632 lines · 20.6 KB · C
RawDownload
/* SPDX-License-Identifier: GPL-2.0 *//* * linux/include/linux/sunrpc/svc.h * * RPC server declarations. * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */  #ifndef SUNRPC_SVC_H#define SUNRPC_SVC_H #include <linux/in.h>#include <linux/in6.h>#include <linux/sunrpc/types.h>#include <linux/sunrpc/xdr.h>#include <linux/sunrpc/auth.h>#include <linux/sunrpc/svcauth.h>#include <linux/lwq.h>#include <linux/wait.h>#include <linux/mm.h>#include <linux/folio_batch.h>#include <linux/kthread.h> /* * * RPC service thread pool. * * Pool of threads and temporary sockets.  Generally there is only * a single one of these per RPC service, but on NUMA machines those * services that can benefit from it (i.e. nfs but not lockd) will * have one pool per NUMA node.  This optimisation reduces cross- * node traffic on multi-node NUMA NFS servers. */struct svc_pool {	unsigned int		sp_id;		/* pool id; also node id on NUMA */	unsigned int		sp_nrthreads;	/* # of threads currently running in pool */	unsigned int		sp_nrthrmin;	/* Min number of threads to run per pool */	unsigned int		sp_nrthrmax;	/* Max requested number of threads in pool */	struct lwq		sp_xprts;	/* pending transports */	struct list_head	sp_all_threads;	/* all server threads */	struct llist_head	sp_idle_threads; /* idle server threads */ 	/* statistics on pool operation */	struct percpu_counter	sp_messages_arrived;	struct percpu_counter	sp_sockets_queued;	struct percpu_counter	sp_threads_woken; 	unsigned long		sp_flags;} ____cacheline_aligned_in_smp; /* bits for sp_flags */enum {	SP_TASK_PENDING,	/* still work to do even if no xprt is queued */	SP_NEED_VICTIM,		/* One thread needs to agree to exit */	SP_VICTIM_REMAINS,	/* One thread needs to actually exit */	SP_TASK_STARTING,	/* Task has started but not added to idle yet */};  /* * RPC service. * * An RPC service is a ``daemon,'' possibly multithreaded, which * receives and processes incoming RPC messages. * It has one or more transport sockets associated with it, and maintains * a list of idle threads waiting for input. * * We currently do not support more than one RPC program per daemon. */struct svc_serv {	struct svc_program *	sv_programs;	/* RPC programs */	struct svc_stat *	sv_stats;	/* RPC statistics */	spinlock_t		sv_lock;	unsigned int		sv_nprogs;	/* Number of sv_programs */	unsigned int		sv_nrthreads;	/* # of running server threads */	unsigned int		sv_max_payload;	/* datagram payload size */	unsigned int		sv_max_mesg;	/* max_payload + 1 page for overheads */	unsigned int		sv_xdrsize;	/* XDR buffer size */	struct list_head	sv_permsocks;	/* all permanent sockets */	struct list_head	sv_tempsocks;	/* all temporary sockets */	int			sv_tmpcnt;	/* count of temporary "valid" sockets */	struct timer_list	sv_temptimer;	/* timer for aging temporary sockets */ 	char *			sv_name;	/* service name */ 	unsigned int		sv_nrpools;	/* number of thread pools */	bool			sv_is_pooled;	/* is this a pooled service? */	struct svc_pool *	sv_pools;	/* array of thread pools */	int			(*sv_threadfn)(void *data); #if defined(CONFIG_SUNRPC_BACKCHANNEL)	struct lwq		sv_cb_list;	/* queue for callback requests						 * that arrive over the same						 * connection */	bool			sv_bc_enabled;	/* service uses backchannel */#endif /* CONFIG_SUNRPC_BACKCHANNEL */}; /* This is used by pool_stats to find and lock an svc */struct svc_info {	struct svc_serv		*serv;	struct mutex		*mutex;}; void svc_destroy(struct svc_serv **svcp); /* * Maximum payload size supported by a kernel RPC server. * This is use to determine the max number of pages nfsd is * willing to return in a single READ operation. * * These happen to all be powers of 2, which is not strictly * necessary but helps enforce the real limitation, which is * that they should be multiples of PAGE_SIZE. * * For UDP transports, a block plus NFS,RPC, and UDP headers * has to fit into the IP datagram limit of 64K.  The largest * feasible number for all known page sizes is probably 48K, * but we choose 32K here.  This is the same as the historical * Linux limit; someone who cares more about NFS/UDP performance * can test a larger number. * * For non-UDP transports we have more freedom.  A size of 4MB is * chosen to accommodate clients that support larger I/O sizes. */enum {	RPCSVC_MAXPAYLOAD	= 4 * 1024 * 1024,	RPCSVC_MAXPAYLOAD_TCP	= RPCSVC_MAXPAYLOAD,	RPCSVC_MAXPAYLOAD_UDP	= 32 * 1024,}; extern u32 svc_max_payload(const struct svc_rqst *rqstp); /* * RPC Call and Reply messages each have their own page array. * rq_pages holds the incoming Call message; rq_respages holds * the outgoing Reply message. Both arrays are sized to * svc_serv_maxpages() entries and are allocated dynamically. * * Pages are sent using ->sendmsg with MSG_SPLICE_PAGES so each * server thread needs to allocate more to replace those used in * sending. * * rq_pages request page contract: * * Transport receive paths that move request data pages out of * rq_pages -- TCP multi-fragment reassembly (svc_tcp_save_pages) * and RDMA Read I/O (svc_rdma_clear_rqst_pages) -- NULL those * entries to prevent svc_rqst_release_pages() from freeing pages * still in transport use, and set rq_pages_nfree to the count. * svc_alloc_arg() refills only that many rq_pages entries. * * For rq_respages, svc_rqst_release_pages() NULLs entries in * [rq_respages, rq_next_page) after each RPC. svc_alloc_arg() * refills only that range. * * xdr_buf holds responses; the structure fits NFS read responses * (header, data pages, optional tail) and enables sharing of * client-side routines. * * The xdr_buf.head kvec always points to the first page in the * rq_*pages list. The xdr_buf.pages pointer points to the second * page on that list. xdr_buf.tail points to the end of the first * page. This assumes that the non-page part of an rpc reply will * fit in a page - NFSd ensures this. lockd also has no trouble. */ /** * svc_serv_maxpages - maximum count of pages needed for one RPC message * @serv: RPC service context * * Returns a count of pages or vectors that can hold the maximum * size RPC message for @serv. * * Each page array can hold at most one payload plus two * overhead pages (one for the RPC header, one for tail data). * nfsd_splice_actor() might need an extra page when a READ * payload is not page-aligned. */static inline unsigned long svc_serv_maxpages(const struct svc_serv *serv){	return DIV_ROUND_UP(serv->sv_max_mesg, PAGE_SIZE) + 2 + 1;} /* * The context of a single thread, including the request currently being * processed. * * RPC programs are free to use rq_private to stash thread-local information. * The sunrpc layer will not access it. */struct svc_rqst {	struct list_head	rq_all;		/* all threads list */	struct llist_node	rq_idle;	/* On the idle list */	struct rcu_head		rq_rcu_head;	/* for RCU deferred kfree */	struct svc_xprt *	rq_xprt;	/* transport ptr */ 	struct sockaddr_storage	rq_addr;	/* peer address */	size_t			rq_addrlen;	struct sockaddr_storage	rq_daddr;	/* dest addr of request						 *  - reply from here */	size_t			rq_daddrlen; 	struct svc_serv *	rq_server;	/* RPC service definition */	struct svc_pool *	rq_pool;	/* thread pool */	const struct svc_procedure *rq_procinfo;/* procedure info */	struct auth_ops *	rq_authop;	/* authentication flavour */	struct svc_cred		rq_cred;	/* auth info */	void *			rq_xprt_ctxt;	/* transport specific context ptr */	struct svc_deferred_req*rq_deferred;	/* deferred request we are replaying */ 	struct xdr_buf		rq_arg;	struct xdr_stream	rq_arg_stream;	struct xdr_stream	rq_res_stream;	struct folio		*rq_scratch_folio;	struct xdr_buf		rq_res;	unsigned long		rq_maxpages;	/* entries per page array */	unsigned long		rq_pages_nfree;	/* rq_pages entries NULLed by transport */	struct page *		*rq_pages;	/* Call buffer pages */	struct page *		*rq_respages;	/* Reply buffer pages */	struct page *		*rq_next_page; /* next reply page to use */	struct page *		*rq_page_end;  /* one past the last reply page */ 	struct folio_batch	rq_fbatch;	struct bio_vec		*rq_bvec; 	__be32			rq_xid;		/* transmission id */	u32			rq_prog;	/* program number */	u32			rq_vers;	/* program version */	u32			rq_proc;	/* procedure number */	u32			rq_prot;	/* IP protocol */	unsigned long		rq_flags;	/* flags field */	ktime_t			rq_qtime;	/* enqueue time */ 	void *			rq_argp;	/* decoded arguments */	void *			rq_resp;	/* xdr'd results */	__be32			*rq_accept_statp;	void *			rq_auth_data;	/* flavor-specific data */	__be32			rq_auth_stat;	/* authentication status */	int			rq_auth_slack;	/* extra space xdr code						 * should leave in head						 * for krb5i, krb5p.						 */	int			rq_reserved;	/* space on socket outq						 * reserved for this request						 */	ktime_t			rq_stime;	/* start time */ 	struct cache_req	rq_chandle;	/* handle passed to caches for 						 * request delaying 						 */	/* Catering to nfsd */	struct auth_domain *	rq_client;	/* RPC peer info */	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */	struct task_struct	*rq_task;	/* service thread */	struct net		*rq_bc_net;	/* pointer to backchannel's						 * net namespace						 */ 	int			rq_err;		/* Thread sets this to inidicate						 * initialisation success.						 */ 	unsigned long		bc_to_initval;	unsigned int		bc_to_retries;	unsigned int		rq_status_counter; /* RPC processing counter */	void			*rq_private;	/* For use by the service thread */}; /* bits for rq_flags */enum {	RQ_SECURE,		/* secure port */	RQ_LOCAL,		/* local request */	RQ_USEDEFERRAL,		/* use deferral */	RQ_DROPME,		/* drop current reply */	RQ_VICTIM,		/* Have agreed to shut down */	RQ_DATA,		/* request has data */}; #define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net) /* * Rigorous type checking on sockaddr type conversions */static inline struct sockaddr_in *svc_addr_in(const struct svc_rqst *rqst){	return (struct sockaddr_in *) &rqst->rq_addr;} static inline struct sockaddr_in6 *svc_addr_in6(const struct svc_rqst *rqst){	return (struct sockaddr_in6 *) &rqst->rq_addr;} static inline struct sockaddr *svc_addr(const struct svc_rqst *rqst){	return (struct sockaddr *) &rqst->rq_addr;} static inline struct sockaddr_in *svc_daddr_in(const struct svc_rqst *rqst){	return (struct sockaddr_in *) &rqst->rq_daddr;} static inline struct sockaddr_in6 *svc_daddr_in6(const struct svc_rqst *rqst){	return (struct sockaddr_in6 *) &rqst->rq_daddr;} static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst){	return (struct sockaddr *) &rqst->rq_daddr;} /** * svc_thread_should_stop - check if this thread should stop * @rqstp: the thread that might need to stop * * To stop an svc thread, the pool flags SP_NEED_VICTIM and SP_VICTIM_REMAINS * are set.  The first thread which sees SP_NEED_VICTIM clears it, becoming * the victim using this function.  It should then promptly call * svc_exit_thread() to complete the process, clearing SP_VICTIM_REMAINS * so the task waiting for a thread to exit can wake and continue. * * Return values: *   %true: caller should invoke svc_exit_thread() *   %false: caller should do nothing */static inline bool svc_thread_should_stop(struct svc_rqst *rqstp){	if (test_and_clear_bit(SP_NEED_VICTIM, &rqstp->rq_pool->sp_flags))		set_bit(RQ_VICTIM, &rqstp->rq_flags); 	return test_bit(RQ_VICTIM, &rqstp->rq_flags);} /** * svc_thread_init_status - report whether thread has initialised successfully * @rqstp: the thread in question * @err: errno code * * After performing any initialisation that could fail, and before starting * normal work, each sunrpc svc_thread must call svc_thread_init_status() * with an appropriate error, or zero. * * If zero is passed, the thread is ready and must continue until * svc_thread_should_stop() returns true.  If a non-zero error is passed * the call will not return - the thread will exit. */static inline void svc_thread_init_status(struct svc_rqst *rqstp, int err){	store_release_wake_up(&rqstp->rq_err, err);	if (err)		kthread_exit(1);} struct svc_deferred_req {	u32			prot;	/* protocol (UDP or TCP) */	struct svc_xprt		*xprt;	struct sockaddr_storage	addr;	/* where reply must go */	size_t			addrlen;	struct sockaddr_storage	daddr;	/* where reply must come from */	size_t			daddrlen;	void			*xprt_ctxt;	struct cache_deferred_req handle;	int			argslen;	__be32			args[];}; struct svc_process_info {	union {		int  (*dispatch)(struct svc_rqst *rqstp);		struct {			unsigned int lovers;			unsigned int hivers;		} mismatch;	};}; /* * RPC program - an array of these can use the same transport endpoint */struct svc_program {	u32			pg_prog;	/* program number */	unsigned int		pg_lovers;	/* lowest version */	unsigned int		pg_hivers;	/* highest version */	unsigned int		pg_nvers;	/* number of versions */	const struct svc_version **pg_vers;	/* version array */	char *			pg_name;	/* service name */	char *			pg_class;	/* class name: services sharing authentication */	enum svc_auth_status	(*pg_authenticate)(struct svc_rqst *rqstp);	__be32			(*pg_init_request)(struct svc_rqst *,						   const struct svc_program *,						   struct svc_process_info *);	int			(*pg_rpcbind_set)(struct net *net,						  const struct svc_program *,						  u32 version, int family,						  unsigned short proto,						  unsigned short port);}; /* * RPC program version */struct svc_version {	u32			vs_vers;	/* version number */	u32			vs_nproc;	/* number of procedures */	const struct svc_procedure *vs_proc;	/* per-procedure info */	unsigned long __percpu	*vs_count;	/* call counts */	u32			vs_xdrsize;	/* xdrsize needed for this version */ 	/* Don't register with rpcbind */	bool			vs_hidden; 	/* Don't care if the rpcbind registration fails */	bool			vs_rpcb_optnl; 	/* Need xprt with congestion control */	bool			vs_need_cong_ctrl; 	/* Dispatch function */	int			(*vs_dispatch)(struct svc_rqst *rqstp);}; /* * RPC procedure info */struct svc_procedure {	/* process the request: */	__be32			(*pc_func)(struct svc_rqst *);	/* XDR decode args: */	bool			(*pc_decode)(struct svc_rqst *rqstp,					     struct xdr_stream *xdr);	/* XDR encode result: */	bool			(*pc_encode)(struct svc_rqst *rqstp,					     struct xdr_stream *xdr);	/* XDR free result: */	void			(*pc_release)(struct svc_rqst *);	unsigned int		pc_argsize;	/* argument struct size */	unsigned int		pc_argzero;	/* how much of argument to clear */	unsigned int		pc_ressize;	/* result struct size */	unsigned int		pc_cachetype;	/* cache info (NFS) */	unsigned int		pc_xdrressize;	/* maximum size of XDR reply */	const char *		pc_name;	/* for display */}; /* * Function prototypes. */int sunrpc_set_pool_mode(const char *val);int sunrpc_get_pool_mode(char *val, size_t size);void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net);int svc_bind(struct svc_serv *serv, struct net *net);struct svc_serv *svc_create(struct svc_program *, unsigned int,			    int (*threadfn)(void *data));bool		   svc_rqst_replace_page(struct svc_rqst *rqstp,					 struct page *page);void		   svc_rqst_release_pages(struct svc_rqst *rqstp);int		   svc_new_thread(struct svc_serv *serv, struct svc_pool *pool);void		   svc_exit_thread(struct svc_rqst *);struct svc_serv *  svc_create_pooled(struct svc_program *prog,				     unsigned int nprog,				     struct svc_stat *stats,				     unsigned int bufsize,				     int (*threadfn)(void *data));int		   svc_set_pool_threads(struct svc_serv *serv, struct svc_pool *pool,					unsigned int min_threads, unsigned int max_threads);int		   svc_set_num_threads(struct svc_serv *serv, unsigned int min_threads,				       unsigned int nrservs);int		   svc_pool_stats_open(struct svc_info *si, struct file *file);void		   svc_process(struct svc_rqst *rqstp);void		   svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp);int		   svc_register(const struct svc_serv *, struct net *, const int,				const unsigned short, const unsigned short); void		   svc_wake_up(struct svc_serv *);void		   svc_reserve(struct svc_rqst *rqstp, int space);void		   svc_pool_wake_idle_thread(struct svc_pool *pool);struct svc_pool   *svc_pool_for_cpu(struct svc_serv *serv);char *		   svc_print_addr(struct svc_rqst *, char *, size_t);const char *	   svc_proc_name(const struct svc_rqst *rqstp);int		   svc_encode_result_payload(struct svc_rqst *rqstp,					     unsigned int offset,					     unsigned int length);char		  *svc_fill_symlink_pathname(struct svc_rqst *rqstp,					     struct kvec *first, void *p,					     size_t total);__be32		   svc_generic_init_request(struct svc_rqst *rqstp,					    const struct svc_program *progp,					    struct svc_process_info *procinfo);int		   svc_generic_rpcbind_set(struct net *net,					   const struct svc_program *progp,					   u32 version, int family,					   unsigned short proto,					   unsigned short port); #define	RPC_MAX_ADDRBUFLEN	(63U) 

Lines 1–500 of 632.