* Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2010, 2013, Intel Corporation.
+ * Copyright (c) 2010, 2014, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* @{
*/
-#if defined(__linux__)
-#include <linux/lustre_net.h>
-#elif defined(__APPLE__)
-#include <darwin/lustre_net.h>
-#elif defined(__WINNT__)
-#include <winnt/lustre_net.h>
-#else
-#error Unsupported operating system.
-#endif
-
#include <libcfs/libcfs.h>
-// #include <obd.h>
-#include <lnet/lnet.h>
+#include <lnet/nidstr.h>
+#include <lnet/api.h>
#include <lustre/lustre_idl.h>
#include <lustre_ha.h>
#include <lustre_sec.h>
#include <lprocfs_status.h>
#include <lu_object.h>
#include <lustre_req_layout.h>
-
#include <obd_support.h>
#include <lustre_ver.h>
#define OFD_MAX_BRW_SIZE (1 << LNET_MTU_BITS)
/* When PAGE_SIZE is a constant, we can check our arithmetic here with cpp! */
-#ifdef __KERNEL__
-# if ((PTLRPC_MAX_BRW_PAGES & (PTLRPC_MAX_BRW_PAGES - 1)) != 0)
-# error "PTLRPC_MAX_BRW_PAGES isn't a power of two"
-# endif
-# if (PTLRPC_MAX_BRW_SIZE != (PTLRPC_MAX_BRW_PAGES * PAGE_CACHE_SIZE))
-# error "PTLRPC_MAX_BRW_SIZE isn't PTLRPC_MAX_BRW_PAGES * PAGE_CACHE_SIZE"
-# endif
-# if (PTLRPC_MAX_BRW_SIZE > LNET_MTU * PTLRPC_BULK_OPS_COUNT)
-# error "PTLRPC_MAX_BRW_SIZE too big"
-# endif
-# if (PTLRPC_MAX_BRW_PAGES > LNET_MAX_IOV * PTLRPC_BULK_OPS_COUNT)
-# error "PTLRPC_MAX_BRW_PAGES too big"
-# endif
-#endif /* __KERNEL__ */
+#if ((PTLRPC_MAX_BRW_PAGES & (PTLRPC_MAX_BRW_PAGES - 1)) != 0)
+# error "PTLRPC_MAX_BRW_PAGES isn't a power of two"
+#endif
+#if (PTLRPC_MAX_BRW_SIZE != (PTLRPC_MAX_BRW_PAGES * PAGE_CACHE_SIZE))
+# error "PTLRPC_MAX_BRW_SIZE isn't PTLRPC_MAX_BRW_PAGES * PAGE_CACHE_SIZE"
+#endif
+#if (PTLRPC_MAX_BRW_SIZE > LNET_MTU * PTLRPC_BULK_OPS_COUNT)
+# error "PTLRPC_MAX_BRW_SIZE too big"
+#endif
+#if (PTLRPC_MAX_BRW_PAGES > LNET_MAX_IOV * PTLRPC_BULK_OPS_COUNT)
+# error "PTLRPC_MAX_BRW_PAGES too big"
+#endif
#define PTLRPC_NTHRS_INIT 2
/**
* FIEMAP request can be 4K+ for now
*/
-#define OST_MAXREQSIZE (5 * 1024)
+#define OST_MAXREQSIZE (16 * 1024)
#define OST_IO_MAXREQSIZE max_t(int, OST_MAXREQSIZE, \
(((_OST_MAXREQSIZE_SUM - 1) | (1024 - 1)) + 1))
/* Macro to hide a typecast. */
#define ptlrpc_req_async_args(req) ((void *)&req->rq_async_args)
+struct ptlrpc_replay_async_args {
+ int praa_old_state;
+ int praa_old_status;
+};
+
/**
* Structure to single define portal connection.
*/
struct ptlrpc_connection {
/** linkage for connections hash table */
- cfs_hlist_node_t c_hash;
+ struct hlist_node c_hash;
/** Our own lnet nid for this connection */
lnet_nid_t c_self;
/** Remote side nid for this connection */
* returned.
*/
struct ptlrpc_request_set {
- atomic_t set_refcount;
+ atomic_t set_refcount;
/** number of in queue requests */
- atomic_t set_new_count;
+ atomic_t set_new_count;
/** number of uncompleted requests */
- atomic_t set_remaining;
+ atomic_t set_remaining;
/** wait queue to wait on for request events */
- wait_queue_head_t set_waitq;
- wait_queue_head_t *set_wakeup_ptr;
+ wait_queue_head_t set_waitq;
+ wait_queue_head_t *set_wakeup_ptr;
/** List of requests in the set */
- cfs_list_t set_requests;
+ struct list_head set_requests;
/**
* List of completion callbacks to be called when the set is completed
* This is only used if \a set_interpret is NULL.
* Links struct ptlrpc_set_cbdata.
*/
- cfs_list_t set_cblist;
+ struct list_head set_cblist;
/** Completion callback, if only one. */
- set_interpreter_func set_interpret;
+ set_interpreter_func set_interpret;
/** opaq argument passed to completion \a set_interpret callback. */
- void *set_arg;
+ void *set_arg;
/**
* Lock for \a set_new_requests manipulations
* locked so that any old caller can communicate requests to
*/
spinlock_t set_new_req_lock;
/** List of new yet unsent requests. Only used with ptlrpcd now. */
- cfs_list_t set_new_requests;
+ struct list_head set_new_requests;
/** rq_status of requests that have been freed already */
- int set_rc;
+ int set_rc;
/** Additional fields used by the flow control extension */
/** Maximum number of RPCs in flight */
- int set_max_inflight;
+ int set_max_inflight;
/** Callback function used to generate RPCs */
- set_producer_func set_producer;
+ set_producer_func set_producer;
/** opaq argument passed to the producer callback */
- void *set_producer_arg;
+ void *set_producer_arg;
};
/**
* Description of a single ptrlrpc_set callback
*/
struct ptlrpc_set_cbdata {
- /** List linkage item */
- cfs_list_t psc_item;
- /** Pointer to interpreting function */
- set_interpreter_func psc_interpret;
- /** Opaq argument to pass to the callback */
- void *psc_data;
+ /** List linkage item */
+ struct list_head psc_item;
+ /** Pointer to interpreting function */
+ set_interpreter_func psc_interpret;
+ /** Opaq argument to pass to the callback */
+ void *psc_data;
};
struct ptlrpc_bulk_desc;
* added to the state for replay/failover consistency guarantees.
*/
struct ptlrpc_reply_state {
- /** Callback description */
- struct ptlrpc_cb_id rs_cb_id;
- /** Linkage for list of all reply states in a system */
- cfs_list_t rs_list;
- /** Linkage for list of all reply states on same export */
- cfs_list_t rs_exp_list;
- /** Linkage for list of all reply states for same obd */
- cfs_list_t rs_obd_list;
+ /** Callback description */
+ struct ptlrpc_cb_id rs_cb_id;
+ /** Linkage for list of all reply states in a system */
+ struct list_head rs_list;
+ /** Linkage for list of all reply states on same export */
+ struct list_head rs_exp_list;
+ /** Linkage for list of all reply states for same obd */
+ struct list_head rs_obd_list;
#if RS_DEBUG
- cfs_list_t rs_debug_list;
+ struct list_head rs_debug_list;
#endif
- /** A spinlock to protect the reply state flags */
+ /** A spinlock to protect the reply state flags */
spinlock_t rs_lock;
- /** Reply state flags */
+ /** Reply state flags */
unsigned long rs_difficult:1; /* ACK/commit stuff */
unsigned long rs_no_ack:1; /* no ACK, even for
difficult requests */
typedef int (*ptlrpc_interpterer_t)(const struct lu_env *env,
struct ptlrpc_request *req,
void *arg, int rc);
+/** Type of request resend call-back */
+typedef void (*ptlrpc_resend_cb_t)(struct ptlrpc_request *req,
+ void *arg);
/**
* Definition of request pool structure.
*/
struct ptlrpc_request_pool {
/** Locks the list */
- spinlock_t prp_lock;
- /** list of ptlrpc_request structs */
- cfs_list_t prp_req_list;
- /** Maximum message size that would fit into a rquest from this pool */
- int prp_rq_size;
- /** Function to allocate more requests for this pool */
- void (*prp_populate)(struct ptlrpc_request_pool *, int);
+ spinlock_t prp_lock;
+ /** list of ptlrpc_request structs */
+ struct list_head prp_req_list;
+ /** Maximum message size that would fit into a rquest from this pool */
+ int prp_rq_size;
+ /** Function to allocate more requests for this pool */
+ void (*prp_populate)(struct ptlrpc_request_pool *, int);
};
struct lu_context;
/**
* List of registered policies
*/
- cfs_list_t nrs_policy_list;
+ struct list_head nrs_policy_list;
/**
* List of policies with queued requests. Policies that have any
* outstanding requests are queued here, and this list is queried
* point transition away from the
* ptlrpc_nrs_pol_state::NRS_POL_STATE_STARTED state are drained.
*/
- cfs_list_t nrs_policy_queued;
+ struct list_head nrs_policy_queued;
/**
* Service partition for this NRS head
*/
/**
* Link into nrs_core::nrs_policies
*/
- cfs_list_t pd_list;
+ struct list_head pd_list;
/**
* NRS operations for this policy
*/
* Linkage into the NRS head's list of policies,
* ptlrpc_nrs:nrs_policy_list
*/
- cfs_list_t pol_list;
+ struct list_head pol_list;
/**
* Linkage into the NRS head's list of policies with enqueued
* requests ptlrpc_nrs:nrs_policy_queued
*/
- cfs_list_t pol_list_queued;
+ struct list_head pol_list_queued;
/**
* Current state of this policy
*/
/**
* List of queued requests.
*/
- cfs_list_t fh_list;
+ struct list_head fh_list;
/**
* For debugging purposes.
*/
};
struct nrs_fifo_req {
- cfs_list_t fr_list;
+ struct list_head fr_list;
__u64 fr_sequence;
};
*/
struct nrs_crrn_client {
struct ptlrpc_nrs_resource cc_res;
- cfs_hlist_node_t cc_hnode;
+ struct hlist_node cc_hnode;
lnet_nid_t cc_nid;
/**
* The round number against which this client is currently scheduling
*/
struct nrs_orr_object {
struct ptlrpc_nrs_resource oo_res;
- cfs_hlist_node_t oo_hnode;
+ struct hlist_node oo_hnode;
/**
* The round number against which requests are being scheduled for this
* object or OST
void (*hpreq_fini)(struct ptlrpc_request *);
};
+struct ptlrpc_cli_req {
+ /** For bulk requests on client only: bulk descriptor */
+ struct ptlrpc_bulk_desc *cr_bulk;
+ /** optional time limit for send attempts */
+ cfs_duration_t cr_delay_limit;
+ /** time request was first queued */
+ cfs_time_t cr_queued_time;
+ /** request sent timeval */
+ struct timeval cr_sent_tv;
+ /** time for request really sent out */
+ time_t cr_sent_out;
+ /** when req reply unlink must finish. */
+ time_t cr_reply_deadline;
+ /** when req bulk unlink must finish. */
+ time_t cr_bulk_deadline;
+ /** Portal to which this request would be sent */
+ short cr_req_ptl;
+ /** Portal where to wait for reply and where reply would be sent */
+ short cr_rep_ptl;
+ /** request resending number */
+ unsigned int cr_resend_nr;
+ /** What was import generation when this request was sent */
+ int cr_imp_gen;
+ enum lustre_imp_state cr_send_state;
+ /** Per-request waitq introduced by bug 21938 for recovery waiting */
+ wait_queue_head_t cr_set_waitq;
+ /** Link item for request set lists */
+ struct list_head cr_set_chain;
+ /** link to waited ctx */
+ struct list_head cr_ctx_chain;
+
+ /** client's half ctx */
+ struct ptlrpc_cli_ctx *cr_cli_ctx;
+ /** Link back to the request set */
+ struct ptlrpc_request_set *cr_set;
+ /** outgoing request MD handle */
+ lnet_handle_md_t cr_req_md_h;
+ /** request-out callback parameter */
+ struct ptlrpc_cb_id cr_req_cbid;
+ /** incoming reply MD handle */
+ lnet_handle_md_t cr_reply_md_h;
+ wait_queue_head_t cr_reply_waitq;
+ /** reply callback parameter */
+ struct ptlrpc_cb_id cr_reply_cbid;
+ /** Async completion handler, called when reply is received */
+ ptlrpc_interpterer_t cr_reply_interp;
+ /** Resend handler, called when request is resend to update RPC data */
+ ptlrpc_resend_cb_t cr_resend_cb;
+ /** Async completion context */
+ union ptlrpc_async_args cr_async_args;
+ /** Opaq data for replay and commit callbacks. */
+ void *cr_cb_data;
+ /**
+ * Commit callback, called when request is committed and about to be
+ * freed.
+ */
+ void (*cr_commit_cb)(struct ptlrpc_request *);
+ /** Replay callback, called after request is replayed at recovery */
+ void (*cr_replay_cb)(struct ptlrpc_request *);
+};
+
+/** client request member alias */
+/* NB: these alias should NOT be used by any new code, instead they should
+ * be removed step by step to avoid potential abuse */
+#define rq_bulk rq_cli.cr_bulk
+#define rq_delay_limit rq_cli.cr_delay_limit
+#define rq_queued_time rq_cli.cr_queued_time
+#define rq_sent_tv rq_cli.cr_sent_tv
+#define rq_real_sent rq_cli.cr_sent_out
+#define rq_reply_deadline rq_cli.cr_reply_deadline
+#define rq_bulk_deadline rq_cli.cr_bulk_deadline
+#define rq_nr_resend rq_cli.cr_resend_nr
+#define rq_request_portal rq_cli.cr_req_ptl
+#define rq_reply_portal rq_cli.cr_rep_ptl
+#define rq_import_generation rq_cli.cr_imp_gen
+#define rq_send_state rq_cli.cr_send_state
+#define rq_set_chain rq_cli.cr_set_chain
+#define rq_ctx_chain rq_cli.cr_ctx_chain
+#define rq_set rq_cli.cr_set
+#define rq_set_waitq rq_cli.cr_set_waitq
+#define rq_cli_ctx rq_cli.cr_cli_ctx
+#define rq_req_md_h rq_cli.cr_req_md_h
+#define rq_req_cbid rq_cli.cr_req_cbid
+#define rq_reply_md_h rq_cli.cr_reply_md_h
+#define rq_reply_waitq rq_cli.cr_reply_waitq
+#define rq_reply_cbid rq_cli.cr_reply_cbid
+#define rq_interpret_reply rq_cli.cr_reply_interp
+#define rq_resend_cb rq_cli.cr_resend_cb
+#define rq_async_args rq_cli.cr_async_args
+#define rq_cb_data rq_cli.cr_cb_data
+#define rq_commit_cb rq_cli.cr_commit_cb
+#define rq_replay_cb rq_cli.cr_replay_cb
+
+struct ptlrpc_srv_req {
+ /** initial thread servicing this request */
+ struct ptlrpc_thread *sr_svc_thread;
+ /**
+ * Server side list of incoming unserved requests sorted by arrival
+ * time. Traversed from time to time to notice about to expire
+ * requests and sent back "early replies" to clients to let them
+ * know server is alive and well, just very busy to service their
+ * requests in time
+ */
+ struct list_head sr_timed_list;
+ /** server-side per-export list */
+ struct list_head sr_exp_list;
+ /** server-side history, used for debuging purposes. */
+ struct list_head sr_hist_list;
+ /** history sequence # */
+ __u64 sr_hist_seq;
+ /** the index of service's srv_at_array into which request is linked */
+ time_t sr_at_index;
+ /** authed uid */
+ uid_t sr_auth_uid;
+ /** authed uid mapped to */
+ uid_t sr_auth_mapped_uid;
+ /** RPC is generated from what part of Lustre */
+ enum lustre_sec_part sr_sp_from;
+ /** request session context */
+ struct lu_context sr_ses;
+ /** \addtogroup nrs
+ * @{
+ */
+ /** stub for NRS request */
+ struct ptlrpc_nrs_request sr_nrq;
+ /** @} nrs */
+ /** request arrival time */
+ struct timeval sr_arrival_time;
+ /** server's half ctx */
+ struct ptlrpc_svc_ctx *sr_svc_ctx;
+ /** (server side), pointed directly into req buffer */
+ struct ptlrpc_user_desc *sr_user_desc;
+ /** separated reply state */
+ struct ptlrpc_reply_state *sr_reply_state;
+ /** server-side hp handlers */
+ struct ptlrpc_hpreq_ops *sr_ops;
+ /** incoming request buffer */
+ struct ptlrpc_request_buffer_desc *sr_rqbd;
+};
+
+/** server request member alias */
+/* NB: these alias should NOT be used by any new code, instead they should
+ * be removed step by step to avoid potential abuse */
+#define rq_svc_thread rq_srv.sr_svc_thread
+#define rq_timed_list rq_srv.sr_timed_list
+#define rq_exp_list rq_srv.sr_exp_list
+#define rq_history_list rq_srv.sr_hist_list
+#define rq_history_seq rq_srv.sr_hist_seq
+#define rq_at_index rq_srv.sr_at_index
+#define rq_auth_uid rq_srv.sr_auth_uid
+#define rq_auth_mapped_uid rq_srv.sr_auth_mapped_uid
+#define rq_sp_from rq_srv.sr_sp_from
+#define rq_session rq_srv.sr_ses
+#define rq_nrq rq_srv.sr_nrq
+#define rq_arrival_time rq_srv.sr_arrival_time
+#define rq_reply_state rq_srv.sr_reply_state
+#define rq_svc_ctx rq_srv.sr_svc_ctx
+#define rq_user_desc rq_srv.sr_user_desc
+#define rq_ops rq_srv.sr_ops
+#define rq_rqbd rq_srv.sr_rqbd
+
/**
* Represents remote procedure call.
*
*/
struct ptlrpc_request {
/* Request type: one of PTL_RPC_MSG_* */
- int rq_type;
+ int rq_type;
/** Result of request processing */
- int rq_status;
- /**
- * Linkage item through which this request is included into
- * sending/delayed lists on client and into rqbd list on server
- */
- cfs_list_t rq_list;
- /**
- * Server side list of incoming unserved requests sorted by arrival
- * time. Traversed from time to time to notice about to expire
- * requests and sent back "early replies" to clients to let them
- * know server is alive and well, just very busy to service their
- * requests in time
- */
- cfs_list_t rq_timed_list;
- /** server-side history, used for debuging purposes. */
- cfs_list_t rq_history_list;
- /** server-side per-export list */
- cfs_list_t rq_exp_list;
- /** server-side hp handlers */
- struct ptlrpc_hpreq_ops *rq_ops;
-
- /** initial thread servicing this request */
- struct ptlrpc_thread *rq_svc_thread;
-
- /** history sequence # */
- __u64 rq_history_seq;
- /** \addtogroup nrs
- * @{
+ int rq_status;
+ /**
+ * Linkage item through which this request is included into
+ * sending/delayed lists on client and into rqbd list on server
*/
- /** stub for NRS request */
- struct ptlrpc_nrs_request rq_nrq;
- /** @} nrs */
- /** the index of service's srv_at_array into which request is linked */
- time_t rq_at_index;
- /** Lock to protect request flags and some other important bits, like
- * rq_list
- */
- spinlock_t rq_lock;
- /** client-side flags are serialized by rq_lock */
+ struct list_head rq_list;
+ /** Lock to protect request flags and some other important bits, like
+ * rq_list
+ */
+ spinlock_t rq_lock;
+ /** client-side flags are serialized by rq_lock @{ */
unsigned int rq_intr:1, rq_replied:1, rq_err:1,
rq_timedout:1, rq_resend:1, rq_restart:1,
/**
rq_no_resend:1, rq_waiting:1, rq_receiving_reply:1,
rq_no_delay:1, rq_net_err:1, rq_wait_ctx:1,
rq_early:1,
- rq_req_unlink:1, rq_reply_unlink:1,
- rq_memalloc:1, /* req originated from "kswapd" */
- /* server-side flags */
- rq_packed_final:1, /* packed final reply */
- rq_hp:1, /* high priority RPC */
- rq_at_linked:1, /* link into service's srv_at_array */
- rq_reply_truncate:1,
- rq_committed:1,
- /* whether the "rq_set" is a valid one */
- rq_invalid_rqset:1,
+ rq_req_unlinked:1, /* unlinked request buffer from lnet */
+ rq_reply_unlinked:1, /* unlinked reply buffer from lnet */
+ rq_memalloc:1, /* req originated from "kswapd" */
+ rq_committed:1,
+ rq_reply_truncated:1,
+ /** whether the "rq_set" is a valid one */
+ rq_invalid_rqset:1,
rq_generation_set:1,
- /* do not resend request on -EINPROGRESS */
+ /** do not resend request on -EINPROGRESS */
rq_no_retry_einprogress:1,
/* allow the req to be sent if the import is in recovery
* status */
rq_allow_replay:1,
/* bulk request, sent to server, but uncommitted */
rq_unstable:1;
+ /** @} */
- unsigned int rq_nr_resend;
-
- enum rq_phase rq_phase; /* one of RQ_PHASE_* */
- enum rq_phase rq_next_phase; /* one of RQ_PHASE_* to be used next */
- atomic_t rq_refcount;/* client-side refcount for SENT race,
- server-side refcounf for multiple replies */
-
- /** Portal to which this request would be sent */
- short rq_request_portal; /* XXX FIXME bug 249 */
- /** Portal where to wait for reply and where reply would be sent */
- short rq_reply_portal; /* XXX FIXME bug 249 */
+ /** server-side flags @{ */
+ unsigned int
+ rq_hp:1, /**< high priority RPC */
+ rq_at_linked:1, /**< link into service's srv_at_array */
+ rq_packed_final:1; /**< packed final reply */
+ /** @} */
+ /** one of RQ_PHASE_* */
+ enum rq_phase rq_phase;
+ /** one of RQ_PHASE_* to be used next */
+ enum rq_phase rq_next_phase;
+ /**
+ * client-side refcount for SENT race, server-side refcounf
+ * for multiple replies
+ */
+ atomic_t rq_refcount;
/**
* client-side:
* !rq_truncate : # reply bytes actually received,
int rq_reqlen;
/** Reply length */
int rq_replen;
+ /** Pool if request is from preallocated list */
+ struct ptlrpc_request_pool *rq_pool;
/** Request message - what client sent */
struct lustre_msg *rq_reqmsg;
/** Reply message - server response */
__u64 rq_transno;
/** xid */
__u64 rq_xid;
- /**
- * List item to for replay list. Not yet commited requests get linked
- * there.
- * Also see \a rq_replay comment above.
- */
- cfs_list_t rq_replay_list;
-
- /**
- * security and encryption data
- * @{ */
- struct ptlrpc_cli_ctx *rq_cli_ctx; /**< client's half ctx */
- struct ptlrpc_svc_ctx *rq_svc_ctx; /**< server's half ctx */
- cfs_list_t rq_ctx_chain; /**< link to waited ctx */
-
- struct sptlrpc_flavor rq_flvr; /**< for client & server */
- enum lustre_sec_part rq_sp_from;
+ /**
+ * List item to for replay list. Not yet commited requests get linked
+ * there.
+ * Also see \a rq_replay comment above.
+ * It's also link chain on obd_export::exp_req_replay_queue
+ */
+ struct list_head rq_replay_list;
+ /** non-shared members for client & server request*/
+ union {
+ struct ptlrpc_cli_req rq_cli;
+ struct ptlrpc_srv_req rq_srv;
+ };
+ /**
+ * security and encryption data
+ * @{ */
+ /** description of flavors for client & server */
+ struct sptlrpc_flavor rq_flvr;
/* client/server security flags */
unsigned int
rq_pack_bulk:1,
/* doesn't expect reply FIXME */
rq_no_reply:1,
- rq_pill_init:1; /* pill initialized */
-
- uid_t rq_auth_uid; /* authed uid */
- uid_t rq_auth_mapped_uid; /* authed uid mapped to */
+ rq_pill_init:1, /* pill initialized */
+ rq_srv_req:1; /* server request */
- /* (server side), pointed directly into req buffer */
- struct ptlrpc_user_desc *rq_user_desc;
- /* various buffer pointers */
- struct lustre_msg *rq_reqbuf; /* req wrapper */
- char *rq_repbuf; /* rep buffer */
- struct lustre_msg *rq_repdata; /* rep wrapper msg */
- struct lustre_msg *rq_clrbuf; /* only in priv mode */
+ /** various buffer pointers */
+ struct lustre_msg *rq_reqbuf; /**< req wrapper */
+ char *rq_repbuf; /**< rep buffer */
+ struct lustre_msg *rq_repdata; /**< rep wrapper msg */
+ /** only in priv mode */
+ struct lustre_msg *rq_clrbuf;
int rq_reqbuf_len; /* req wrapper buf len */
int rq_reqdata_len; /* req wrapper msg len */
int rq_repbuf_len; /* rep buffer len */
int rq_clrdata_len; /* only in priv mode */
/** early replies go to offset 0, regular replies go after that */
- unsigned int rq_reply_off;
-
- /** @} */
-
- /** Fields that help to see if request and reply were swabbed or not */
- __u32 rq_req_swab_mask;
- __u32 rq_rep_swab_mask;
-
- /** What was import generation when this request was sent */
- int rq_import_generation;
- enum lustre_imp_state rq_send_state;
-
- /** how many early replies (for stats) */
- int rq_early_count;
-
- /** client+server request */
- lnet_handle_md_t rq_req_md_h;
- struct ptlrpc_cb_id rq_req_cbid;
- /** optional time limit for send attempts */
- cfs_duration_t rq_delay_limit;
- /** time request was first queued */
- cfs_time_t rq_queued_time;
-
- /* server-side... */
- /** request arrival time */
- struct timeval rq_arrival_time;
- /** separated reply state */
- struct ptlrpc_reply_state *rq_reply_state;
- /** incoming request buffer */
- struct ptlrpc_request_buffer_desc *rq_rqbd;
-
- /** client-only incoming reply */
- lnet_handle_md_t rq_reply_md_h;
- wait_queue_head_t rq_reply_waitq;
- struct ptlrpc_cb_id rq_reply_cbid;
-
- /** our LNet NID */
- lnet_nid_t rq_self;
- /** Peer description (the other side) */
- lnet_process_id_t rq_peer;
- /** Server-side, export on which request was received */
- struct obd_export *rq_export;
- /** Client side, import where request is being sent */
- struct obd_import *rq_import;
-
- /** Replay callback, called after request is replayed at recovery */
- void (*rq_replay_cb)(struct ptlrpc_request *);
- /**
- * Commit callback, called when request is committed and about to be
- * freed.
- */
- void (*rq_commit_cb)(struct ptlrpc_request *);
- /** Opaq data for replay and commit callbacks. */
- void *rq_cb_data;
-
- /** For bulk requests on client only: bulk descriptor */
- struct ptlrpc_bulk_desc *rq_bulk;
+ unsigned int rq_reply_off;
- /** client outgoing req */
- /**
- * when request/reply sent (secs), or time when request should be sent
- */
- time_t rq_sent;
- /** time for request really sent out */
- time_t rq_real_sent;
-
- /** when request must finish. volatile
- * so that servers' early reply updates to the deadline aren't
- * kept in per-cpu cache */
- volatile time_t rq_deadline;
- /** when req reply unlink must finish. */
- time_t rq_reply_deadline;
- /** when req bulk unlink must finish. */
- time_t rq_bulk_deadline;
- /**
- * service time estimate (secs)
- * If the requestsis not served by this time, it is marked as timed out.
- */
- int rq_timeout;
-
- /** Multi-rpc bits */
- /** Per-request waitq introduced by bug 21938 for recovery waiting */
- wait_queue_head_t rq_set_waitq;
- /** Link item for request set lists */
- cfs_list_t rq_set_chain;
- /** Link back to the request set */
- struct ptlrpc_request_set *rq_set;
- /** Async completion handler, called when reply is received */
- ptlrpc_interpterer_t rq_interpret_reply;
- /** Async completion context */
- union ptlrpc_async_args rq_async_args;
-
- /** Pool if request is from preallocated list */
- struct ptlrpc_request_pool *rq_pool;
-
- struct lu_context rq_session;
+ /** @} */
- /** request format description */
- struct req_capsule rq_pill;
+ /** Fields that help to see if request and reply were swabbed or not */
+ __u32 rq_req_swab_mask;
+ __u32 rq_rep_swab_mask;
+
+ /** how many early replies (for stats) */
+ int rq_early_count;
+ /** Server-side, export on which request was received */
+ struct obd_export *rq_export;
+ /** import where request is being sent */
+ struct obd_import *rq_import;
+ /** our LNet NID */
+ lnet_nid_t rq_self;
+ /** Peer description (the other side) */
+ lnet_process_id_t rq_peer;
+ /**
+ * service time estimate (secs)
+ * If the request is not served by this time, it is marked as timed out.
+ */
+ int rq_timeout;
+ /**
+ * when request/reply sent (secs), or time when request should be sent
+ */
+ time_t rq_sent;
+ /** when request must finish. */
+ time_t rq_deadline;
+ /** request format description */
+ struct req_capsule rq_pill;
};
/**
/**
* Returns 1 if request buffer at offset \a index was already swabbed
*/
-static inline int lustre_req_swabbed(struct ptlrpc_request *req, int index)
+static inline int lustre_req_swabbed(struct ptlrpc_request *req, size_t index)
{
LASSERT(index < sizeof(req->rq_req_swab_mask) * 8);
return req->rq_req_swab_mask & (1 << index);
/**
* Returns 1 if request reply buffer at offset \a index was already swabbed
*/
-static inline int lustre_rep_swabbed(struct ptlrpc_request *req, int index)
+static inline int lustre_rep_swabbed(struct ptlrpc_request *req, size_t index)
{
LASSERT(index < sizeof(req->rq_rep_swab_mask) * 8);
return req->rq_rep_swab_mask & (1 << index);
/**
* Mark request buffer at offset \a index that it was already swabbed
*/
-static inline void lustre_set_req_swabbed(struct ptlrpc_request *req, int index)
+static inline void lustre_set_req_swabbed(struct ptlrpc_request *req,
+ size_t index)
{
LASSERT(index < sizeof(req->rq_req_swab_mask) * 8);
LASSERT((req->rq_req_swab_mask & (1 << index)) == 0);
/**
* Mark request reply buffer at offset \a index that it was already swabbed
*/
-static inline void lustre_set_rep_swabbed(struct ptlrpc_request *req, int index)
+static inline void lustre_set_rep_swabbed(struct ptlrpc_request *req,
+ size_t index)
{
LASSERT(index < sizeof(req->rq_rep_swab_mask) * 8);
LASSERT((req->rq_rep_swab_mask & (1 << index)) == 0);
/**
* Debugging functions and helpers to print request structure into debug log
* @{
- */
+ */
/* Spare the preprocessor, spoil the bugs. */
#define FLAG(field, str) (field ? str : "")
* Structure that defines a single page of a bulk transfer
*/
struct ptlrpc_bulk_page {
- /** Linkage to list of pages in a bulk */
- cfs_list_t bp_link;
- /**
- * Number of bytes in a page to transfer starting from \a bp_pageoffset
- */
- int bp_buflen;
- /** offset within a page */
- int bp_pageoffset;
- /** The page itself */
- struct page *bp_page;
+ /** Linkage to list of pages in a bulk */
+ struct list_head bp_link;
+ /**
+ * Number of bytes in a page to transfer starting from \a bp_pageoffset
+ */
+ int bp_buflen;
+ /** offset within a page */
+ int bp_pageoffset;
+ /** The page itself */
+ struct page *bp_page;
};
#define BULK_GET_SOURCE 0
/** array of associated MDs */
lnet_handle_md_t bd_mds[PTLRPC_BULK_OPS_COUNT];
-#if defined(__KERNEL__)
/*
* encrypt iov, size is either 0 or bd_iov_count.
*/
lnet_kiov_t *bd_enc_iov;
lnet_kiov_t bd_iov[0];
-#else
- lnet_md_iovec_t bd_iov[0];
-#endif
};
enum {
/**
* List of active threads in svc->srv_threads
*/
- cfs_list_t t_link;
+ struct list_head t_link;
/**
* thread-private data (preallocated memory)
*/
/**
* service thread pid
*/
- pid_t t_pid;
+ pid_t t_pid;
/**
* put watchdog in the structure per thread b=14840
*/
* More than one request can fit into the buffer.
*/
struct ptlrpc_request_buffer_desc {
- /** Link item for rqbds on a service */
- cfs_list_t rqbd_list;
- /** History of requests for this buffer */
- cfs_list_t rqbd_reqs;
- /** Back pointer to service for which this buffer is registered */
- struct ptlrpc_service_part *rqbd_svcpt;
- /** LNet descriptor */
- lnet_handle_md_t rqbd_md_h;
- int rqbd_refcount;
- /** The buffer itself */
- char *rqbd_buffer;
- struct ptlrpc_cb_id rqbd_cbid;
- /**
- * This "embedded" request structure is only used for the
- * last request to fit into the buffer
- */
- struct ptlrpc_request rqbd_req;
+ /** Link item for rqbds on a service */
+ struct list_head rqbd_list;
+ /** History of requests for this buffer */
+ struct list_head rqbd_reqs;
+ /** Back pointer to service for which this buffer is registered */
+ struct ptlrpc_service_part *rqbd_svcpt;
+ /** LNet descriptor */
+ lnet_handle_md_t rqbd_md_h;
+ int rqbd_refcount;
+ /** The buffer itself */
+ char *rqbd_buffer;
+ struct ptlrpc_cb_id rqbd_cbid;
+ /**
+ * This "embedded" request structure is only used for the
+ * last request to fit into the buffer
+ */
+ struct ptlrpc_request rqbd_req;
};
typedef int (*svc_handler_t)(struct ptlrpc_request *req);
struct ptlrpc_service {
/** serialize /proc operations */
spinlock_t srv_lock;
- /** most often accessed fields */
- /** chain thru all services */
- cfs_list_t srv_list;
+ /** most often accessed fields */
+ /** chain thru all services */
+ struct list_head srv_list;
/** service operations table */
struct ptlrpc_service_ops srv_ops;
/** only statically allocated strings here; we don't clean them */
/** only statically allocated strings here; we don't clean them */
char *srv_thread_name;
/** service thread list */
- cfs_list_t srv_threads;
+ struct list_head srv_threads;
/** threads # should be created for each partition on initializing */
int srv_nthrs_cpt_init;
/** limit of threads number for each partition */
int srv_nthrs_cpt_limit;
/** Root of /proc dir tree for this service */
- cfs_proc_dir_entry_t *srv_procroot;
+ struct proc_dir_entry *srv_procroot;
/** Pointer to statistic data for this service */
struct lprocfs_stats *srv_stats;
/** # hp per lp reqs to handle */
/** # running threads */
int scp_nthrs_running;
/** service threads list */
- cfs_list_t scp_threads;
+ struct list_head scp_threads;
/**
* serialize the following fields, used for protecting
/** # incoming reqs */
int scp_nreqs_incoming;
/** request buffers to be reposted */
- cfs_list_t scp_rqbd_idle;
+ struct list_head scp_rqbd_idle;
/** req buffers receiving */
- cfs_list_t scp_rqbd_posted;
+ struct list_head scp_rqbd_posted;
/** incoming reqs */
- cfs_list_t scp_req_incoming;
+ struct list_head scp_req_incoming;
/** timeout before re-posting reqs, in tick */
cfs_duration_t scp_rqbd_timeout;
/**
wait_queue_head_t scp_waitq;
/** request history */
- cfs_list_t scp_hist_reqs;
+ struct list_head scp_hist_reqs;
/** request buffer history */
- cfs_list_t scp_hist_rqbds;
+ struct list_head scp_hist_rqbds;
/** # request buffers in history */
int scp_hist_nrqbds;
/** sequence number for request */
*/
spinlock_t scp_rep_lock __cfs_cacheline_aligned;
/** all the active replies */
- cfs_list_t scp_rep_active;
-#ifndef __KERNEL__
- /** replies waiting for service */
- cfs_list_t scp_rep_queue;
-#endif
+ struct list_head scp_rep_active;
/** List of free reply_states */
- cfs_list_t scp_rep_idle;
+ struct list_head scp_rep_idle;
/** waitq to run, when adding stuff to srv_free_rs_list */
wait_queue_head_t scp_rep_waitq;
/** # 'difficult' replies */
* Record the partner index to be processed next.
*/
int pc_cursor;
-#ifndef __KERNEL__
- /**
- * Async rpcs flag to make sure that ptlrpcd_check() is called only
- * once.
- */
- int pc_recurred;
- /**
- * Currently not used.
- */
- void *pc_callback;
- /**
- * User-space async rpcs callback.
- */
- void *pc_wait_callback;
- /**
- * User-space check idle rpcs callback.
- */
- void *pc_idle_callback;
-#endif
};
/* Bits for pc_flags */
int ptlrpc_reply(struct ptlrpc_request *req);
int ptlrpc_send_error(struct ptlrpc_request *req, int difficult);
int ptlrpc_error(struct ptlrpc_request *req);
-void ptlrpc_resend_req(struct ptlrpc_request *request);
int ptlrpc_at_get_net_latency(struct ptlrpc_request *req);
int ptl_send_rpc(struct ptlrpc_request *request, int noreply);
int ptlrpc_register_rqbd(struct ptlrpc_request_buffer_desc *rqbd);
int ptlrpc_queue_wait(struct ptlrpc_request *req);
int ptlrpc_replay_req(struct ptlrpc_request *req);
-int ptlrpc_unregister_reply(struct ptlrpc_request *req, int async);
void ptlrpc_restart_req(struct ptlrpc_request *req);
void ptlrpc_abort_inflight(struct obd_import *imp);
void ptlrpc_cleanup_imp(struct obd_import *imp);
void *arg);
int ptlrpc_set_add_cb(struct ptlrpc_request_set *set,
set_interpreter_func fn, void *data);
-int ptlrpc_set_next_timeout(struct ptlrpc_request_set *);
int ptlrpc_check_set(const struct lu_env *env, struct ptlrpc_request_set *set);
int ptlrpc_set_wait(struct ptlrpc_request_set *);
-int ptlrpc_expired_set(void *data);
-void ptlrpc_interrupted_set(void *data);
void ptlrpc_mark_interrupted(struct ptlrpc_request *req);
void ptlrpc_set_destroy(struct ptlrpc_request_set *);
void ptlrpc_set_add_req(struct ptlrpc_request_set *, struct ptlrpc_request *);
-void ptlrpc_set_add_new_req(struct ptlrpcd_ctl *pc,
- struct ptlrpc_request *req);
void ptlrpc_free_rq_pool(struct ptlrpc_request_pool *pool);
void ptlrpc_add_rqs_to_pool(struct ptlrpc_request_pool *pool, int num_rq);
void ptlrpc_server_drop_request(struct ptlrpc_request *req);
void ptlrpc_request_change_export(struct ptlrpc_request *req,
struct obd_export *export);
+void ptlrpc_update_export_timer(struct obd_export *exp, long extra_delay);
-#ifdef __KERNEL__
int ptlrpc_hr_init(void);
void ptlrpc_hr_fini(void);
-#else
-# define ptlrpc_hr_init() (0)
-# define ptlrpc_hr_fini() do {} while(0)
-#endif
/** @} */
/** @} */
/**
- * ptlrpc msg buffer and swab interface
+ * ptlrpc msg buffer and swab interface
*
* @{
*/
int ptlrpc_buf_need_swab(struct ptlrpc_request *req, const int inout,
- int index);
+ __u32 index);
void ptlrpc_buf_set_swabbed(struct ptlrpc_request *req, const int inout,
- int index);
+ __u32 index);
int ptlrpc_unpack_rep_msg(struct ptlrpc_request *req, int len);
int ptlrpc_unpack_req_msg(struct ptlrpc_request *req, int len);
unsigned int newlen, int move_data);
void lustre_free_reply_state(struct ptlrpc_reply_state *rs);
int __lustre_unpack_msg(struct lustre_msg *m, int len);
-int lustre_msg_hdr_size(__u32 magic, int count);
-int lustre_msg_size(__u32 magic, int count, __u32 *lengths);
-int lustre_msg_size_v2(int count, __u32 *lengths);
-int lustre_packed_msg_size(struct lustre_msg *msg);
-int lustre_msg_early_size(void);
-void *lustre_msg_buf_v2(struct lustre_msg_v2 *m, int n, int min_size);
-void *lustre_msg_buf(struct lustre_msg *m, int n, int minlen);
-int lustre_msg_buflen(struct lustre_msg *m, int n);
-void lustre_msg_set_buflen(struct lustre_msg *m, int n, int len);
-int lustre_msg_bufcount(struct lustre_msg *m);
-char *lustre_msg_string(struct lustre_msg *m, int n, int max_len);
+__u32 lustre_msg_hdr_size(__u32 magic, __u32 count);
+__u32 lustre_msg_size(__u32 magic, int count, __u32 *lengths);
+__u32 lustre_msg_size_v2(int count, __u32 *lengths);
+__u32 lustre_packed_msg_size(struct lustre_msg *msg);
+__u32 lustre_msg_early_size(void);
+void *lustre_msg_buf_v2(struct lustre_msg_v2 *m, __u32 n, __u32 min_size);
+void *lustre_msg_buf(struct lustre_msg *m, __u32 n, __u32 minlen);
+__u32 lustre_msg_buflen(struct lustre_msg *m, __u32 n);
+void lustre_msg_set_buflen(struct lustre_msg *m, __u32 n, __u32 len);
+__u32 lustre_msg_bufcount(struct lustre_msg *m);
+char *lustre_msg_string(struct lustre_msg *m, __u32 n, __u32 max_len);
__u32 lustre_msghdr_get_flags(struct lustre_msg *msg);
void lustre_msghdr_set_flags(struct lustre_msg *msg, __u32 flags);
__u32 lustre_msg_get_flags(struct lustre_msg *msg);
-void lustre_msg_add_flags(struct lustre_msg *msg, int flags);
-void lustre_msg_set_flags(struct lustre_msg *msg, int flags);
-void lustre_msg_clear_flags(struct lustre_msg *msg, int flags);
+void lustre_msg_add_flags(struct lustre_msg *msg, __u32 flags);
+void lustre_msg_set_flags(struct lustre_msg *msg, __u32 flags);
+void lustre_msg_clear_flags(struct lustre_msg *msg, __u32 flags);
__u32 lustre_msg_get_op_flags(struct lustre_msg *msg);
-void lustre_msg_add_op_flags(struct lustre_msg *msg, int flags);
-void lustre_msg_set_op_flags(struct lustre_msg *msg, int flags);
+void lustre_msg_add_op_flags(struct lustre_msg *msg, __u32 flags);
+void lustre_msg_set_op_flags(struct lustre_msg *msg, __u32 flags);
struct lustre_handle *lustre_msg_get_handle(struct lustre_msg *msg);
__u32 lustre_msg_get_type(struct lustre_msg *msg);
__u32 lustre_msg_get_version(struct lustre_msg *msg);
-void lustre_msg_add_version(struct lustre_msg *msg, int version);
+void lustre_msg_add_version(struct lustre_msg *msg, __u32 version);
__u32 lustre_msg_get_opc(struct lustre_msg *msg);
__u64 lustre_msg_get_last_xid(struct lustre_msg *msg);
+__u16 lustre_msg_get_tag(struct lustre_msg *msg);
__u64 lustre_msg_get_last_committed(struct lustre_msg *msg);
__u64 *lustre_msg_get_versions(struct lustre_msg *msg);
__u64 lustre_msg_get_transno(struct lustre_msg *msg);
__u32 lustre_msg_get_service_time(struct lustre_msg *msg);
char *lustre_msg_get_jobid(struct lustre_msg *msg);
__u32 lustre_msg_get_cksum(struct lustre_msg *msg);
-#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 50, 0)
+#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 53, 0)
__u32 lustre_msg_calc_cksum(struct lustre_msg *msg, int compat18);
#else
-# warning "remove checksum compatibility support for b1_8"
__u32 lustre_msg_calc_cksum(struct lustre_msg *msg);
#endif
void lustre_msg_set_handle(struct lustre_msg *msg,struct lustre_handle *handle);
void lustre_msg_set_type(struct lustre_msg *msg, __u32 type);
void lustre_msg_set_opc(struct lustre_msg *msg, __u32 opc);
void lustre_msg_set_last_xid(struct lustre_msg *msg, __u64 last_xid);
+void lustre_msg_set_tag(struct lustre_msg *msg, __u16 tag);
void lustre_msg_set_last_committed(struct lustre_msg *msg,__u64 last_committed);
void lustre_msg_set_versions(struct lustre_msg *msg, __u64 *versions);
void lustre_msg_set_transno(struct lustre_msg *msg, __u64 transno);
}
/**
- * Returns true if request \a req got early reply and hard deadline is not met
+ * Returns true if request \a req got early reply and hard deadline is not met
*/
static inline int
ptlrpc_client_early(struct ptlrpc_request *req)
spin_unlock(&req->rq_lock);
return 1;
}
- rc = req->rq_receiving_reply ;
- rc = rc || req->rq_req_unlink || req->rq_reply_unlink;
+ rc = !req->rq_req_unlinked || !req->rq_reply_unlinked ||
+ req->rq_receiving_reply;
spin_unlock(&req->rq_lock);
return rc;
}
int ptlrpc_pinger_add_import(struct obd_import *imp);
int ptlrpc_pinger_del_import(struct obd_import *imp);
int ptlrpc_add_timeout_client(int time, enum timeout_event event,
- timeout_cb_t cb, void *data,
- cfs_list_t *obd_list);
-int ptlrpc_del_timeout_client(cfs_list_t *obd_list,
+ timeout_cb_t cb, void *data,
+ struct list_head *obd_list);
+int ptlrpc_del_timeout_client(struct list_head *obd_list,
enum timeout_event event);
struct ptlrpc_request * ptlrpc_prep_ping(struct obd_import *imp);
int ptlrpc_obd_ping(struct obd_device *obd);
-#ifdef __KERNEL__
void ping_evictor_start(void);
void ping_evictor_stop(void);
-#else
-#define ping_evictor_start() do {} while (0)
-#define ping_evictor_stop() do {} while (0)
-#endif
void ptlrpc_pinger_ir_up(void);
void ptlrpc_pinger_ir_down(void);
/** @} */
* @{
*/
const char* ll_opcode2str(__u32 opcode);
-#ifdef LPROCFS
+#ifdef CONFIG_PROC_FS
void ptlrpc_lprocfs_register_obd(struct obd_device *obd);
void ptlrpc_lprocfs_unregister_obd(struct obd_device *obd);
void ptlrpc_lprocfs_brw(struct ptlrpc_request *req, int bytes);