diff options
Diffstat (limited to 'net/smc/smc_core.h')
| -rw-r--r-- | net/smc/smc_core.h | 277 |
1 files changed, 252 insertions, 25 deletions
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 86d160f0d187..5c18f08a4c8a 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -13,12 +13,29 @@ #define _SMC_CORE_H #include <linux/atomic.h> +#include <linux/types.h> +#include <linux/smc.h> +#include <linux/pci.h> #include <rdma/ib_verbs.h> +#include <net/genetlink.h> +#include <net/smc.h> #include "smc.h" #include "smc_ib.h" +#include "smc_clc.h" #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. + */ +#define SMCR_MAX_SEND_WR_DEF 16 /* Default number of work requests per send queue */ +#define SMCR_MAX_RECV_WR_DEF 48 /* Default number of work requests per recv queue */ struct smc_lgr_list { /* list of link group definition */ struct list_head list; @@ -39,11 +56,16 @@ enum smc_link_state { /* possible states of a link */ }; #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 { u8 raw[SMC_WR_BUF_SIZE]; }; +struct smc_wr_v2_buf { + u8 raw[SMC_WR_BUF_V2_SIZE]; +}; + #define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */ enum smc_wr_reg_state { @@ -89,23 +111,42 @@ struct smc_link { 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 */ 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 { + struct percpu_ref wr_tx_refs; + } ____cacheline_aligned_in_smp; + struct completion tx_ref_comp; - struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */ + 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 */ unsigned long 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*/ @@ -122,13 +163,20 @@ struct smc_link { 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 */ + u16 max_send_wr; + u16 max_recv_wr; }; /* For now we just allow one parallel link per link group. The SMC protocol @@ -136,9 +184,15 @@ struct smc_link { */ #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*/ +#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 { @@ -151,9 +205,11 @@ struct smc_buf_desc { 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 + 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 */ @@ -163,10 +219,17 @@ struct smc_buf_desc { /* 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 */ + /* SMC-D tx buffer */ + bool is_attached; + /* no need for explicit writes */ + /* SMC-D rx buffer: */ unsigned short sba_idx; /* SBA index number */ u64 token; @@ -199,10 +262,17 @@ enum smc_lgr_type { /* redundancy state of lgr */ SMC_LGR_ASYMMETRIC_LOCAL, /* local has 1, peer 2 active RNICs */ }; +enum smcr_buf_type { /* types of SMC-R sndbufs and RMBs */ + SMCR_PHYS_CONT_BUFS = 0, + SMCR_VIRT_CONT_BUFS = 1, + SMCR_MIXED_BUFS = 2, +}; + enum smc_llc_flowtype { SMC_LLC_FLOW_NONE = 0, SMC_LLC_FLOW_ADD_LINK = 2, SMC_LLC_FLOW_DEL_LINK = 4, + SMC_LLC_FLOW_REQ_ADD_LINK = 5, SMC_LLC_FLOW_RKEY = 6, }; @@ -221,25 +291,37 @@ struct smc_link_group { 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 rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ - struct mutex rmbs_lock; /* protects rx buffers */ + struct rw_semaphore rmbs_lock; /* protects rx buffers */ + u64 alloc_sndbufs; /* stats of tx buffers */ + u64 alloc_rmbs; /* stats of 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 */ + struct workqueue_struct *tx_wq; /* wq for conn. tx workers */ 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 */ + refcount_t refcnt; /* lgr reference count */ bool is_smcd; /* SMC-R or SMC-D */ + u8 smc_version; + u8 negotiated_eid[SMC_MAX_EID_LEN]; + u8 peer_os; /* peer operating system */ + u8 peer_smc_release; + u8 peer_hostname[SMC_MAX_HOSTNAME_LEN]; union { struct { /* SMC-R */ enum smc_lgr_role role; /* client or server */ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ + struct smc_wr_v2_buf *wr_rx_buf_v2; + /* WR v2 recv payload buffer */ + struct smc_wr_v2_buf *wr_tx_buf_v2; + /* WR v2 send payload buffer */ char peer_systemid[SMC_SYSTEMID_LEN]; /* unique system_id of peer */ struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] @@ -249,6 +331,7 @@ struct smc_link_group { /* used rtoken elements */ u8 next_link_id; enum smc_lgr_type type; + enum smcr_buf_type buf_type; /* redundancy state */ u8 pnet_id[SMC_MAX_PNETID_LEN + 1]; /* pnet id of this lgr */ @@ -256,14 +339,16 @@ struct smc_link_group { /* queue for llc events */ spinlock_t llc_event_q_lock; /* protects llc_event_q */ - struct mutex llc_conf_mutex; + struct rw_semaphore 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; + wait_queue_head_t llc_flow_waiter; /* w4 next llc event */ + wait_queue_head_t llc_msg_waiter; + /* w4 next llc msg */ struct smc_llc_flow llc_flow_lcl; /* llc local control field */ struct smc_llc_flow llc_flow_rmt; @@ -276,9 +361,22 @@ struct smc_link_group { /* link keep alive time */ u32 llc_termination_rsn; /* rsn code for termination */ + u8 nexthop_mac[ETH_ALEN]; + u8 uses_gateway; + __be32 saddr; + /* net namespace */ + struct net *net; + u8 max_conns; + /* max conn can be assigned to lgr */ + u8 max_links; + /* max links can be added in lgr */ + u16 max_send_wr; + /* number of WR buffers on send */ + u16 max_recv_wr; + /* number of WR buffers on recv */ }; struct { /* SMC-D */ - u64 peer_gid; + struct smcd_gid peer_gid; /* Peer GID (remote) */ struct smcd_dev *smcd; /* ISM device for VLAN reg. */ @@ -290,20 +388,67 @@ struct smc_link_group { struct smc_clc_msg_local; +#define GID_LIST_SIZE 2 + +struct smc_gidlist { + u8 len; + u8 list[GID_LIST_SIZE][SMC_GID_SIZE]; +}; + +struct smc_init_info_smcrv2 { + /* Input fields */ + __be32 saddr; + struct sock *clc_sk; + __be32 daddr; + + /* 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; unsigned short vlan_id; - int srv_first_contact; - int cln_first_contact; + u32 rc; + u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ - struct smc_clc_msg_local *ib_lcl; + 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 */ - u64 ism_gid; - struct smcd_dev *ism_dev; + 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. @@ -339,7 +484,18 @@ static inline struct smc_connection *smc_lgr_find_conn( return res; } -/* returns true if the specified link is usable */ +static inline bool smc_conn_lgr_valid(struct smc_connection *conn) +{ + return conn->lgr && conn->alert_token_local; +} + +/* + * 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() + */ static inline bool smc_link_usable(struct smc_link *lnk) { if (lnk->state == SMC_LNK_UNUSED || lnk->state == SMC_LNK_INACTIVE) @@ -347,19 +503,85 @@ static inline bool smc_link_usable(struct smc_link *lnk) return true; } +/* + * 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 + */ +static inline bool smc_link_sendable(struct smc_link *lnk) +{ + return smc_link_usable(lnk) && + lnk->qp_attr.cur_qp_state == IB_QPS_RTS; +} + +static inline bool smc_link_active(struct smc_link *lnk) +{ + return lnk->state == SMC_LNK_ACTIVE; +} + +static inline bool smc_link_shared_v2_rxbuf(struct smc_link *lnk) +{ + return lnk->wr_rx_sge_cnt > 1; +} + +static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw) +{ + sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x", + be16_to_cpu(((__be16 *)gid_raw)[0]), + be16_to_cpu(((__be16 *)gid_raw)[1]), + be16_to_cpu(((__be16 *)gid_raw)[2]), + be16_to_cpu(((__be16 *)gid_raw)[3]), + be16_to_cpu(((__be16 *)gid_raw)[4]), + be16_to_cpu(((__be16 *)gid_raw)[5]), + be16_to_cpu(((__be16 *)gid_raw)[6]), + be16_to_cpu(((__be16 *)gid_raw)[7])); +} + +struct smc_pci_dev { + __u32 pci_fid; + __u16 pci_pchid; + __u16 pci_vendor; + __u16 pci_device; + __u8 pci_id[SMC_PCI_ID_STR_LEN]; +}; + +static inline void smc_set_pci_values(struct pci_dev *pci_dev, + struct smc_pci_dev *smc_dev) +{ + smc_dev->pci_vendor = pci_dev->vendor; + smc_dev->pci_device = pci_dev->device; + snprintf(smc_dev->pci_id, sizeof(smc_dev->pci_id), "%s", + pci_name(pci_dev)); +#if IS_ENABLED(CONFIG_S390) + { /* Set s390 specific PCI information */ + struct zpci_dev *zdev; + + zdev = to_zpci(pci_dev); + smc_dev->pci_fid = zdev->fid; + smc_dev->pci_pchid = zdev->pchid; + } +#endif +} + 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_cleanup_early(struct smc_link_group *lgr); void smc_lgr_terminate_sched(struct smc_link_group *lgr); +void smc_lgr_hold(struct smc_link_group *lgr); +void smc_lgr_put(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, +void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *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 smcd_buf_attach(struct smc_sock *smc); 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); @@ -369,31 +591,36 @@ 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, bool log); +void smcr_link_hold(struct smc_link *lnk); +void smcr_link_put(struct smc_link *lnk); +void smc_switch_link_and_count(struct smc_connection *conn, + struct smc_link *to_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); +int smcr_link_reg_buf(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); +int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb); +int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); +int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb); +int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb); static inline struct smc_link_group *smc_get_lgr(struct smc_link *link) { |