linux_dsm_epyc7002/include/linux/nfsd/state.h
Andy Adamson ec6b5d7b50 nfsd41: create_session operation
Implement the create_session operation confoming to
http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-26

Look up the client id (generated by the server on exchange_id,
given by the client on create_session).
If neither a confirmed or unconfirmed client is found
then the client id is stale
If a confirmed cilent is found (i.e. we already received
create_session for it) then compare the sequence id
to determine if it's a replay or possibly a mis-ordered rpc.
If the seqid is in order, update the confirmed client seqid
and procedd with updating the session parameters.

If an unconfirmed client_id is found then verify the creds
and seqid.  If both match move the client id to confirmed state
and proceed with processing the create_session.

Currently, we do not support persistent sessions, and RDMA.

alloc_init_session generates a new sessionid and creates
a session structure.

NFSD_PAGES_PER_SLOT is used for the max response cached calculation, and for
the counting of DRC pages using the hard limits set in struct srv_serv.

A note on NFSD_PAGES_PER_SLOT:

Other patches in this series allow for NFSD_PAGES_PER_SLOT + 1 pages to be
cached in a DRC slot when the response size is less than NFSD_PAGES_PER_SLOT *
PAGE_SIZE but xdr_buf pages are used. e.g. a READDIR operation will encode a
small amount of data in the xdr_buf head, and then the READDIR in the xdr_buf
pages.  So, the hard limit calculation use of pages by a session is
underestimated by the number of cached operations using the xdr_buf pages.

Yet another patch caches no pages for the solo sequence operation, or any
compound where cache_this is False.  So the hard limit calculation use of
pages by a session is overestimated by the number of these operations in the
cache.

TODO: improve resource pre-allocation and negotiate session
parameters accordingly.  Respect and possibly adjust
backchannel attributes.

Signed-off-by: Marc Eshel <eshel@almaden.ibm.com>
Signed-off-by: Dean Hildebrand <dhildeb@us.ibm.com>
[nfsd41: remove headerpadsz from channel attributes]
Our client and server only support a headerpadsz of 0.
[nfsd41: use DRC limits in fore channel init]
[nfsd41: do not change CREATE_SESSION back channel attrs]
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
[use sessionid_lock spin lock]
[nfsd41: use bool inuse for slot state]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
[nfsd41 remove sl_session from alloc_init_session]
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
[simplify nfsd4_encode_create_session error handling]
[nfsd41: fix comment style in init_forechannel_attrs]
[nfsd41: allocate struct nfsd4_session and slot table in one piece]
[nfsd41: no need to INIT_LIST_HEAD in alloc_init_session just prior to list_add]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
2009-04-03 17:41:18 -07:00

369 lines
12 KiB
C

/*
* linux/include/nfsd/state.h
*
* Copyright (c) 2001 The Regents of the University of Michigan.
* All rights reserved.
*
* Kendrick Smith <kmsmith@umich.edu>
* Andy Adamson <andros@umich.edu>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
*/
#ifndef _NFSD4_STATE_H
#define _NFSD4_STATE_H
#include <linux/list.h>
#include <linux/kref.h>
#include <linux/sunrpc/clnt.h>
#define NFS4_OPAQUE_LIMIT 1024
typedef struct {
u32 cl_boot;
u32 cl_id;
} clientid_t;
typedef struct {
u32 so_boot;
u32 so_stateownerid;
u32 so_fileid;
} stateid_opaque_t;
typedef struct {
u32 si_generation;
stateid_opaque_t si_opaque;
} stateid_t;
#define si_boot si_opaque.so_boot
#define si_stateownerid si_opaque.so_stateownerid
#define si_fileid si_opaque.so_fileid
struct nfs4_cb_recall {
u32 cbr_ident;
int cbr_trunc;
stateid_t cbr_stateid;
struct knfsd_fh cbr_fh;
struct nfs4_delegation *cbr_dp;
};
struct nfs4_delegation {
struct list_head dl_perfile;
struct list_head dl_perclnt;
struct list_head dl_recall_lru; /* delegation recalled */
atomic_t dl_count; /* ref count */
struct nfs4_client *dl_client;
struct nfs4_file *dl_file;
struct file_lock *dl_flock;
struct file *dl_vfs_file;
u32 dl_type;
time_t dl_time;
struct nfs4_cb_recall dl_recall;
};
#define dl_stateid dl_recall.cbr_stateid
#define dl_fh dl_recall.cbr_fh
/* client delegation callback info */
struct nfs4_callback {
/* SETCLIENTID info */
u32 cb_addr;
unsigned short cb_port;
u32 cb_prog;
u32 cb_ident;
/* RPC client info */
atomic_t cb_set; /* successful CB_NULL call */
struct rpc_clnt * cb_client;
};
/* Maximum number of slots per session. 128 is useful for long haul TCP */
#define NFSD_MAX_SLOTS_PER_SESSION 128
/* Maximum number of pages per slot cache entry */
#define NFSD_PAGES_PER_SLOT 1
/* Maximum number of operations per session compound */
#define NFSD_MAX_OPS_PER_COMPOUND 16
struct nfsd4_cache_entry {
__be32 ce_status;
struct kvec ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */
struct page *ce_respages[NFSD_PAGES_PER_SLOT + 1];
short ce_resused;
int ce_opcnt;
int ce_rpchdrlen;
};
struct nfsd4_slot {
bool sl_inuse;
u32 sl_seqid;
struct nfsd4_cache_entry sl_cache_entry;
};
struct nfsd4_session {
struct kref se_ref;
struct list_head se_hash; /* hash by sessionid */
struct list_head se_perclnt;
u32 se_flags;
struct nfs4_client *se_client; /* for expire_client */
struct nfs4_sessionid se_sessionid;
u32 se_fmaxreq_sz;
u32 se_fmaxresp_sz;
u32 se_fmaxresp_cached;
u32 se_fmaxops;
u32 se_fnumslots;
struct nfsd4_slot se_slots[]; /* forward channel slots */
};
static inline void
nfsd4_put_session(struct nfsd4_session *ses)
{
extern void free_session(struct kref *kref);
kref_put(&ses->se_ref, free_session);
}
static inline void
nfsd4_get_session(struct nfsd4_session *ses)
{
kref_get(&ses->se_ref);
}
/* formatted contents of nfs4_sessionid */
struct nfsd4_sessionid {
clientid_t clientid;
u32 sequence;
u32 reserved;
};
#define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */
/*
* struct nfs4_client - one per client. Clientids live here.
* o Each nfs4_client is hashed by clientid.
*
* o Each nfs4_clients is also hashed by name
* (the opaque quantity initially sent by the client to identify itself).
*
* o cl_perclient list is used to ensure no dangling stateowner references
* when we expire the nfs4_client
*/
struct nfs4_client {
struct list_head cl_idhash; /* hash by cl_clientid.id */
struct list_head cl_strhash; /* hash by cl_name */
struct list_head cl_openowners;
struct list_head cl_delegations;
struct list_head cl_lru; /* tail queue */
struct xdr_netobj cl_name; /* id generated by client */
char cl_recdir[HEXDIR_LEN]; /* recovery dir */
nfs4_verifier cl_verifier; /* generated by client */
time_t cl_time; /* time of last lease renewal */
__be32 cl_addr; /* client ipaddress */
u32 cl_flavor; /* setclientid pseudoflavor */
char *cl_principal; /* setclientid principal name */
struct svc_cred cl_cred; /* setclientid principal */
clientid_t cl_clientid; /* generated by server */
nfs4_verifier cl_confirm; /* generated by server */
struct nfs4_callback cl_callback; /* callback info */
atomic_t cl_count; /* ref count */
u32 cl_firststate; /* recovery dir creation */
/* for nfs41 */
struct list_head cl_sessions;
u32 cl_seqid; /* seqid for create_session */
u32 cl_exchange_flags;
struct nfs4_sessionid cl_sessionid;
};
/* struct nfs4_client_reset
* one per old client. Populates reset_str_hashtbl. Filled from conf_id_hashtbl
* upon lease reset, or from upcall to state_daemon (to read in state
* from non-volitile storage) upon reboot.
*/
struct nfs4_client_reclaim {
struct list_head cr_strhash; /* hash by cr_name */
char cr_recdir[HEXDIR_LEN]; /* recover dir */
};
static inline void
update_stateid(stateid_t *stateid)
{
stateid->si_generation++;
}
/* A reasonable value for REPLAY_ISIZE was estimated as follows:
* The OPEN response, typically the largest, requires
* 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) +
* 4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) +
* 20(deleg. space limit) + ~32(deleg. ace) = 112 bytes
*/
#define NFSD4_REPLAY_ISIZE 112
/*
* Replay buffer, where the result of the last seqid-mutating operation
* is cached.
*/
struct nfs4_replay {
__be32 rp_status;
unsigned int rp_buflen;
char *rp_buf;
unsigned intrp_allocated;
struct knfsd_fh rp_openfh;
char rp_ibuf[NFSD4_REPLAY_ISIZE];
};
/*
* nfs4_stateowner can either be an open_owner, or a lock_owner
*
* so_idhash: stateid_hashtbl[] for open owner, lockstateid_hashtbl[]
* for lock_owner
* so_strhash: ownerstr_hashtbl[] for open_owner, lock_ownerstr_hashtbl[]
* for lock_owner
* so_perclient: nfs4_client->cl_perclient entry - used when nfs4_client
* struct is reaped.
* so_perfilestate: heads the list of nfs4_stateid (either open or lock)
* and is used to ensure no dangling nfs4_stateid references when we
* release a stateowner.
* so_perlockowner: (open) nfs4_stateid->st_perlockowner entry - used when
* close is called to reap associated byte-range locks
* so_close_lru: (open) stateowner is placed on this list instead of being
* reaped (when so_perfilestate is empty) to hold the last close replay.
* reaped by laundramat thread after lease period.
*/
struct nfs4_stateowner {
struct kref so_ref;
struct list_head so_idhash; /* hash by so_id */
struct list_head so_strhash; /* hash by op_name */
struct list_head so_perclient;
struct list_head so_stateids;
struct list_head so_perstateid; /* for lockowners only */
struct list_head so_close_lru; /* tail queue */
time_t so_time; /* time of placement on so_close_lru */
int so_is_open_owner; /* 1=openowner,0=lockowner */
u32 so_id;
struct nfs4_client * so_client;
/* after increment in ENCODE_SEQID_OP_TAIL, represents the next
* sequence id expected from the client: */
u32 so_seqid;
struct xdr_netobj so_owner; /* open owner name */
int so_confirmed; /* successful OPEN_CONFIRM? */
struct nfs4_replay so_replay;
};
/*
* nfs4_file: a file opened by some number of (open) nfs4_stateowners.
* o fi_perfile list is used to search for conflicting
* share_acces, share_deny on the file.
*/
struct nfs4_file {
atomic_t fi_ref;
struct list_head fi_hash; /* hash by "struct inode *" */
struct list_head fi_stateids;
struct list_head fi_delegations;
struct inode *fi_inode;
u32 fi_id; /* used with stateowner->so_id
* for stateid_hashtbl hash */
bool fi_had_conflict;
};
/*
* nfs4_stateid can either be an open stateid or (eventually) a lock stateid
*
* (open)nfs4_stateid: one per (open)nfs4_stateowner, nfs4_file
*
* st_hash: stateid_hashtbl[] entry or lockstateid_hashtbl entry
* st_perfile: file_hashtbl[] entry.
* st_perfile_state: nfs4_stateowner->so_perfilestate
* st_perlockowner: (open stateid) list of lock nfs4_stateowners
* st_access_bmap: used only for open stateid
* st_deny_bmap: used only for open stateid
* st_openstp: open stateid lock stateid was derived from
*
* XXX: open stateids and lock stateids have diverged sufficiently that
* we should consider defining separate structs for the two cases.
*/
struct nfs4_stateid {
struct list_head st_hash;
struct list_head st_perfile;
struct list_head st_perstateowner;
struct list_head st_lockowners;
struct nfs4_stateowner * st_stateowner;
struct nfs4_file * st_file;
stateid_t st_stateid;
struct file * st_vfs_file;
unsigned long st_access_bmap;
unsigned long st_deny_bmap;
struct nfs4_stateid * st_openstp;
};
/* flags for preprocess_seqid_op() */
#define CONFIRM 0x00000002
#define OPEN_STATE 0x00000004
#define LOCK_STATE 0x00000008
#define RD_STATE 0x00000010
#define WR_STATE 0x00000020
#define CLOSE_STATE 0x00000040
#define seqid_mutating_err(err) \
(((err) != nfserr_stale_clientid) && \
((err) != nfserr_bad_seqid) && \
((err) != nfserr_stale_stateid) && \
((err) != nfserr_bad_stateid))
extern __be32 nfs4_preprocess_stateid_op(struct svc_fh *current_fh,
stateid_t *stateid, int flags, struct file **filp);
extern void nfs4_lock_state(void);
extern void nfs4_unlock_state(void);
extern int nfs4_in_grace(void);
extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
extern void put_nfs4_client(struct nfs4_client *clp);
extern void nfs4_free_stateowner(struct kref *kref);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
extern void nfs4_put_delegation(struct nfs4_delegation *dp);
extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
extern void nfsd4_init_recdir(char *recdir_name);
extern int nfsd4_recdir_load(void);
extern void nfsd4_shutdown_recdir(void);
extern int nfs4_client_to_reclaim(const char *name);
extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
extern void nfsd4_recdir_purge_old(void);
extern int nfsd4_create_clid_dir(struct nfs4_client *clp);
extern void nfsd4_remove_clid_dir(struct nfs4_client *clp);
static inline void
nfs4_put_stateowner(struct nfs4_stateowner *so)
{
kref_put(&so->so_ref, nfs4_free_stateowner);
}
static inline void
nfs4_get_stateowner(struct nfs4_stateowner *so)
{
kref_get(&so->so_ref);
}
#endif /* NFSD4_STATE_H */