--- zzzz-none-000/linux-3.10.107/net/sunrpc/xprtrdma/xprt_rdma.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/sunrpc/xprtrdma/xprt_rdma.h 2021-02-04 17:41:59.000000000 +0000 @@ -43,6 +43,7 @@ #include /* wait_queue_head_t, etc */ #include /* spinlock_t, etc */ #include /* atomic_t, etc */ +#include /* struct work_struct */ #include /* RDMA connection api */ #include /* RDMA verbs api */ @@ -58,14 +59,18 @@ * Interface Adapter -- one per transport instance */ struct rpcrdma_ia { + const struct rpcrdma_memreg_ops *ri_ops; + rwlock_t ri_qplock; + struct ib_device *ri_device; struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; - struct ib_mr *ri_bind_mem; - u32 ri_dma_lkey; - int ri_have_dma_lkey; + struct ib_mr *ri_dma_mr; struct completion ri_done; int ri_async_rc; - enum rpcrdma_memreg ri_memreg_strategy; + unsigned int ri_max_frmr_depth; + struct ib_device_attr ri_devattr; + struct ib_qp_attr ri_qp_attr; + struct ib_qp_init_attr ri_qp_init_attr; }; /* @@ -76,21 +81,73 @@ atomic_t rep_cqcount; int rep_cqinit; int rep_connected; - struct rpcrdma_ia *rep_ia; - struct ib_cq *rep_cq; struct ib_qp_init_attr rep_attr; wait_queue_head_t rep_connect_wait; - struct ib_sge rep_pad; /* holds zeroed pad */ - struct ib_mr *rep_pad_mr; /* holds zeroed pad */ - void (*rep_func)(struct rpcrdma_ep *); - struct rpc_xprt *rep_xprt; /* for rep_func */ struct rdma_conn_param rep_remote_cma; struct sockaddr_storage rep_remote_addr; + struct delayed_work rep_connect_worker; }; +/* + * Force a signaled SEND Work Request every so often, + * in case the provider needs to do some housekeeping. + */ +#define RPCRDMA_MAX_UNSIGNALED_SENDS (32) + #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) +/* Force completion handler to ignore the signal + */ +#define RPCRDMA_IGNORE_COMPLETION (0ULL) + +/* Pre-allocate extra Work Requests for handling backward receives + * and sends. This is a fixed value because the Work Queues are + * allocated when the forward channel is set up. + */ +#if defined(CONFIG_SUNRPC_BACKCHANNEL) +#define RPCRDMA_BACKWARD_WRS (8) +#else +#define RPCRDMA_BACKWARD_WRS (0) +#endif + +/* Registered buffer -- registered kmalloc'd memory for RDMA SEND/RECV + * + * The below structure appears at the front of a large region of kmalloc'd + * memory, which always starts on a good alignment boundary. + */ + +struct rpcrdma_regbuf { + size_t rg_size; + struct rpcrdma_req *rg_owner; + struct ib_sge rg_iov; + __be32 rg_base[0] __attribute__ ((aligned(256))); +}; + +static inline u64 +rdmab_addr(struct rpcrdma_regbuf *rb) +{ + return rb->rg_iov.addr; +} + +static inline u32 +rdmab_length(struct rpcrdma_regbuf *rb) +{ + return rb->rg_iov.length; +} + +static inline u32 +rdmab_lkey(struct rpcrdma_regbuf *rb) +{ + return rb->rg_iov.lkey; +} + +static inline struct rpcrdma_msg * +rdmab_to_msg(struct rpcrdma_regbuf *rb) +{ + return (struct rpcrdma_msg *)rb->rg_base; +} + /* * struct rpcrdma_rep -- this structure encapsulates state required to recv * and complete a reply, asychronously. It needs several pieces of @@ -108,26 +165,63 @@ * struct rpcrdma_buffer. N is the max number of outstanding requests. */ -/* temporary static scatter/gather max */ -#define RPCRDMA_MAX_DATA_SEGS (64) /* max scatter/gather */ +#define RPCRDMA_MAX_DATA_SEGS ((1 * 1024 * 1024) / PAGE_SIZE) #define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 2) /* head+tail = 2 */ -#define MAX_RPCRDMAHDR (\ - /* max supported RPC/RDMA header */ \ - sizeof(struct rpcrdma_msg) + (2 * sizeof(u32)) + \ - (sizeof(struct rpcrdma_read_chunk) * RPCRDMA_MAX_SEGS) + sizeof(u32)) struct rpcrdma_buffer; struct rpcrdma_rep { - unsigned int rr_len; /* actual received reply length */ - struct rpcrdma_buffer *rr_buffer; /* home base for this structure */ - struct rpc_xprt *rr_xprt; /* needed for request/reply matching */ - void (*rr_func)(struct rpcrdma_rep *);/* called by tasklet in softint */ - struct list_head rr_list; /* tasklet list */ - wait_queue_head_t rr_unbind; /* optional unbind wait */ - struct ib_sge rr_iov; /* for posting */ - struct ib_mr *rr_handle; /* handle for mem in rr_iov */ - char rr_base[MAX_RPCRDMAHDR]; /* minimal inline receive buffer */ + unsigned int rr_len; + struct ib_device *rr_device; + struct rpcrdma_xprt *rr_rxprt; + struct work_struct rr_work; + struct list_head rr_list; + struct rpcrdma_regbuf *rr_rdmabuf; +}; + +#define RPCRDMA_BAD_LEN (~0U) + +/* + * struct rpcrdma_mw - external memory region metadata + * + * An external memory region is any buffer or page that is registered + * on the fly (ie, not pre-registered). + * + * Each rpcrdma_buffer has a list of free MWs anchored in rb_mws. During + * call_allocate, rpcrdma_buffer_get() assigns one to each segment in + * an rpcrdma_req. Then rpcrdma_register_external() grabs these to keep + * track of registration metadata while each RPC is pending. + * rpcrdma_deregister_external() uses this metadata to unmap and + * release these resources when an RPC is complete. + */ +enum rpcrdma_frmr_state { + FRMR_IS_INVALID, /* ready to be used */ + FRMR_IS_VALID, /* in use */ + FRMR_IS_STALE, /* failed completion */ +}; + +struct rpcrdma_frmr { + struct scatterlist *sg; + int sg_nents; + struct ib_mr *fr_mr; + enum rpcrdma_frmr_state fr_state; + struct work_struct fr_work; + struct rpcrdma_xprt *fr_xprt; +}; + +struct rpcrdma_fmr { + struct ib_fmr *fmr; + u64 *physaddrs; +}; + +struct rpcrdma_mw { + union { + struct rpcrdma_fmr fmr; + struct rpcrdma_frmr frmr; + } r; + void (*mw_sendcompletion)(struct ib_wc *); + struct list_head mw_list; + struct list_head mw_all; }; /* @@ -155,21 +249,7 @@ */ struct rpcrdma_mr_seg { /* chunk descriptors */ - union { /* chunk memory handles */ - struct ib_mr *rl_mr; /* if registered directly */ - struct rpcrdma_mw { /* if registered from region */ - union { - struct ib_mw *mw; - struct ib_fmr *fmr; - struct { - struct ib_fast_reg_page_list *fr_pgl; - struct ib_mr *fr_mr; - enum { FRMR_IS_INVALID, FRMR_IS_VALID } state; - } frmr; - } r; - struct list_head mw_list; - } *rl_mw; - } mr_chunk; + struct rpcrdma_mw *rl_mw; /* registered MR */ u64 mr_base; /* registration result */ u32 mr_rkey; /* registration result */ u32 mr_len; /* length of chunk or segment */ @@ -181,22 +261,33 @@ char *mr_offset; /* kva if no page, else offset */ }; +#define RPCRDMA_MAX_IOVS (2) + struct rpcrdma_req { - size_t rl_size; /* actual length of buffer */ - unsigned int rl_niovs; /* 0, 2 or 4 */ - unsigned int rl_nchunks; /* non-zero if chunks */ - unsigned int rl_connect_cookie; /* retry detection */ - struct rpcrdma_buffer *rl_buffer; /* home base for this structure */ + struct list_head rl_free; + unsigned int rl_niovs; + unsigned int rl_nchunks; + unsigned int rl_connect_cookie; + struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply;/* holder for reply buffer */ - struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS];/* chunk segments */ - struct ib_sge rl_send_iov[4]; /* for active requests */ - struct ib_sge rl_iov; /* for posting */ - struct ib_mr *rl_handle; /* handle for mem in rl_iov */ - char rl_base[MAX_RPCRDMAHDR]; /* start of actual buffer */ - __u32 rl_xdr_buf[0]; /* start of returned rpc rq_buffer */ + struct ib_sge rl_send_iov[RPCRDMA_MAX_IOVS]; + struct rpcrdma_regbuf *rl_rdmabuf; + struct rpcrdma_regbuf *rl_sendbuf; + struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; + + struct list_head rl_all; + bool rl_backchannel; }; -#define rpcr_to_rdmar(r) \ - container_of((r)->rq_buffer, struct rpcrdma_req, rl_xdr_buf[0]) + +static inline struct rpcrdma_req * +rpcr_to_rdmar(struct rpc_rqst *rqst) +{ + void *buffer = rqst->rq_buffer; + struct rpcrdma_regbuf *rb; + + rb = container_of(buffer, struct rpcrdma_regbuf, rg_base); + return rb->rg_owner; +} /* * struct rpcrdma_buffer -- holds list/queue of pre-registered memory for @@ -205,16 +296,19 @@ * One of these is associated with a transport instance */ struct rpcrdma_buffer { - spinlock_t rb_lock; /* protects indexes */ - atomic_t rb_credits; /* most recent server credits */ - unsigned long rb_cwndscale; /* cached framework rpc_cwndscale */ - int rb_max_requests;/* client max requests */ - struct list_head rb_mws; /* optional memory windows/fmrs/frmrs */ - int rb_send_index; - struct rpcrdma_req **rb_send_bufs; - int rb_recv_index; - struct rpcrdma_rep **rb_recv_bufs; - char *rb_pool; + spinlock_t rb_mwlock; /* protect rb_mws list */ + struct list_head rb_mws; + struct list_head rb_all; + char *rb_pool; + + spinlock_t rb_lock; /* protect buf lists */ + struct list_head rb_send_bufs; + struct list_head rb_recv_bufs; + u32 rb_max_requests; + + u32 rb_bc_srv_max_requests; + spinlock_t rb_reqslock; /* protect rb_allreqs */ + struct list_head rb_allreqs; }; #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia) @@ -259,9 +353,33 @@ unsigned long hardway_register_count; unsigned long failed_marshal_count; unsigned long bad_reply_count; + unsigned long nomsg_call_count; + unsigned long bcall_count; }; /* + * Per-registration mode operations + */ +struct rpcrdma_xprt; +struct rpcrdma_memreg_ops { + int (*ro_map)(struct rpcrdma_xprt *, + struct rpcrdma_mr_seg *, int, bool); + int (*ro_unmap)(struct rpcrdma_xprt *, + struct rpcrdma_mr_seg *); + int (*ro_open)(struct rpcrdma_ia *, + struct rpcrdma_ep *, + struct rpcrdma_create_data_internal *); + size_t (*ro_maxpages)(struct rpcrdma_xprt *); + int (*ro_init)(struct rpcrdma_xprt *); + void (*ro_destroy)(struct rpcrdma_buffer *); + const char *ro_displayname; +}; + +extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops; +extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops; +extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops; + +/* * RPCRDMA transport -- encapsulates the structures above for * integration with RPC. * @@ -272,16 +390,16 @@ * during unmount. */ struct rpcrdma_xprt { - struct rpc_xprt xprt; + struct rpc_xprt rx_xprt; struct rpcrdma_ia rx_ia; struct rpcrdma_ep rx_ep; struct rpcrdma_buffer rx_buf; struct rpcrdma_create_data_internal rx_data; - struct delayed_work rdma_connect; + struct delayed_work rx_connect_worker; struct rpcrdma_stats rx_stats; }; -#define rpcx_to_rdmax(x) container_of(x, struct rpcrdma_xprt, xprt) +#define rpcx_to_rdmax(x) container_of(x, struct rpcrdma_xprt, rx_xprt) #define rpcx_to_rdmad(x) (rpcx_to_rdmax(x)->rx_data) /* Setting this to 0 ensures interoperability with early servers. @@ -300,9 +418,9 @@ */ int rpcrdma_ep_create(struct rpcrdma_ep *, struct rpcrdma_ia *, struct rpcrdma_create_data_internal *); -int rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *); +void rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_connect(struct rpcrdma_ep *, struct rpcrdma_ia *); -int rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); +void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); @@ -312,29 +430,80 @@ /* * Buffer calls - xprtrdma/verbs.c */ -int rpcrdma_buffer_create(struct rpcrdma_buffer *, struct rpcrdma_ep *, - struct rpcrdma_ia *, - struct rpcrdma_create_data_internal *); +struct rpcrdma_req *rpcrdma_create_req(struct rpcrdma_xprt *); +struct rpcrdma_rep *rpcrdma_create_rep(struct rpcrdma_xprt *); +void rpcrdma_destroy_req(struct rpcrdma_ia *, struct rpcrdma_req *); +int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); +struct rpcrdma_mw *rpcrdma_get_mw(struct rpcrdma_xprt *); +void rpcrdma_put_mw(struct rpcrdma_xprt *, struct rpcrdma_mw *); struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_req *); void rpcrdma_recv_buffer_get(struct rpcrdma_req *); void rpcrdma_recv_buffer_put(struct rpcrdma_rep *); -int rpcrdma_register_internal(struct rpcrdma_ia *, void *, int, - struct ib_mr **, struct ib_sge *); -int rpcrdma_deregister_internal(struct rpcrdma_ia *, - struct ib_mr *, struct ib_sge *); - -int rpcrdma_register_external(struct rpcrdma_mr_seg *, - int, int, struct rpcrdma_xprt *); -int rpcrdma_deregister_external(struct rpcrdma_mr_seg *, - struct rpcrdma_xprt *, void *); +struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *, + size_t, gfp_t); +void rpcrdma_free_regbuf(struct rpcrdma_ia *, + struct rpcrdma_regbuf *); + +unsigned int rpcrdma_max_segments(struct rpcrdma_xprt *); +int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int); + +int frwr_alloc_recovery_wq(void); +void frwr_destroy_recovery_wq(void); + +int rpcrdma_alloc_wq(void); +void rpcrdma_destroy_wq(void); + +/* + * Wrappers for chunk registration, shared by read/write chunk code. + */ + +void rpcrdma_mapping_error(struct rpcrdma_mr_seg *); + +static inline enum dma_data_direction +rpcrdma_data_dir(bool writing) +{ + return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; +} + +static inline void +rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg, + enum dma_data_direction direction) +{ + seg->mr_dir = direction; + seg->mr_dmalen = seg->mr_len; + + if (seg->mr_page) + seg->mr_dma = ib_dma_map_page(device, + seg->mr_page, offset_in_page(seg->mr_offset), + seg->mr_dmalen, seg->mr_dir); + else + seg->mr_dma = ib_dma_map_single(device, + seg->mr_offset, + seg->mr_dmalen, seg->mr_dir); + + if (ib_dma_mapping_error(device, seg->mr_dma)) + rpcrdma_mapping_error(seg); +} + +static inline void +rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg) +{ + if (seg->mr_page) + ib_dma_unmap_page(device, + seg->mr_dma, seg->mr_dmalen, seg->mr_dir); + else + ib_dma_unmap_single(device, + seg->mr_dma, seg->mr_dmalen, seg->mr_dir); +} /* * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c */ +void rpcrdma_connect_worker(struct work_struct *); void rpcrdma_conn_func(struct rpcrdma_ep *); void rpcrdma_reply_handler(struct rpcrdma_rep *); @@ -343,6 +512,23 @@ */ int rpcrdma_marshal_req(struct rpc_rqst *); +/* RPC/RDMA module init - xprtrdma/transport.c + */ +int xprt_rdma_init(void); +void xprt_rdma_cleanup(void); + +/* Backchannel calls - xprtrdma/backchannel.c + */ +#if defined(CONFIG_SUNRPC_BACKCHANNEL) +int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int); +int xprt_rdma_bc_up(struct svc_serv *, struct net *); +int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int); +void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *); +int rpcrdma_bc_marshal_reply(struct rpc_rqst *); +void xprt_rdma_bc_free_rqst(struct rpc_rqst *); +void xprt_rdma_bc_destroy(struct rpc_xprt *, unsigned int); +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ + /* Temporary NFS request map cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_map_cachep; /* WR context cache. Created in svc_rdma.c */