/* 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 <ubraun@linux.vnet.ibm.com>
*/
#define SMC_RMBS_PER_LGR_MAX 255 /* max. # of RMBs per link group */ #define SMC_CONN_PER_LGR_MIN 16 /* min. # of connections per link group */ #define SMC_CONN_PER_LGR_MAX 255 /* max. # of connections per link group, * also is the default value for SMC-R v1 and v2.0
*/ #define SMC_CONN_PER_LGR_PREFER 255 /* Preferred connections per link group used for * SMC-R v2.1 and later negotiation, vendors or * distributions may modify it to a value between * 16-255 as needed.
*/
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 */ #define SMC_WR_BUF_V2_SIZE 8192 /* size of v2 work request buffer */
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 */ struct ib_send_wr *wr_tx_v2_ib; /* WR send v2 meta data */ struct ib_sge *wr_tx_v2_sge; /* WR send v2 gather meta data*/ struct smc_wr_tx_pend *wr_tx_v2_pend; /* WR send v2 waiting for CQE */
dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */
dma_addr_t wr_tx_v2_dma_addr; /* DMA address of v2 tx buf*/
atomic_long_t wr_tx_id; /* seq # of last sent WR */ unsignedlong *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 { struct percpu_ref wr_tx_refs;
} ____cacheline_aligned_in_smp; struct completion tx_ref_comp;
u8 *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 */ int wr_rx_sge_cnt; /* rx sge, V1 is 1, V2 is either 2 or 1 */ int wr_rx_buflen; /* buffer len for the first sge, len for the * second sge is lgr shared if rx sge is 2.
*/
dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */
dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/
u64 wr_rx_id; /* seq # of last recv WR */
u64 wr_rx_id_compl; /* seq # of last completed WR */
u32 wr_rx_cnt; /* number of WR recv buffers */ unsignedlong wr_rx_tstamp; /* jiffies when last buf rx */
wait_queue_head_t wr_rx_empty_wait; /* wait for RQ empty */
struct ib_reg_wr wr_reg; /* WR register memory region */
wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ struct { struct percpu_ref wr_reg_refs;
} ____cacheline_aligned_in_smp; struct completion reg_ref_comp; 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_uid[SMC_LGR_ID_SIZE]; /* unique lnk id */
u8 peer_link_uid[SMC_LGR_ID_SIZE]; /* peer uid */
u8 link_idx; /* index in lgr link array */
u8 link_is_asym; /* is link asymmetric? */
u8 clearing : 1; /* link is being cleared */
refcount_t refcnt; /* link reference count */ struct smc_link_group *lgr; /* parent link group */ struct work_struct link_down_wrk; /* wrk to bring link down */ char ibname[IB_DEVICE_NAME_MAX]; /* ib device name */ int ndev_ifidx; /* network device ifindex */
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 */
atomic_t conn_cnt; /* connections on this link */
};
/* 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_LINKS_ADD_LNK_MIN 1 /* min. # of links per link group */ #define SMC_LINKS_ADD_LNK_MAX 2 /* max. # of links per link group, also is the * default value for smc-r v1.0 and v2.0
*/ #define SMC_LINKS_PER_LGR_MAX_PREFER 2 /* Preferred max links per link group used for * SMC-R v2.1 and later negotiation, vendors or * distributions may modify it to a value between * 1-2 as needed.
*/
/* 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[SMC_LINKS_PER_LGR_MAX]; /* memory region: for rmb and * vzalloced sndbuf * incl. rkey provided to peer * and lkey provided to local
*/
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_dma_need_sync;
u8 is_reg_err; /* buffer registration err */
u8 is_vm; /* virtually contiguous */
}; struct { /* SMC-D */ unsignedshort sba_idx; /* SBA index number */
u64 token; /* DMB token number */
dma_addr_t dma_addr; /* DMA address */
};
};
};
#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 */
};
/* Output fields when saddr is set */ struct smc_ib_device *ib_dev_v2;
u8 ib_port_v2;
u8 ib_gid_v2[SMC_GID_SIZE];
/* Additional output fields when clc_sk and daddr is set as well */
u8 uses_gateway;
u8 nexthop_mac[ETH_ALEN];
struct smc_gidlist gidlist;
};
#define SMC_MAX_V2_ISM_DEVS SMCD_CLC_MAX_V2_GID_ENTRIES /* max # of proposed non-native ISM devices, * which can't exceed the max # of CHID-GID * entries in CLC proposal SMC-Dv2 extension.
*/ struct smc_init_info {
u8 is_smcd;
u8 smc_type_v1;
u8 smc_type_v2;
u8 release_nr;
u8 max_conns;
u8 max_links;
u8 first_contact_peer;
u8 first_contact_local;
u16 feature_mask; unsignedshort vlan_id;
u32 rc;
u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */
u8 smcr_version;
u8 check_smcrv2;
u8 peer_gid[SMC_GID_SIZE];
u8 peer_mac[ETH_ALEN];
u8 peer_systemid[SMC_SYSTEMID_LEN]; struct smc_ib_device *ib_dev;
u8 ib_gid[SMC_GID_SIZE];
u8 ib_port;
u32 ib_clcqpn; struct smc_init_info_smcrv2 smcrv2; /* SMC-D */ struct smcd_gid ism_peer_gid[SMC_MAX_V2_ISM_DEVS + 1]; struct smcd_dev *ism_dev[SMC_MAX_V2_ISM_DEVS + 1];
u16 ism_chid[SMC_MAX_V2_ISM_DEVS + 1];
u8 ism_offered_cnt; /* # of ISM devices offered */
u8 ism_selected; /* index of selected ISM dev*/
u8 smcd_version;
};
/* 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.
*/ staticinlinestruct smc_connection *smc_lgr_find_conn(
u32 token, struct smc_link_group *lgr)
{ struct smc_connection *res = NULL; struct rb_node *node;
/* * Returns true if the specified link is usable. * * usable means the link is ready to receive RDMA messages, map memory * on the link, etc. This doesn't ensure we are able to send RDMA messages * on this link, if sending RDMA messages is needed, use smc_link_sendable()
*/ staticinlinebool smc_link_usable(struct smc_link *lnk)
{ if (lnk->state == SMC_LNK_UNUSED || lnk->state == SMC_LNK_INACTIVE) returnfalse; returntrue;
}
/* * Returns true if the specified link is ready to receive AND send RDMA * messages. * * For the client side in first contact, the underlying QP may still in * RESET or RTR when the link state is ACTIVATING, checks in smc_link_usable() * is not strong enough. For those places that need to send any CDC or LLC * messages, use smc_link_sendable(), otherwise, use smc_link_usable() instead
*/ staticinlinebool smc_link_sendable(struct smc_link *lnk)
{ return smc_link_usable(lnk) &&
lnk->qp_attr.cur_qp_state == IB_QPS_RTS;
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.