_link_group { struct list_head list; struct rb_root conns_all; /* connection tree */ rwlock_t conns_lock; /* protects conns_all */ unsigned int conns_num; /* current # of connections */ unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ struct mutex sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ struct mutex rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ struct work_struct terminate_work; /* abnormal lgr termination */ u8 sync_err : 1; /* lgr no longer fits to peer */ u8 terminating : 1;/* lgr is terminating */ u8 freefast : 1; /* free worker scheduled fast */ u8 freeing : 1; /* lgr is being freed */ bool is_smcd; /* SMC-R or SMC-D */ union { struct { /* SMC-R */ enum smc_lgr_role role; /* client or server */ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ char peer_systemid[SMC_SYSTEMID_LEN]; /* unique system_id of peer */ struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] [SMC_LINKS_PER_LGR_MAX]; /* remote addr/key pairs */ DECLARE_BITMAP(rtokens_used_mask, SMC_RMBS_PER_LGR_MAX); /* used rtoken elements */ u8 next_link_id; enum smc_lgr_type type; /* redundancy state */ u8 pnet_id[SMC_MAX_PNETID_LEN + 1]; /* pnet id of this lgr */ struct list_head llc_event_q; /* queue for llc events */ spinlock_t llc_event_q_lock; /* protects llc_event_q */ struct mutex llc_conf_mutex; /* protects lgr reconfig. */ struct work_struct llc_add_link_work; struct work_struct llc_del_link_work; struct work_struct llc_event_work; /* llc event worker */ wait_queue_head_t llc_waiter; /* w4 next llc event */ struct smc_llc_flow llc_flow_lcl; /* llc local control field */ struct smc_llc_flow llc_flow_rmt; /* llc remote control field */ struct smc_llc_qentry *delayed_event; /* arrived when flow active */ spinlock_t llc_flow_lock; /* protects llc flow */ int llc_testlink_time; /* link keep alive time */ }; struct { /* SMC-D */ u64 peer_gid; /* Peer GID (remote) */ struct smcd_dev *smcd; /* ISM device for VLAN reg. */ u8 peer_shutdown : 1; /* peer triggered shutdownn */ }; }; }; struct smc_clc_msg_local; struct smc_init_info { u8 is_smcd; unsigned short vlan_id; int srv_first_contact; int cln_first_contact; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; u8 ib_gid[SMC_GID_SIZE]; u8 ib_port; u32 ib_clcqpn; /* SMC-D */ u64 ism_gid; struct smcd_dev *ism_dev; }; /* Find the connection associated with the given alert token in the link group. * To use rbtrees we have to implement our own search core. * Requires @conns_lock * @token alert token to search for * @lgr link group to search in * Returns connection associated with token if found, NULL otherwise. */ static inline struct smc_connection *smc_lgr_find_conn( u32 token, struct smc_link_group *lgr) { struct smc_connection *res = NULL; struct rb_node *node; node = lgr->conns_all.rb_node; while (node) { struct smc_connection *cur = rb_entry(node, struct smc_connection, alert_node); if (cur->alert_token_local > token) { node = node->rb_left; } else { if (cur->alert_token_local < token) { node = node->rb_right; } else { res = cur; break; } } } return res; } /* returns true if the specified link is usable */ static inline bool smc_link_usable(struct smc_link *lnk) { if (lnk->state == SMC_LNK_UNUSED || lnk->state == SMC_LNK_INACTIVE) return false; return true; } struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; void smc_lgr_cleanup_early(struct smc_connection *conn); void smc_lgr_terminate_sched(struct smc_link_group *lgr); void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport); void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan); void smc_smcd_terminate_all(struct smcd_dev *dev); void smc_smcr_terminate_all(struct smc_ib_device *smcibdev); int smc_buf_create(struct smc_sock *smc, bool is_smcd); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *link, struct smc_clc_msg_accept_confirm *clc); int smc_rtoken_add(struct smc_link *lnk, __be64 nw_vaddr, __be32 nw_rkey); int smc_rtoken_delete(struct smc_link *lnk, __be32 nw_rkey); void smc_rtoken_set(struct smc_link_group *lgr, int link_idx, int link_idx_new, __be32 nw_rkey_known, __be64 nw_vaddr, __be32 nw_rkey); void smc_rtoken_set2(struct smc_link_group *lgr, int rtok_idx, int link_id, __be64 nw_vaddr, __be32 nw_rkey); void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn); void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn); void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn); void smc_rmb_sync_sg_for_device(struct smc_connection *conn); int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini); void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr); int smc_core_init(void); void smc_core_exit(void); int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini); void smcr_link_clear(struct smc_link *lnk); int smcr_buf_map_lgr(struct smc_link *lnk); int smcr_buf_reg_lgr(struct smc_link *lnk); void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type); void smcr_lgr_set_type_asym(struct smc_link_group *lgr, enum smc_lgr_type new_type, int asym_lnk_idx); int smcr_link_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc); struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err); void smcr_link_down_cond(struct smc_link *lnk); void smcr_link_down_cond_sched(struct smc_link *lnk); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { return link->lgr; } #endif