X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=fs%2Fnfsd%2Fnfs4state.c;h=d24dd12ddb4d11d1ebfd49bc11e69d72bee731e3;hp=0b03c1ed21c5d0157f2ff6a41c1614be64e193e8;hb=b8fd47aefa5f13df1edacbc7e68d9874635109e5;hpb=21315edd4877b593d5bf17a601a48fc836b8ba58 diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 0b03c1e..d24dd12 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -49,7 +50,11 @@ #include #include #include +#include #include +#include +#include +#include #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -57,14 +62,13 @@ static time_t lease_time = 90; /* default lease time */ static time_t user_lease_time = 90; static time_t boot_time; -static int in_grace = 1; -static u32 current_clientid = 1; static u32 current_ownerid = 1; static u32 current_fileid = 1; static u32 current_delegid = 1; static u32 nfs4_init; static stateid_t zerostateid; /* bits all 0 */ static stateid_t onestateid; /* bits all 1 */ +static u64 current_sessionid = 1; #define ZERO_STATEID(stateid) (!memcmp((stateid), &zerostateid, sizeof(stateid_t))) #define ONE_STATEID(stateid) (!memcmp((stateid), &onestateid, sizeof(stateid_t))) @@ -72,18 +76,21 @@ static stateid_t onestateid; /* bits all 1 */ /* forward declarations */ static struct nfs4_stateid * find_stateid(stateid_t *stid, int flags); static struct nfs4_delegation * find_delegation_stateid(struct inode *ino, stateid_t *stid); -static void release_stateid_lockowners(struct nfs4_stateid *open_stp); static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery"; static void nfs4_set_recdir(char *recdir); -/* Locking: - * - * client_mutex: - * protects clientid_hashtbl[], clientstr_hashtbl[], - * unconfstr_hashtbl[], uncofid_hashtbl[]. - */ +/* Locking: */ + +/* Currently used for almost all code touching nfsv4 state: */ static DEFINE_MUTEX(client_mutex); +/* + * Currently used for the del_recall_lru and file hash table. In an + * effort to decrease the scope of the client_mutex, this spinlock may + * eventually cover more: + */ +static DEFINE_SPINLOCK(recall_lock); + static struct kmem_cache *stateowner_slab = NULL; static struct kmem_cache *file_slab = NULL; static struct kmem_cache *stateid_slab = NULL; @@ -114,40 +121,27 @@ opaque_hashval(const void *ptr, int nbytes) return x; } -/* forward declarations */ -static void release_stateowner(struct nfs4_stateowner *sop); -static void release_stateid(struct nfs4_stateid *stp, int flags); - -/* - * Delegation state - */ - -/* recall_lock protects the del_recall_lru */ -static DEFINE_SPINLOCK(recall_lock); static struct list_head del_recall_lru; -static void -free_nfs4_file(struct kref *kref) -{ - struct nfs4_file *fp = container_of(kref, struct nfs4_file, fi_ref); - list_del(&fp->fi_hash); - iput(fp->fi_inode); - kmem_cache_free(file_slab, fp); -} - static inline void put_nfs4_file(struct nfs4_file *fi) { - kref_put(&fi->fi_ref, free_nfs4_file); + if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) { + list_del(&fi->fi_hash); + spin_unlock(&recall_lock); + iput(fi->fi_inode); + kmem_cache_free(file_slab, fi); + } } static inline void get_nfs4_file(struct nfs4_file *fi) { - kref_get(&fi->fi_ref); + atomic_inc(&fi->fi_ref); } static int num_delegations; +unsigned int max_delegations; /* * Open owner state (share locks) @@ -191,7 +185,9 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f struct nfs4_callback *cb = &stp->st_stateowner->so_client->cl_callback; dprintk("NFSD alloc_init_deleg\n"); - if (num_delegations > STATEID_HASH_SIZE * 4) + if (fp->fi_had_conflict) + return NULL; + if (num_delegations > max_delegations) return NULL; dp = kmem_cache_alloc(deleg_slab, GFP_KERNEL); if (dp == NULL) @@ -210,13 +206,11 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f dp->dl_recall.cbr_dp = NULL; dp->dl_recall.cbr_ident = cb->cb_ident; dp->dl_recall.cbr_trunc = 0; - dp->dl_stateid.si_boot = boot_time; + dp->dl_stateid.si_boot = get_seconds(); dp->dl_stateid.si_stateownerid = current_delegid++; dp->dl_stateid.si_fileid = 0; dp->dl_stateid.si_generation = 0; - dp->dl_fhlen = current_fh->fh_handle.fh_size; - memcpy(dp->dl_fhval, ¤t_fh->fh_handle.fh_base, - current_fh->fh_handle.fh_size); + fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle); dp->dl_time = 0; atomic_set(&dp->dl_count, 1); list_add(&dp->dl_perfile, &fp->fi_delegations); @@ -250,7 +244,7 @@ nfs4_close_delegation(struct nfs4_delegation *dp) /* The following nfsd_close may not actually close the file, * but we want to remove the lease in any case. */ if (dp->dl_flock) - setlease(filp, F_UNLCK, &dp->dl_flock); + vfs_setlease(filp, F_UNLCK, &dp->dl_flock); nfsd_close(filp); } @@ -305,6 +299,291 @@ static struct list_head unconf_id_hashtbl[CLIENT_HASH_SIZE]; static struct list_head client_lru; static struct list_head close_lru; +static void unhash_generic_stateid(struct nfs4_stateid *stp) +{ + list_del(&stp->st_hash); + list_del(&stp->st_perfile); + list_del(&stp->st_perstateowner); +} + +static void free_generic_stateid(struct nfs4_stateid *stp) +{ + put_nfs4_file(stp->st_file); + kmem_cache_free(stateid_slab, stp); +} + +static void release_lock_stateid(struct nfs4_stateid *stp) +{ + unhash_generic_stateid(stp); + locks_remove_posix(stp->st_vfs_file, (fl_owner_t)stp->st_stateowner); + free_generic_stateid(stp); +} + +static void unhash_lockowner(struct nfs4_stateowner *sop) +{ + struct nfs4_stateid *stp; + + list_del(&sop->so_idhash); + list_del(&sop->so_strhash); + list_del(&sop->so_perstateid); + while (!list_empty(&sop->so_stateids)) { + stp = list_first_entry(&sop->so_stateids, + struct nfs4_stateid, st_perstateowner); + release_lock_stateid(stp); + } +} + +static void release_lockowner(struct nfs4_stateowner *sop) +{ + unhash_lockowner(sop); + nfs4_put_stateowner(sop); +} + +static void +release_stateid_lockowners(struct nfs4_stateid *open_stp) +{ + struct nfs4_stateowner *lock_sop; + + while (!list_empty(&open_stp->st_lockowners)) { + lock_sop = list_entry(open_stp->st_lockowners.next, + struct nfs4_stateowner, so_perstateid); + /* list_del(&open_stp->st_lockowners); */ + BUG_ON(lock_sop->so_is_open_owner); + release_lockowner(lock_sop); + } +} + +static void release_open_stateid(struct nfs4_stateid *stp) +{ + unhash_generic_stateid(stp); + release_stateid_lockowners(stp); + nfsd_close(stp->st_vfs_file); + free_generic_stateid(stp); +} + +static void unhash_openowner(struct nfs4_stateowner *sop) +{ + struct nfs4_stateid *stp; + + list_del(&sop->so_idhash); + list_del(&sop->so_strhash); + list_del(&sop->so_perclient); + list_del(&sop->so_perstateid); /* XXX: necessary? */ + while (!list_empty(&sop->so_stateids)) { + stp = list_first_entry(&sop->so_stateids, + struct nfs4_stateid, st_perstateowner); + release_open_stateid(stp); + } +} + +static void release_openowner(struct nfs4_stateowner *sop) +{ + unhash_openowner(sop); + list_del(&sop->so_close_lru); + nfs4_put_stateowner(sop); +} + +static DEFINE_SPINLOCK(sessionid_lock); +#define SESSION_HASH_SIZE 512 +static struct list_head sessionid_hashtbl[SESSION_HASH_SIZE]; + +static inline int +hash_sessionid(struct nfs4_sessionid *sessionid) +{ + struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid; + + return sid->sequence % SESSION_HASH_SIZE; +} + +static inline void +dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) +{ + u32 *ptr = (u32 *)(&sessionid->data[0]); + dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]); +} + +static void +gen_sessionid(struct nfsd4_session *ses) +{ + struct nfs4_client *clp = ses->se_client; + struct nfsd4_sessionid *sid; + + sid = (struct nfsd4_sessionid *)ses->se_sessionid.data; + sid->clientid = clp->cl_clientid; + sid->sequence = current_sessionid++; + sid->reserved = 0; +} + +/* + * Give the client the number of slots it requests bound by + * NFSD_MAX_SLOTS_PER_SESSION and by sv_drc_max_pages. + * + * If we run out of pages (sv_drc_pages_used == sv_drc_max_pages) we + * should (up to a point) re-negotiate active sessions and reduce their + * slot usage to make rooom for new connections. For now we just fail the + * create session. + */ +static int set_forechannel_maxreqs(struct nfsd4_channel_attrs *fchan) +{ + int status = 0, np = fchan->maxreqs * NFSD_PAGES_PER_SLOT; + + spin_lock(&nfsd_serv->sv_lock); + if (np + nfsd_serv->sv_drc_pages_used > nfsd_serv->sv_drc_max_pages) + np = nfsd_serv->sv_drc_max_pages - nfsd_serv->sv_drc_pages_used; + nfsd_serv->sv_drc_pages_used += np; + spin_unlock(&nfsd_serv->sv_lock); + + if (np <= 0) { + status = nfserr_resource; + fchan->maxreqs = 0; + } else + fchan->maxreqs = np / NFSD_PAGES_PER_SLOT; + + return status; +} + +/* + * fchan holds the client values on input, and the server values on output + */ +static int init_forechannel_attrs(struct svc_rqst *rqstp, + struct nfsd4_session *session, + struct nfsd4_channel_attrs *fchan) +{ + int status = 0; + __u32 maxcount = svc_max_payload(rqstp); + + /* headerpadsz set to zero in encode routine */ + + /* Use the client's max request and max response size if possible */ + if (fchan->maxreq_sz > maxcount) + fchan->maxreq_sz = maxcount; + session->se_fmaxreq_sz = fchan->maxreq_sz; + + if (fchan->maxresp_sz > maxcount) + fchan->maxresp_sz = maxcount; + session->se_fmaxresp_sz = fchan->maxresp_sz; + + /* Set the max response cached size our default which is + * a multiple of PAGE_SIZE and small */ + session->se_fmaxresp_cached = NFSD_PAGES_PER_SLOT * PAGE_SIZE; + fchan->maxresp_cached = session->se_fmaxresp_cached; + + /* Use the client's maxops if possible */ + if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND) + fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND; + session->se_fmaxops = fchan->maxops; + + /* try to use the client requested number of slots */ + if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION) + fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION; + + /* FIXME: Error means no more DRC pages so the server should + * recover pages from existing sessions. For now fail session + * creation. + */ + status = set_forechannel_maxreqs(fchan); + + session->se_fnumslots = fchan->maxreqs; + return status; +} + +static int +alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, + struct nfsd4_create_session *cses) +{ + struct nfsd4_session *new, tmp; + int idx, status = nfserr_resource, slotsize; + + memset(&tmp, 0, sizeof(tmp)); + + /* FIXME: For now, we just accept the client back channel attributes. */ + status = init_forechannel_attrs(rqstp, &tmp, &cses->fore_channel); + if (status) + goto out; + + /* allocate struct nfsd4_session and slot table in one piece */ + slotsize = tmp.se_fnumslots * sizeof(struct nfsd4_slot); + new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL); + if (!new) + goto out; + + memcpy(new, &tmp, sizeof(*new)); + + new->se_client = clp; + gen_sessionid(new); + idx = hash_sessionid(&new->se_sessionid); + memcpy(clp->cl_sessionid.data, new->se_sessionid.data, + NFS4_MAX_SESSIONID_LEN); + + new->se_flags = cses->flags; + kref_init(&new->se_ref); + spin_lock(&sessionid_lock); + list_add(&new->se_hash, &sessionid_hashtbl[idx]); + list_add(&new->se_perclnt, &clp->cl_sessions); + spin_unlock(&sessionid_lock); + + status = nfs_ok; +out: + return status; +} + +/* caller must hold sessionid_lock */ +static struct nfsd4_session * +find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid) +{ + struct nfsd4_session *elem; + int idx; + + dump_sessionid(__func__, sessionid); + idx = hash_sessionid(sessionid); + dprintk("%s: idx is %d\n", __func__, idx); + /* Search in the appropriate list */ + list_for_each_entry(elem, &sessionid_hashtbl[idx], se_hash) { + dump_sessionid("list traversal", &elem->se_sessionid); + if (!memcmp(elem->se_sessionid.data, sessionid->data, + NFS4_MAX_SESSIONID_LEN)) { + return elem; + } + } + + dprintk("%s: session not found\n", __func__); + return NULL; +} + +/* caller must hold sessionid_lock */ +static void +unhash_session(struct nfsd4_session *ses) +{ + list_del(&ses->se_hash); + list_del(&ses->se_perclnt); +} + +static void +release_session(struct nfsd4_session *ses) +{ + spin_lock(&sessionid_lock); + unhash_session(ses); + spin_unlock(&sessionid_lock); + nfsd4_put_session(ses); +} + +static void nfsd4_release_respages(struct page **respages, short resused); + +void +free_session(struct kref *kref) +{ + struct nfsd4_session *ses; + int i; + + ses = container_of(kref, struct nfsd4_session, se_ref); + for (i = 0; i < ses->se_fnumslots; i++) { + struct nfsd4_cache_entry *e = &ses->se_slots[i].sl_cache_entry; + nfsd4_release_respages(e->ce_respages, e->ce_resused); + } + kfree(ses->se_slots); + kfree(ses); +} + static inline void renew_client(struct nfs4_client *clp) { @@ -324,8 +603,8 @@ STALE_CLIENTID(clientid_t *clid) { if (clid->cl_boot == boot_time) return 0; - dprintk("NFSD stale clientid (%08x/%08x)\n", - clid->cl_boot, clid->cl_id); + dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n", + clid->cl_boot, clid->cl_id, boot_time); return 1; } @@ -334,29 +613,47 @@ STALE_CLIENTID(clientid_t *clid) * This type of memory management is somewhat inefficient, but we use it * anyway since SETCLIENTID is not a common operation. */ -static inline struct nfs4_client * -alloc_client(struct xdr_netobj name) +static struct nfs4_client *alloc_client(struct xdr_netobj name) { struct nfs4_client *clp; - if ((clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL))!= NULL) { - if ((clp->cl_name.data = kmalloc(name.len, GFP_KERNEL)) != NULL) { - memcpy(clp->cl_name.data, name.data, name.len); - clp->cl_name.len = name.len; - } - else { - kfree(clp); - clp = NULL; - } + clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL); + if (clp == NULL) + return NULL; + clp->cl_name.data = kmalloc(name.len, GFP_KERNEL); + if (clp->cl_name.data == NULL) { + kfree(clp); + return NULL; } + memcpy(clp->cl_name.data, name.data, name.len); + clp->cl_name.len = name.len; return clp; } +static void +shutdown_callback_client(struct nfs4_client *clp) +{ + struct rpc_clnt *clnt = clp->cl_callback.cb_client; + + if (clnt) { + /* + * Callback threads take a reference on the client, so there + * should be no outstanding callbacks at this point. + */ + clp->cl_callback.cb_client = NULL; + rpc_shutdown_client(clnt); + } +} + static inline void free_client(struct nfs4_client *clp) { + shutdown_callback_client(clp); + nfsd4_release_respages(clp->cl_slot.sl_cache_entry.ce_respages, + clp->cl_slot.sl_cache_entry.ce_resused); if (clp->cl_cred.cr_group_info) put_group_info(clp->cl_cred.cr_group_info); + kfree(clp->cl_principal); kfree(clp->cl_name.data); kfree(clp); } @@ -369,19 +666,6 @@ put_nfs4_client(struct nfs4_client *clp) } static void -shutdown_callback_client(struct nfs4_client *clp) -{ - struct rpc_clnt *clnt = clp->cl_callback.cb_client; - - /* shutdown rpc client, ending any outstanding recall rpcs */ - if (clnt) { - clp->cl_callback.cb_client = NULL; - rpc_shutdown_client(clnt); - rpciod_down(); - } -} - -static void expire_client(struct nfs4_client *clp) { struct nfs4_stateowner *sop; @@ -391,8 +675,6 @@ expire_client(struct nfs4_client *clp) dprintk("NFSD: expire_client cl_count %d\n", atomic_read(&clp->cl_count)); - shutdown_callback_client(clp); - INIT_LIST_HEAD(&reaplist); spin_lock(&recall_lock); while (!list_empty(&clp->cl_delegations)) { @@ -413,17 +695,24 @@ expire_client(struct nfs4_client *clp) list_del(&clp->cl_lru); while (!list_empty(&clp->cl_openowners)) { sop = list_entry(clp->cl_openowners.next, struct nfs4_stateowner, so_perclient); - release_stateowner(sop); + release_openowner(sop); + } + while (!list_empty(&clp->cl_sessions)) { + struct nfsd4_session *ses; + ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, + se_perclnt); + release_session(ses); } put_nfs4_client(clp); } -static struct nfs4_client * -create_client(struct xdr_netobj name, char *recdir) { +static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir) +{ struct nfs4_client *clp; - if (!(clp = alloc_client(name))) - goto out; + clp = alloc_client(name); + if (clp == NULL) + return NULL; memcpy(clp->cl_recdir, recdir, HEXDIR_LEN); atomic_set(&clp->cl_count, 1); atomic_set(&clp->cl_callback.cb_set, 0); @@ -431,78 +720,79 @@ create_client(struct xdr_netobj name, char *recdir) { INIT_LIST_HEAD(&clp->cl_strhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); + INIT_LIST_HEAD(&clp->cl_sessions); INIT_LIST_HEAD(&clp->cl_lru); -out: return clp; } -static void -copy_verf(struct nfs4_client *target, nfs4_verifier *source) { - memcpy(target->cl_verifier.data, source->data, sizeof(target->cl_verifier.data)); +static void copy_verf(struct nfs4_client *target, nfs4_verifier *source) +{ + memcpy(target->cl_verifier.data, source->data, + sizeof(target->cl_verifier.data)); } -static void -copy_clid(struct nfs4_client *target, struct nfs4_client *source) { +static void copy_clid(struct nfs4_client *target, struct nfs4_client *source) +{ target->cl_clientid.cl_boot = source->cl_clientid.cl_boot; target->cl_clientid.cl_id = source->cl_clientid.cl_id; } -static void -copy_cred(struct svc_cred *target, struct svc_cred *source) { - +static void copy_cred(struct svc_cred *target, struct svc_cred *source) +{ target->cr_uid = source->cr_uid; target->cr_gid = source->cr_gid; target->cr_group_info = source->cr_group_info; get_group_info(target->cr_group_info); } -static inline int -same_name(const char *n1, const char *n2) { +static int same_name(const char *n1, const char *n2) +{ return 0 == memcmp(n1, n2, HEXDIR_LEN); } static int -cmp_verf(nfs4_verifier *v1, nfs4_verifier *v2) { - return(!memcmp(v1->data,v2->data,sizeof(v1->data))); +same_verf(nfs4_verifier *v1, nfs4_verifier *v2) +{ + return 0 == memcmp(v1->data, v2->data, sizeof(v1->data)); } static int -cmp_clid(clientid_t * cl1, clientid_t * cl2) { - return((cl1->cl_boot == cl2->cl_boot) && - (cl1->cl_id == cl2->cl_id)); +same_clid(clientid_t *cl1, clientid_t *cl2) +{ + return (cl1->cl_boot == cl2->cl_boot) && (cl1->cl_id == cl2->cl_id); } /* XXX what about NGROUP */ static int -cmp_creds(struct svc_cred *cr1, struct svc_cred *cr2){ - return(cr1->cr_uid == cr2->cr_uid); - +same_creds(struct svc_cred *cr1, struct svc_cred *cr2) +{ + return cr1->cr_uid == cr2->cr_uid; } -static void -gen_clid(struct nfs4_client *clp) { +static void gen_clid(struct nfs4_client *clp) +{ + static u32 current_clientid = 1; + clp->cl_clientid.cl_boot = boot_time; clp->cl_clientid.cl_id = current_clientid++; } -static void -gen_confirm(struct nfs4_client *clp) { - struct timespec tv; - u32 * p; +static void gen_confirm(struct nfs4_client *clp) +{ + static u32 i; + u32 *p; - tv = CURRENT_TIME; p = (u32 *)clp->cl_confirm.data; - *p++ = tv.tv_sec; - *p++ = tv.tv_nsec; + *p++ = get_seconds(); + *p++ = i++; } -static int -check_name(struct xdr_netobj name) { - +static int check_name(struct xdr_netobj name) +{ if (name.len == 0) return 0; if (name.len > NFS4_OPAQUE_LIMIT) { - printk("NFSD: check_name: name too long(%d)!\n", name.len); + dprintk("NFSD: check_name: name too long(%d)!\n", name.len); return 0; } return 1; @@ -541,7 +831,7 @@ find_confirmed_client(clientid_t *clid) unsigned int idhashval = clientid_hashval(clid->cl_id); list_for_each_entry(clp, &conf_id_hashtbl[idhashval], cl_idhash) { - if (cmp_clid(&clp->cl_clientid, clid)) + if (same_clid(&clp->cl_clientid, clid)) return clp; } return NULL; @@ -554,31 +844,51 @@ find_unconfirmed_client(clientid_t *clid) unsigned int idhashval = clientid_hashval(clid->cl_id); list_for_each_entry(clp, &unconf_id_hashtbl[idhashval], cl_idhash) { - if (cmp_clid(&clp->cl_clientid, clid)) + if (same_clid(&clp->cl_clientid, clid)) return clp; } return NULL; } +/* + * Return 1 iff clp's clientid establishment method matches the use_exchange_id + * parameter. Matching is based on the fact the at least one of the + * EXCHGID4_FLAG_USE_{NON_PNFS,PNFS_MDS,PNFS_DS} flags must be set for v4.1 + * + * FIXME: we need to unify the clientid namespaces for nfsv4.x + * and correctly deal with client upgrade/downgrade in EXCHANGE_ID + * and SET_CLIENTID{,_CONFIRM} + */ +static inline int +match_clientid_establishment(struct nfs4_client *clp, bool use_exchange_id) +{ + bool has_exchange_flags = (clp->cl_exchange_flags != 0); + return use_exchange_id == has_exchange_flags; +} + static struct nfs4_client * -find_confirmed_client_by_str(const char *dname, unsigned int hashval) +find_confirmed_client_by_str(const char *dname, unsigned int hashval, + bool use_exchange_id) { struct nfs4_client *clp; list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) { - if (same_name(clp->cl_recdir, dname)) + if (same_name(clp->cl_recdir, dname) && + match_clientid_establishment(clp, use_exchange_id)) return clp; } return NULL; } static struct nfs4_client * -find_unconfirmed_client_by_str(const char *dname, unsigned int hashval) +find_unconfirmed_client_by_str(const char *dname, unsigned int hashval, + bool use_exchange_id) { struct nfs4_client *clp; list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) { - if (same_name(clp->cl_recdir, dname)) + if (same_name(clp->cl_recdir, dname) && + match_clientid_establishment(clp, use_exchange_id)) return clp; } return NULL; @@ -677,39 +987,534 @@ out_err: return; } +void +nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp) +{ + struct nfsd4_compoundres *resp = rqstp->rq_resp; + + resp->cstate.statp = statp; +} + /* - * RFC 3010 has a complex implmentation description of processing a - * SETCLIENTID request consisting of 5 bullets, labeled as - * CASE0 - CASE4 below. - * - * NOTES: - * callback information will be processed in a future patch - * - * an unconfirmed record is added when: - * NORMAL (part of CASE 4): there is no confirmed nor unconfirmed record. - * CASE 1: confirmed record found with matching name, principal, - * verifier, and clientid. - * CASE 2: confirmed record found with matching name, principal, - * and there is no unconfirmed record with matching - * name and principal - * - * an unconfirmed record is replaced when: - * CASE 3: confirmed record found with matching name, principal, - * and an unconfirmed record is found with matching - * name, principal, and with clientid and - * confirm that does not match the confirmed record. - * CASE 4: there is no confirmed record with matching name and - * principal. there is an unconfirmed record with - * matching name, principal. - * - * an unconfirmed record is deleted when: - * CASE 1: an unconfirmed record that matches input name, verifier, - * and confirmed clientid. - * CASE 4: any unconfirmed records with matching name and principal - * that exist after an unconfirmed record has been replaced - * as described above. + * Dereference the result pages. + */ +static void +nfsd4_release_respages(struct page **respages, short resused) +{ + int i; + + dprintk("--> %s\n", __func__); + for (i = 0; i < resused; i++) { + if (!respages[i]) + continue; + put_page(respages[i]); + respages[i] = NULL; + } +} + +static void +nfsd4_copy_pages(struct page **topages, struct page **frompages, short count) +{ + int i; + + for (i = 0; i < count; i++) { + topages[i] = frompages[i]; + if (!topages[i]) + continue; + get_page(topages[i]); + } +} + +/* + * Cache the reply pages up to NFSD_PAGES_PER_SLOT + 1, clearing the previous + * pages. We add a page to NFSD_PAGES_PER_SLOT for the case where the total + * length of the XDR response is less than se_fmaxresp_cached + * (NFSD_PAGES_PER_SLOT * PAGE_SIZE) but the xdr_buf pages is used for a + * of the reply (e.g. readdir). * + * Store the base and length of the rq_req.head[0] page + * of the NFSv4.1 data, just past the rpc header. */ +void +nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) +{ + struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry; + struct svc_rqst *rqstp = resp->rqstp; + struct nfsd4_compoundargs *args = rqstp->rq_argp; + struct nfsd4_op *op = &args->ops[resp->opcnt]; + struct kvec *resv = &rqstp->rq_res.head[0]; + + dprintk("--> %s entry %p\n", __func__, entry); + + /* Don't cache a failed OP_SEQUENCE. */ + if (resp->opcnt == 1 && op->opnum == OP_SEQUENCE && resp->cstate.status) + return; + + nfsd4_release_respages(entry->ce_respages, entry->ce_resused); + entry->ce_opcnt = resp->opcnt; + entry->ce_status = resp->cstate.status; + + /* + * Don't need a page to cache just the sequence operation - the slot + * does this for us! + */ + + if (nfsd4_not_cached(resp)) { + entry->ce_resused = 0; + entry->ce_rpchdrlen = 0; + dprintk("%s Just cache SEQUENCE. ce_cachethis %d\n", __func__, + resp->cstate.slot->sl_cache_entry.ce_cachethis); + return; + } + entry->ce_resused = rqstp->rq_resused; + if (entry->ce_resused > NFSD_PAGES_PER_SLOT + 1) + entry->ce_resused = NFSD_PAGES_PER_SLOT + 1; + nfsd4_copy_pages(entry->ce_respages, rqstp->rq_respages, + entry->ce_resused); + entry->ce_datav.iov_base = resp->cstate.statp; + entry->ce_datav.iov_len = resv->iov_len - ((char *)resp->cstate.statp - + (char *)page_address(rqstp->rq_respages[0])); + /* Current request rpc header length*/ + entry->ce_rpchdrlen = (char *)resp->cstate.statp - + (char *)page_address(rqstp->rq_respages[0]); +} + +/* + * We keep the rpc header, but take the nfs reply from the replycache. + */ +static int +nfsd41_copy_replay_data(struct nfsd4_compoundres *resp, + struct nfsd4_cache_entry *entry) +{ + struct svc_rqst *rqstp = resp->rqstp; + struct kvec *resv = &resp->rqstp->rq_res.head[0]; + int len; + + /* Current request rpc header length*/ + len = (char *)resp->cstate.statp - + (char *)page_address(rqstp->rq_respages[0]); + if (entry->ce_datav.iov_len + len > PAGE_SIZE) { + dprintk("%s v41 cached reply too large (%Zd).\n", __func__, + entry->ce_datav.iov_len); + return 0; + } + /* copy the cached reply nfsd data past the current rpc header */ + memcpy((char *)resv->iov_base + len, entry->ce_datav.iov_base, + entry->ce_datav.iov_len); + resv->iov_len = len + entry->ce_datav.iov_len; + return 1; +} + +/* + * Keep the first page of the replay. Copy the NFSv4.1 data from the first + * cached page. Replace any futher replay pages from the cache. + */ +__be32 +nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, + struct nfsd4_sequence *seq) +{ + struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry; + __be32 status; + + dprintk("--> %s entry %p\n", __func__, entry); + + /* + * If this is just the sequence operation, we did not keep + * a page in the cache entry because we can just use the + * slot info stored in struct nfsd4_sequence that was checked + * against the slot in nfsd4_sequence(). + * + * This occurs when seq->cachethis is FALSE, or when the client + * session inactivity timer fires and a solo sequence operation + * is sent (lease renewal). + */ + if (seq && nfsd4_not_cached(resp)) { + seq->maxslots = resp->cstate.session->se_fnumslots; + return nfs_ok; + } + + if (!nfsd41_copy_replay_data(resp, entry)) { + /* + * Not enough room to use the replay rpc header, send the + * cached header. Release all the allocated result pages. + */ + svc_free_res_pages(resp->rqstp); + nfsd4_copy_pages(resp->rqstp->rq_respages, entry->ce_respages, + entry->ce_resused); + } else { + /* Release all but the first allocated result page */ + + resp->rqstp->rq_resused--; + svc_free_res_pages(resp->rqstp); + + nfsd4_copy_pages(&resp->rqstp->rq_respages[1], + &entry->ce_respages[1], + entry->ce_resused - 1); + } + + resp->rqstp->rq_resused = entry->ce_resused; + resp->opcnt = entry->ce_opcnt; + resp->cstate.iovlen = entry->ce_datav.iov_len + entry->ce_rpchdrlen; + status = entry->ce_status; + + return status; +} + +/* + * Set the exchange_id flags returned by the server. + */ +static void +nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) +{ + /* pNFS is not supported */ + new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS; + + /* Referrals are supported, Migration is not. */ + new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER; + + /* set the wire flags to return to client. */ + clid->flags = new->cl_exchange_flags; +} + +__be32 +nfsd4_exchange_id(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_exchange_id *exid) +{ + struct nfs4_client *unconf, *conf, *new; + int status; + unsigned int strhashval; + char dname[HEXDIR_LEN]; + nfs4_verifier verf = exid->verifier; + u32 ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr; + + dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p " + " ip_addr=%u flags %x, spa_how %d\n", + __func__, rqstp, exid, exid->clname.len, exid->clname.data, + ip_addr, exid->flags, exid->spa_how); + + if (!check_name(exid->clname) || (exid->flags & ~EXCHGID4_FLAG_MASK_A)) + return nfserr_inval; + + /* Currently only support SP4_NONE */ + switch (exid->spa_how) { + case SP4_NONE: + break; + case SP4_SSV: + return nfserr_encr_alg_unsupp; + default: + BUG(); /* checked by xdr code */ + case SP4_MACH_CRED: + return nfserr_serverfault; /* no excuse :-/ */ + } + + status = nfs4_make_rec_clidname(dname, &exid->clname); + + if (status) + goto error; + + strhashval = clientstr_hashval(dname); + + nfs4_lock_state(); + status = nfs_ok; + + conf = find_confirmed_client_by_str(dname, strhashval, true); + if (conf) { + if (!same_verf(&verf, &conf->cl_verifier)) { + /* 18.35.4 case 8 */ + if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + status = nfserr_not_same; + goto out; + } + /* Client reboot: destroy old state */ + expire_client(conf); + goto out_new; + } + if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { + /* 18.35.4 case 9 */ + if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + status = nfserr_perm; + goto out; + } + expire_client(conf); + goto out_new; + } + if (ip_addr != conf->cl_addr && + !(exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A)) { + /* Client collision. 18.35.4 case 3 */ + status = nfserr_clid_inuse; + goto out; + } + /* + * Set bit when the owner id and verifier map to an already + * confirmed client id (18.35.3). + */ + exid->flags |= EXCHGID4_FLAG_CONFIRMED_R; + + /* + * Falling into 18.35.4 case 2, possible router replay. + * Leave confirmed record intact and return same result. + */ + copy_verf(conf, &verf); + new = conf; + goto out_copy; + } else { + /* 18.35.4 case 7 */ + if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + status = nfserr_noent; + goto out; + } + } + + unconf = find_unconfirmed_client_by_str(dname, strhashval, true); + if (unconf) { + /* + * Possible retry or client restart. Per 18.35.4 case 4, + * a new unconfirmed record should be generated regardless + * of whether any properties have changed. + */ + expire_client(unconf); + } + +out_new: + /* Normal case */ + new = create_client(exid->clname, dname); + if (new == NULL) { + status = nfserr_resource; + goto out; + } + + copy_verf(new, &verf); + copy_cred(&new->cl_cred, &rqstp->rq_cred); + new->cl_addr = ip_addr; + gen_clid(new); + gen_confirm(new); + add_to_unconfirmed(new, strhashval); +out_copy: + exid->clientid.cl_boot = new->cl_clientid.cl_boot; + exid->clientid.cl_id = new->cl_clientid.cl_id; + + new->cl_slot.sl_seqid = 0; + exid->seqid = 1; + nfsd4_set_ex_flags(new, exid); + + dprintk("nfsd4_exchange_id seqid %d flags %x\n", + new->cl_slot.sl_seqid, new->cl_exchange_flags); + status = nfs_ok; + +out: + nfs4_unlock_state(); +error: + dprintk("nfsd4_exchange_id returns %d\n", ntohl(status)); + return status; +} + +static int +check_slot_seqid(u32 seqid, struct nfsd4_slot *slot) +{ + dprintk("%s enter. seqid %d slot->sl_seqid %d\n", __func__, seqid, + slot->sl_seqid); + + /* The slot is in use, and no response has been sent. */ + if (slot->sl_inuse) { + if (seqid == slot->sl_seqid) + return nfserr_jukebox; + else + return nfserr_seq_misordered; + } + /* Normal */ + if (likely(seqid == slot->sl_seqid + 1)) + return nfs_ok; + /* Replay */ + if (seqid == slot->sl_seqid) + return nfserr_replay_cache; + /* Wraparound */ + if (seqid == 1 && (slot->sl_seqid + 1) == 0) + return nfs_ok; + /* Misordered replay or misordered new request */ + return nfserr_seq_misordered; +} + +__be32 +nfsd4_create_session(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_create_session *cr_ses) +{ + u32 ip_addr = svc_addr_in(rqstp)->sin_addr.s_addr; + struct nfsd4_compoundres *resp = rqstp->rq_resp; + struct nfs4_client *conf, *unconf; + struct nfsd4_slot *slot = NULL; + int status = 0; + + nfs4_lock_state(); + unconf = find_unconfirmed_client(&cr_ses->clientid); + conf = find_confirmed_client(&cr_ses->clientid); + + if (conf) { + slot = &conf->cl_slot; + status = check_slot_seqid(cr_ses->seqid, slot); + if (status == nfserr_replay_cache) { + dprintk("Got a create_session replay! seqid= %d\n", + slot->sl_seqid); + cstate->slot = slot; + cstate->status = status; + /* Return the cached reply status */ + status = nfsd4_replay_cache_entry(resp, NULL); + goto out; + } else if (cr_ses->seqid != conf->cl_slot.sl_seqid + 1) { + status = nfserr_seq_misordered; + dprintk("Sequence misordered!\n"); + dprintk("Expected seqid= %d but got seqid= %d\n", + slot->sl_seqid, cr_ses->seqid); + goto out; + } + conf->cl_slot.sl_seqid++; + } else if (unconf) { + if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || + (ip_addr != unconf->cl_addr)) { + status = nfserr_clid_inuse; + goto out; + } + + slot = &unconf->cl_slot; + status = check_slot_seqid(cr_ses->seqid, slot); + if (status) { + /* an unconfirmed replay returns misordered */ + status = nfserr_seq_misordered; + goto out; + } + + slot->sl_seqid++; /* from 0 to 1 */ + move_to_confirmed(unconf); + + /* + * We do not support RDMA or persistent sessions + */ + cr_ses->flags &= ~SESSION4_PERSIST; + cr_ses->flags &= ~SESSION4_RDMA; + + conf = unconf; + } else { + status = nfserr_stale_clientid; + goto out; + } + + status = alloc_init_session(rqstp, conf, cr_ses); + if (status) + goto out; + + memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data, + NFS4_MAX_SESSIONID_LEN); + cr_ses->seqid = slot->sl_seqid; + + slot->sl_inuse = true; + cstate->slot = slot; + /* Ensure a page is used for the cache */ + slot->sl_cache_entry.ce_cachethis = 1; +out: + nfs4_unlock_state(); + dprintk("%s returns %d\n", __func__, ntohl(status)); + return status; +} + +__be32 +nfsd4_destroy_session(struct svc_rqst *r, + struct nfsd4_compound_state *cstate, + struct nfsd4_destroy_session *sessionid) +{ + struct nfsd4_session *ses; + u32 status = nfserr_badsession; + + /* Notes: + * - The confirmed nfs4_client->cl_sessionid holds destroyed sessinid + * - Should we return nfserr_back_chan_busy if waiting for + * callbacks on to-be-destroyed session? + * - Do we need to clear any callback info from previous session? + */ + + dump_sessionid(__func__, &sessionid->sessionid); + spin_lock(&sessionid_lock); + ses = find_in_sessionid_hashtbl(&sessionid->sessionid); + if (!ses) { + spin_unlock(&sessionid_lock); + goto out; + } + + unhash_session(ses); + spin_unlock(&sessionid_lock); + + /* wait for callbacks */ + shutdown_callback_client(ses->se_client); + nfsd4_put_session(ses); + status = nfs_ok; +out: + dprintk("%s returns %d\n", __func__, ntohl(status)); + return status; +} + +__be32 +nfsd4_sequence(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_sequence *seq) +{ + struct nfsd4_compoundres *resp = rqstp->rq_resp; + struct nfsd4_session *session; + struct nfsd4_slot *slot; + int status; + + if (resp->opcnt != 1) + return nfserr_sequence_pos; + + spin_lock(&sessionid_lock); + status = nfserr_badsession; + session = find_in_sessionid_hashtbl(&seq->sessionid); + if (!session) + goto out; + + status = nfserr_badslot; + if (seq->slotid >= session->se_fnumslots) + goto out; + + slot = &session->se_slots[seq->slotid]; + dprintk("%s: slotid %d\n", __func__, seq->slotid); + + status = check_slot_seqid(seq->seqid, slot); + if (status == nfserr_replay_cache) { + cstate->slot = slot; + cstate->session = session; + /* Return the cached reply status and set cstate->status + * for nfsd4_svc_encode_compoundres processing */ + status = nfsd4_replay_cache_entry(resp, seq); + cstate->status = nfserr_replay_cache; + goto replay_cache; + } + if (status) + goto out; + + /* Success! bump slot seqid */ + slot->sl_inuse = true; + slot->sl_seqid = seq->seqid; + slot->sl_cache_entry.ce_cachethis = seq->cachethis; + /* Always set the cache entry cachethis for solo sequence */ + if (nfsd4_is_solo_sequence(resp)) + slot->sl_cache_entry.ce_cachethis = 1; + + cstate->slot = slot; + cstate->session = session; + +replay_cache: + /* Renew the clientid on success and on replay. + * Hold a session reference until done processing the compound: + * nfsd4_put_session called only if the cstate slot is set. + */ + renew_client(session->se_client); + nfsd4_get_session(session); +out: + spin_unlock(&sessionid_lock); + dprintk("%s: return %d\n", __func__, ntohl(status)); + return status; +} + __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_setclientid *setclid) @@ -723,6 +1528,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unsigned int strhashval; struct nfs4_client *conf, *unconf, *new; __be32 status; + char *princ; char dname[HEXDIR_LEN]; if (!check_name(clname)) @@ -740,53 +1546,38 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, strhashval = clientstr_hashval(dname); nfs4_lock_state(); - conf = find_confirmed_client_by_str(dname, strhashval); + conf = find_confirmed_client_by_str(dname, strhashval, false); if (conf) { - /* - * CASE 0: - * clname match, confirmed, different principal - * or different ip_address - */ + /* RFC 3530 14.2.33 CASE 0: */ status = nfserr_clid_inuse; - if (!cmp_creds(&conf->cl_cred, &rqstp->rq_cred) - || conf->cl_addr != sin->sin_addr.s_addr) { + if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { dprintk("NFSD: setclientid: string in use by client" - "at %u.%u.%u.%u\n", NIPQUAD(conf->cl_addr)); + " at %pI4\n", &conf->cl_addr); goto out; } } - unconf = find_unconfirmed_client_by_str(dname, strhashval); + /* + * section 14.2.33 of RFC 3530 (under the heading "IMPLEMENTATION") + * has a description of SETCLIENTID request processing consisting + * of 5 bullet points, labeled as CASE0 - CASE4 below. + */ + unconf = find_unconfirmed_client_by_str(dname, strhashval, false); status = nfserr_resource; if (!conf) { - /* - * CASE 4: - * placed first, because it is the normal case. + /* + * RFC 3530 14.2.33 CASE 4: + * placed first, because it is the normal case */ if (unconf) expire_client(unconf); new = create_client(clname, dname); if (new == NULL) goto out; - copy_verf(new, &clverifier); - new->cl_addr = sin->sin_addr.s_addr; - copy_cred(&new->cl_cred,&rqstp->rq_cred); gen_clid(new); - gen_confirm(new); - gen_callback(new, setclid); - add_to_unconfirmed(new, strhashval); - } else if (cmp_verf(&conf->cl_verifier, &clverifier)) { + } else if (same_verf(&conf->cl_verifier, &clverifier)) { /* - * CASE 1: - * cl_name match, confirmed, principal match - * verifier match: probable callback update - * - * remove any unconfirmed nfs4_client with - * matching cl_name, cl_verifier, and cl_clientid - * - * create and insert an unconfirmed nfs4_client with same - * cl_name, cl_verifier, and cl_clientid as existing - * nfs4_client, but with the new callback info and a - * new cl_confirm + * RFC 3530 14.2.33 CASE 1: + * probable callback update */ if (unconf) { /* Note this is removing unconfirmed {*x***}, @@ -799,65 +1590,44 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, new = create_client(clname, dname); if (new == NULL) goto out; - copy_verf(new,&conf->cl_verifier); - new->cl_addr = sin->sin_addr.s_addr; - copy_cred(&new->cl_cred,&rqstp->rq_cred); copy_clid(new, conf); - gen_confirm(new); - gen_callback(new, setclid); - add_to_unconfirmed(new,strhashval); } else if (!unconf) { /* - * CASE 2: - * clname match, confirmed, principal match - * verfier does not match - * no unconfirmed. create a new unconfirmed nfs4_client - * using input clverifier, clname, and callback info - * and generate a new cl_clientid and cl_confirm. + * RFC 3530 14.2.33 CASE 2: + * probable client reboot; state will be removed if + * confirmed. */ new = create_client(clname, dname); if (new == NULL) goto out; - copy_verf(new,&clverifier); - new->cl_addr = sin->sin_addr.s_addr; - copy_cred(&new->cl_cred,&rqstp->rq_cred); gen_clid(new); - gen_confirm(new); - gen_callback(new, setclid); - add_to_unconfirmed(new, strhashval); - } else if (!cmp_verf(&conf->cl_confirm, &unconf->cl_confirm)) { - /* - * CASE3: - * confirmed found (name, principal match) - * confirmed verifier does not match input clverifier - * - * unconfirmed found (name match) - * confirmed->cl_confirm != unconfirmed->cl_confirm - * - * remove unconfirmed. - * - * create an unconfirmed nfs4_client - * with same cl_name as existing confirmed nfs4_client, - * but with new callback info, new cl_clientid, - * new cl_verifier and a new cl_confirm + } else { + /* + * RFC 3530 14.2.33 CASE 3: + * probable client reboot; state will be removed if + * confirmed. */ expire_client(unconf); new = create_client(clname, dname); if (new == NULL) goto out; - copy_verf(new,&clverifier); - new->cl_addr = sin->sin_addr.s_addr; - copy_cred(&new->cl_cred,&rqstp->rq_cred); gen_clid(new); - gen_confirm(new); - gen_callback(new, setclid); - add_to_unconfirmed(new, strhashval); - } else { - /* No cases hit !!! */ - status = nfserr_inval; - goto out; - } + copy_verf(new, &clverifier); + new->cl_addr = sin->sin_addr.s_addr; + new->cl_flavor = rqstp->rq_flavor; + princ = svc_gss_principal(rqstp); + if (princ) { + new->cl_principal = kstrdup(princ, GFP_KERNEL); + if (new->cl_principal == NULL) { + free_client(new); + goto out; + } + } + copy_cred(&new->cl_cred, &rqstp->rq_cred); + gen_confirm(new); + gen_callback(new, setclid); + add_to_unconfirmed(new, strhashval); setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot; setclid->se_clientid.cl_id = new->cl_clientid.cl_id; memcpy(setclid->se_confirm.data, new->cl_confirm.data, sizeof(setclid->se_confirm.data)); @@ -869,11 +1639,9 @@ out: /* - * RFC 3010 has a complex implmentation description of processing a - * SETCLIENTID_CONFIRM request consisting of 4 bullets describing - * processing on a DRC miss, labeled as CASE1 - CASE4 below. - * - * NOTE: callback information will be processed here in a future patch + * Section 14.2.34 of RFC 3530 (under the heading "IMPLEMENTATION") has + * a description of SETCLIENTID_CONFIRM request processing consisting of 4 + * bullets, labeled as CASE1 - CASE4 below. */ __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, @@ -904,17 +1672,17 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, if (unconf && unconf->cl_addr != sin->sin_addr.s_addr) goto out; - if ((conf && unconf) && - (cmp_verf(&unconf->cl_confirm, &confirm)) && - (cmp_verf(&conf->cl_verifier, &unconf->cl_verifier)) && - (same_name(conf->cl_recdir,unconf->cl_recdir)) && - (!cmp_verf(&conf->cl_confirm, &unconf->cl_confirm))) { - /* CASE 1: - * unconf record that matches input clientid and input confirm. - * conf record that matches input clientid. - * conf and unconf records match names, verifiers - */ - if (!cmp_creds(&conf->cl_cred, &unconf->cl_cred)) + /* + * section 14.2.34 of RFC 3530 has a description of + * SETCLIENTID_CONFIRM request processing consisting + * of 4 bullet points, labeled as CASE1 - CASE4 below. + */ + if (conf && unconf && same_verf(&confirm, &unconf->cl_confirm)) { + /* + * RFC 3530 14.2.34 CASE 1: + * callback update + */ + if (!same_creds(&conf->cl_cred, &unconf->cl_cred)) status = nfserr_clid_inuse; else { /* XXX: We just turn off callbacks until we can handle @@ -926,50 +1694,44 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfs_ok; } - } else if ((conf && !unconf) || - ((conf && unconf) && - (!cmp_verf(&conf->cl_verifier, &unconf->cl_verifier) || - !same_name(conf->cl_recdir, unconf->cl_recdir)))) { - /* CASE 2: - * conf record that matches input clientid. - * if unconf record matches input clientid, then - * unconf->cl_name or unconf->cl_verifier don't match the - * conf record. + } else if (conf && !unconf) { + /* + * RFC 3530 14.2.34 CASE 2: + * probable retransmitted request; play it safe and + * do nothing. */ - if (!cmp_creds(&conf->cl_cred,&rqstp->rq_cred)) + if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) status = nfserr_clid_inuse; else status = nfs_ok; } else if (!conf && unconf - && cmp_verf(&unconf->cl_confirm, &confirm)) { - /* CASE 3: - * conf record not found. - * unconf record found. - * unconf->cl_confirm matches input confirm + && same_verf(&unconf->cl_confirm, &confirm)) { + /* + * RFC 3530 14.2.34 CASE 3: + * Normal case; new or rebooted client: */ - if (!cmp_creds(&unconf->cl_cred, &rqstp->rq_cred)) { + if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { status = nfserr_clid_inuse; } else { unsigned int hash = clientstr_hashval(unconf->cl_recdir); conf = find_confirmed_client_by_str(unconf->cl_recdir, - hash); + hash, false); if (conf) { nfsd4_remove_clid_dir(conf); expire_client(conf); } move_to_confirmed(unconf); conf = unconf; + nfsd4_probe_callback(conf); status = nfs_ok; } - } else if ((!conf || (conf && !cmp_verf(&conf->cl_confirm, &confirm))) - && (!unconf || (unconf && !cmp_verf(&unconf->cl_confirm, + } else if ((!conf || (conf && !same_verf(&conf->cl_confirm, &confirm))) + && (!unconf || (unconf && !same_verf(&unconf->cl_confirm, &confirm)))) { - /* CASE 4: - * conf record not found, or if conf, conf->cl_confirm does not - * match input confirm. - * unconf record not found, or if unconf, unconf->cl_confirm - * does not match input confirm. + /* + * RFC 3530 14.2.34 CASE 4: + * Client probably hasn't noticed that we rebooted yet. */ status = nfserr_stale_clientid; } else { @@ -977,8 +1739,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; } out: - if (!status) - nfsd4_probe_callback(conf); nfs4_unlock_state(); return status; } @@ -992,13 +1752,16 @@ alloc_init_file(struct inode *ino) fp = kmem_cache_alloc(file_slab, GFP_KERNEL); if (fp) { - kref_init(&fp->fi_ref); + atomic_set(&fp->fi_ref, 1); INIT_LIST_HEAD(&fp->fi_hash); INIT_LIST_HEAD(&fp->fi_stateids); INIT_LIST_HEAD(&fp->fi_delegations); + spin_lock(&recall_lock); list_add(&fp->fi_hash, &file_hashtbl[hashval]); + spin_unlock(&recall_lock); fp->fi_inode = igrab(ino); fp->fi_id = current_fileid++; + fp->fi_had_conflict = false; return fp; } return NULL; @@ -1013,7 +1776,7 @@ nfsd4_free_slab(struct kmem_cache **slab) *slab = NULL; } -static void +void nfsd4_free_slabs(void) { nfsd4_free_slab(&stateowner_slab); @@ -1026,19 +1789,19 @@ static int nfsd4_init_slabs(void) { stateowner_slab = kmem_cache_create("nfsd4_stateowners", - sizeof(struct nfs4_stateowner), 0, 0, NULL, NULL); + sizeof(struct nfs4_stateowner), 0, 0, NULL); if (stateowner_slab == NULL) goto out_nomem; file_slab = kmem_cache_create("nfsd4_files", - sizeof(struct nfs4_file), 0, 0, NULL, NULL); + sizeof(struct nfs4_file), 0, 0, NULL); if (file_slab == NULL) goto out_nomem; stateid_slab = kmem_cache_create("nfsd4_stateids", - sizeof(struct nfs4_stateid), 0, 0, NULL, NULL); + sizeof(struct nfs4_stateid), 0, 0, NULL); if (stateid_slab == NULL) goto out_nomem; deleg_slab = kmem_cache_create("nfsd4_delegations", - sizeof(struct nfs4_delegation), 0, 0, NULL, NULL); + sizeof(struct nfs4_delegation), 0, 0, NULL); if (deleg_slab == NULL) goto out_nomem; return 0; @@ -1105,48 +1868,6 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp, str return sop; } -static void -release_stateid_lockowners(struct nfs4_stateid *open_stp) -{ - struct nfs4_stateowner *lock_sop; - - while (!list_empty(&open_stp->st_lockowners)) { - lock_sop = list_entry(open_stp->st_lockowners.next, - struct nfs4_stateowner, so_perstateid); - /* list_del(&open_stp->st_lockowners); */ - BUG_ON(lock_sop->so_is_open_owner); - release_stateowner(lock_sop); - } -} - -static void -unhash_stateowner(struct nfs4_stateowner *sop) -{ - struct nfs4_stateid *stp; - - list_del(&sop->so_idhash); - list_del(&sop->so_strhash); - if (sop->so_is_open_owner) - list_del(&sop->so_perclient); - list_del(&sop->so_perstateid); - while (!list_empty(&sop->so_stateids)) { - stp = list_entry(sop->so_stateids.next, - struct nfs4_stateid, st_perstateowner); - if (sop->so_is_open_owner) - release_stateid(stp, OPEN_STATE); - else - release_stateid(stp, LOCK_STATE); - } -} - -static void -release_stateowner(struct nfs4_stateowner *sop) -{ - unhash_stateowner(sop); - list_del(&sop->so_close_lru); - nfs4_put_stateowner(sop); -} - static inline void init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_stateowner *sop = open->op_stateowner; @@ -1162,36 +1883,19 @@ init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open * stp->st_stateowner = sop; get_nfs4_file(fp); stp->st_file = fp; - stp->st_stateid.si_boot = boot_time; + stp->st_stateid.si_boot = get_seconds(); stp->st_stateid.si_stateownerid = sop->so_id; stp->st_stateid.si_fileid = fp->fi_id; stp->st_stateid.si_generation = 0; stp->st_access_bmap = 0; stp->st_deny_bmap = 0; - __set_bit(open->op_share_access, &stp->st_access_bmap); + __set_bit(open->op_share_access & ~NFS4_SHARE_WANT_MASK, + &stp->st_access_bmap); __set_bit(open->op_share_deny, &stp->st_deny_bmap); stp->st_openstp = NULL; } static void -release_stateid(struct nfs4_stateid *stp, int flags) -{ - struct file *filp = stp->st_vfs_file; - - list_del(&stp->st_hash); - list_del(&stp->st_perfile); - list_del(&stp->st_perstateowner); - if (flags & OPEN_STATE) { - release_stateid_lockowners(stp); - stp->st_vfs_file = NULL; - nfsd_close(filp); - } else if (flags & LOCK_STATE) - locks_remove_posix(filp, (fl_owner_t) stp->st_stateowner); - put_nfs4_file(stp->st_file); - kmem_cache_free(stateid_slab, stp); -} - -static void move_to_close_lru(struct nfs4_stateowner *sop) { dprintk("NFSD: move_to_close_lru nfs4_stateowner %p\n", sop); @@ -1201,10 +1905,12 @@ move_to_close_lru(struct nfs4_stateowner *sop) } static int -cmp_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner, clientid_t *clid) { - return ((sop->so_owner.len == owner->len) && - !memcmp(sop->so_owner.data, owner->data, owner->len) && - (sop->so_client->cl_clientid.cl_id == clid->cl_id)); +same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner, + clientid_t *clid) +{ + return (sop->so_owner.len == owner->len) && + 0 == memcmp(sop->so_owner.data, owner->data, owner->len) && + (sop->so_client->cl_clientid.cl_id == clid->cl_id); } static struct nfs4_stateowner * @@ -1213,7 +1919,7 @@ find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open) struct nfs4_stateowner *so = NULL; list_for_each_entry(so, &ownerstr_hashtbl[hashval], so_strhash) { - if (cmp_owner_str(so, &open->op_owner, &open->op_clientid)) + if (same_owner_str(so, &open->op_owner, &open->op_clientid)) return so; } return NULL; @@ -1226,25 +1932,61 @@ find_file(struct inode *ino) unsigned int hashval = file_hashval(ino); struct nfs4_file *fp; + spin_lock(&recall_lock); list_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) { if (fp->fi_inode == ino) { get_nfs4_file(fp); + spin_unlock(&recall_lock); return fp; } } + spin_unlock(&recall_lock); return NULL; } -static int access_valid(u32 x) +static inline int access_valid(u32 x, u32 minorversion) { - return (x > 0 && x < 4); + if ((x & NFS4_SHARE_ACCESS_MASK) < NFS4_SHARE_ACCESS_READ) + return 0; + if ((x & NFS4_SHARE_ACCESS_MASK) > NFS4_SHARE_ACCESS_BOTH) + return 0; + x &= ~NFS4_SHARE_ACCESS_MASK; + if (minorversion && x) { + if ((x & NFS4_SHARE_WANT_MASK) > NFS4_SHARE_WANT_CANCEL) + return 0; + if ((x & NFS4_SHARE_WHEN_MASK) > NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED) + return 0; + x &= ~(NFS4_SHARE_WANT_MASK | NFS4_SHARE_WHEN_MASK); + } + if (x) + return 0; + return 1; } -static int deny_valid(u32 x) +static inline int deny_valid(u32 x) { - return (x >= 0 && x < 5); + /* Note: unlike access bits, deny bits may be zero. */ + return x <= NFS4_SHARE_DENY_BOTH; } +/* + * We store the NONE, READ, WRITE, and BOTH bits separately in the + * st_{access,deny}_bmap field of the stateid, in order to track not + * only what share bits are currently in force, but also what + * combinations of share bits previous opens have used. This allows us + * to enforce the recommendation of rfc 3530 14.2.19 that the server + * return an error if the client attempt to downgrade to a combination + * of share bits not explicable by closing some of its previous opens. + * + * XXX: This enforcement is actually incomplete, since we don't keep + * track of access/deny bit combinations; so, e.g., we allow: + * + * OPEN allow read, deny write + * OPEN allow both, deny none + * DOWNGRADE allow read, deny none + * + * which we should reject. + */ static void set_access(unsigned int *access, unsigned long bmap) { int i; @@ -1312,7 +2054,7 @@ static inline void nfs4_file_downgrade(struct file *filp, unsigned int share_access) { if (share_access & NFS4_SHARE_ACCESS_WRITE) { - put_write_access(filp->f_path.dentry->d_inode); + drop_file_write_access(filp); filp->f_mode = (filp->f_mode | FMODE_READ) & ~FMODE_WRITE; } } @@ -1325,8 +2067,7 @@ do_recall(void *__dp) { struct nfs4_delegation *dp = __dp; - daemonize("nfsv4-recall"); - + dp->dl_file->fi_had_conflict = true; nfsd4_cb_recall(dp); return 0; } @@ -1355,6 +2096,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl) * lock) we know the server hasn't removed the lease yet, we know * it's safe to take a reference: */ atomic_inc(&dp->dl_count); + atomic_inc(&dp->dl_client->cl_count); spin_lock(&recall_lock); list_add_tail(&dp->dl_recall_lru, &del_recall_lru); @@ -1363,8 +2105,12 @@ void nfsd_break_deleg_cb(struct file_lock *fl) /* only place dl_time is set. protected by lock_kernel*/ dp->dl_time = get_seconds(); - /* XXX need to merge NFSD_LEASE_TIME with fs/locks.c:lease_break_time */ - fl->fl_break_time = jiffies + NFSD_LEASE_TIME * HZ; + /* + * We don't want the locks code to timeout the lease for us; + * we'll remove it ourself if the delegation isn't returned + * in time. + */ + fl->fl_break_time = 0; t = kthread_run(do_recall, dp, "%s", "nfs4_cb_recall"); if (IS_ERR(t)) { @@ -1373,6 +2119,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl) printk(KERN_INFO "NFSD: Callback thread failed for " "for client (clientid %08x/%08x)\n", clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); + put_nfs4_client(dp->dl_client); nfs4_put_delegation(dp); } } @@ -1397,7 +2144,7 @@ void nfsd_release_deleg_cb(struct file_lock *fl) /* * Set the delegation file_lock back pointer. * - * Called from __setlease() with lock_kernel() held. + * Called from setlease() with lock_kernel() held. */ static void nfsd_copy_lock_deleg_cb(struct file_lock *new, struct file_lock *fl) @@ -1411,7 +2158,7 @@ void nfsd_copy_lock_deleg_cb(struct file_lock *new, struct file_lock *fl) } /* - * Called from __setlease() with lock_kernel() held + * Called from setlease() with lock_kernel() held */ static int nfsd_same_client_deleg_cb(struct file_lock *onlist, struct file_lock *try) @@ -1447,7 +2194,8 @@ static struct lock_manager_operations nfsd_lease_mng_ops = { __be32 -nfsd4_process_open1(struct nfsd4_open *open) +nfsd4_process_open1(struct nfsd4_compound_state *cstate, + struct nfsd4_open *open) { clientid_t *clientid = &open->op_clientid; struct nfs4_client *clp = NULL; @@ -1470,10 +2218,13 @@ nfsd4_process_open1(struct nfsd4_open *open) return nfserr_expired; goto renew; } + /* When sessions are used, skip open sequenceid processing */ + if (nfsd4_has_session(cstate)) + goto renew; if (!sop->so_confirmed) { /* Replace unconfirmed owners without checking for replay. */ clp = sop->so_client; - release_stateowner(sop); + release_openowner(sop); open->op_stateowner = NULL; goto renew; } @@ -1637,6 +2388,10 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta int err = get_write_access(inode); if (err) return nfserrno(err); + err = mnt_want_write(cur_fh->fh_export->ex_path.mnt); + if (err) + return nfserrno(err); + file_take_write(filp); } status = nfsd4_truncate(rqstp, cur_fh, open); if (status) { @@ -1646,8 +2401,8 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta } /* remember the open */ filp->f_mode |= open->op_share_access; - set_bit(open->op_share_access, &stp->st_access_bmap); - set_bit(open->op_share_deny, &stp->st_deny_bmap); + __set_bit(open->op_share_access, &stp->st_access_bmap); + __set_bit(open->op_share_deny, &stp->st_deny_bmap); return nfs_ok; } @@ -1685,7 +2440,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta case NFS4_OPEN_CLAIM_NULL: /* Let's not give out any delegations till everyone's * had the chance to reclaim theirs.... */ - if (nfs4_in_grace()) + if (locks_in_grace()) goto out; if (!atomic_read(&cb->cb_set) || !sop->so_confirmed) goto out; @@ -1706,16 +2461,16 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta locks_init_lock(&fl); fl.fl_lmops = &nfsd_lease_mng_ops; fl.fl_flags = FL_LEASE; + fl.fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; fl.fl_end = OFFSET_MAX; fl.fl_owner = (fl_owner_t)dp; fl.fl_file = stp->st_vfs_file; fl.fl_pid = current->tgid; - /* setlease checks to see if delegation should be handed out. + /* vfs_setlease checks to see if delegation should be handed out. * the lock_manager callbacks fl_mylease and fl_change are used */ - if ((status = setlease(stp->st_vfs_file, - flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK, &flp))) { + if ((status = vfs_setlease(stp->st_vfs_file, fl.fl_type, &flp))) { dprintk("NFSD: setlease failed [%d], no delegation\n", status); unhash_delegation(dp); flag = NFS4_OPEN_DELEGATE_NONE; @@ -1733,7 +2488,7 @@ out: if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && flag == NFS4_OPEN_DELEGATE_NONE && open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) - printk("NFSD: WARNING: refusing delegation reclaim\n"); + dprintk("NFSD: WARNING: refusing delegation reclaim\n"); open->op_delegate_type = flag; } @@ -1743,6 +2498,7 @@ out: __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfs4_file *fp = NULL; struct inode *ino = current_fh->fh_dentry->d_inode; struct nfs4_stateid *stp = NULL; @@ -1750,7 +2506,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf __be32 status; status = nfserr_inval; - if (!access_valid(open->op_share_access) + if (!access_valid(open->op_share_access, resp->cstate.minorversion) || !deny_valid(open->op_share_deny)) goto out; /* @@ -1789,21 +2545,26 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf /* Stateid was not found, this is a new OPEN */ int flags = 0; if (open->op_share_access & NFS4_SHARE_ACCESS_READ) - flags |= MAY_READ; + flags |= NFSD_MAY_READ; if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) - flags |= MAY_WRITE; + flags |= NFSD_MAY_WRITE; status = nfs4_new_open(rqstp, &stp, dp, current_fh, flags); if (status) goto out; init_stateid(stp, fp, open); status = nfsd4_truncate(rqstp, current_fh, open); if (status) { - release_stateid(stp, OPEN_STATE); + release_open_stateid(stp); goto out; } + if (nfsd4_has_session(&resp->cstate)) + update_stateid(&stp->st_stateid); } memcpy(&open->op_stateid, &stp->st_stateid, sizeof(stateid_t)); + if (nfsd4_has_session(&resp->cstate)) + open->op_stateowner->so_confirmed = 1; + /* * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. @@ -1824,16 +2585,13 @@ out: * To finish the open response, we just need to set the rflags. */ open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX; - if (!open->op_stateowner->so_confirmed) + if (!open->op_stateowner->so_confirmed && + !nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM; return status; } -static struct workqueue_struct *laundry_wq; -static void laundromat_main(struct work_struct *); -static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main); - __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, clientid_t *clid) @@ -1865,12 +2623,15 @@ out: return status; } +struct lock_manager nfsd4_manager = { +}; + static void -end_grace(void) +nfsd4_end_grace(void) { dprintk("NFSD: end of grace period\n"); nfsd4_recdir_purge_old(); - in_grace = 0; + locks_end_grace(&nfsd4_manager); } static time_t @@ -1887,8 +2648,8 @@ nfs4_laundromat(void) nfs4_lock_state(); dprintk("NFSD: laundromat service - starting\n"); - if (in_grace) - end_grace(); + if (locks_in_grace()) + nfsd4_end_grace(); list_for_each_safe(pos, next, &client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) { @@ -1933,7 +2694,7 @@ nfs4_laundromat(void) } dprintk("NFSD: purging unused open stateowner (so_id %d)\n", sop->so_id); - release_stateowner(sop); + release_openowner(sop); } if (clientid_val < NFSD_LAUNDROMAT_MINTIMEOUT) clientid_val = NFSD_LAUNDROMAT_MINTIMEOUT; @@ -1941,7 +2702,11 @@ nfs4_laundromat(void) return clientid_val; } -void +static struct workqueue_struct *laundry_wq; +static void laundromat_main(struct work_struct *); +static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main); + +static void laundromat_main(struct work_struct *not_used) { time_t t; @@ -1974,12 +2739,42 @@ nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stateid *stp) static int STALE_STATEID(stateid_t *stateid) { - if (stateid->si_boot == boot_time) - return 0; - dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n", - stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid, - stateid->si_generation); - return 1; + if (time_after((unsigned long)boot_time, + (unsigned long)stateid->si_boot)) { + dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n", + stateid->si_boot, stateid->si_stateownerid, + stateid->si_fileid, stateid->si_generation); + return 1; + } + return 0; +} + +static int +EXPIRED_STATEID(stateid_t *stateid) +{ + if (time_before((unsigned long)boot_time, + ((unsigned long)stateid->si_boot)) && + time_before((unsigned long)(stateid->si_boot + lease_time), get_seconds())) { + dprintk("NFSD: expired stateid (%08x/%08x/%08x/%08x)!\n", + stateid->si_boot, stateid->si_stateownerid, + stateid->si_fileid, stateid->si_generation); + return 1; + } + return 0; +} + +static __be32 +stateid_error_map(stateid_t *stateid) +{ + if (STALE_STATEID(stateid)) + return nfserr_stale_stateid; + if (EXPIRED_STATEID(stateid)) + return nfserr_expired; + + dprintk("NFSD: bad stateid (%08x/%08x/%08x/%08x)!\n", + stateid->si_boot, stateid->si_stateownerid, + stateid->si_fileid, stateid->si_generation); + return nfserr_bad_stateid; } static inline int @@ -2014,12 +2809,9 @@ out: static inline __be32 check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags) { - /* Trying to call delegreturn with a special stateid? Yuch: */ - if (!(flags & (RD_STATE | WR_STATE))) - return nfserr_bad_stateid; - else if (ONE_STATEID(stateid) && (flags & RD_STATE)) + if (ONE_STATEID(stateid) && (flags & RD_STATE)) return nfs_ok; - else if (nfs4_in_grace()) { + else if (locks_in_grace()) { /* Answer in remaining cases depends on existance of * conflicting state; so we must wait out the grace period. */ return nfserr_grace; @@ -2036,81 +2828,110 @@ check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags) * that are not able to provide mandatory locking. */ static inline int -io_during_grace_disallowed(struct inode *inode, int flags) +grace_disallows_io(struct inode *inode) +{ + return locks_in_grace() && mandatory_lock(inode); +} + +static int check_stateid_generation(stateid_t *in, stateid_t *ref, int flags) +{ + /* + * When sessions are used the stateid generation number is ignored + * when it is zero. + */ + if ((flags & HAS_SESSION) && in->si_generation == 0) + goto out; + + /* If the client sends us a stateid from the future, it's buggy: */ + if (in->si_generation > ref->si_generation) + return nfserr_bad_stateid; + /* + * The following, however, can happen. For example, if the + * client sends an open and some IO at the same time, the open + * may bump si_generation while the IO is still in flight. + * Thanks to hard links and renames, the client never knows what + * file an open will affect. So it could avoid that situation + * only by serializing all opens and IO from the same open + * owner. To recover from the old_stateid error, the client + * will just have to retry the IO: + */ + if (in->si_generation < ref->si_generation) + return nfserr_old_stateid; +out: + return nfs_ok; +} + +static int is_delegation_stateid(stateid_t *stateid) { - return nfs4_in_grace() && (flags & (RD_STATE | WR_STATE)) - && MANDATORY_LOCK(inode); + return stateid->si_fileid == 0; } /* * Checks for stateid operations */ __be32 -nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int flags, struct file **filpp) +nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, + stateid_t *stateid, int flags, struct file **filpp) { struct nfs4_stateid *stp = NULL; struct nfs4_delegation *dp = NULL; - stateid_t *stidp; + struct svc_fh *current_fh = &cstate->current_fh; struct inode *ino = current_fh->fh_dentry->d_inode; __be32 status; - dprintk("NFSD: preprocess_stateid_op: stateid = (%08x/%08x/%08x/%08x)\n", - stateid->si_boot, stateid->si_stateownerid, - stateid->si_fileid, stateid->si_generation); if (filpp) *filpp = NULL; - if (io_during_grace_disallowed(ino, flags)) + if (grace_disallows_io(ino)) return nfserr_grace; + if (nfsd4_has_session(cstate)) + flags |= HAS_SESSION; + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) return check_special_stateids(current_fh, stateid, flags); - /* STALE STATEID */ status = nfserr_stale_stateid; if (STALE_STATEID(stateid)) goto out; - /* BAD STATEID */ status = nfserr_bad_stateid; - if (!stateid->si_fileid) { /* delegation stateid */ - if(!(dp = find_delegation_stateid(ino, stateid))) { - dprintk("NFSD: delegation stateid not found\n"); + if (is_delegation_stateid(stateid)) { + dp = find_delegation_stateid(ino, stateid); + if (!dp) { + status = stateid_error_map(stateid); goto out; } - stidp = &dp->dl_stateid; + status = check_stateid_generation(stateid, &dp->dl_stateid, + flags); + if (status) + goto out; + status = nfs4_check_delegmode(dp, flags); + if (status) + goto out; + renew_client(dp->dl_client); + if (filpp) + *filpp = dp->dl_vfs_file; } else { /* open or lock stateid */ - if (!(stp = find_stateid(stateid, flags))) { - dprintk("NFSD: open or lock stateid not found\n"); + stp = find_stateid(stateid, flags); + if (!stp) { + status = stateid_error_map(stateid); goto out; } - if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp)) + if (nfs4_check_fh(current_fh, stp)) goto out; if (!stp->st_stateowner->so_confirmed) goto out; - stidp = &stp->st_stateid; - } - if (stateid->si_generation > stidp->si_generation) - goto out; - - /* OLD STATEID */ - status = nfserr_old_stateid; - if (stateid->si_generation < stidp->si_generation) - goto out; - if (stp) { - if ((status = nfs4_check_openmode(stp,flags))) + status = check_stateid_generation(stateid, &stp->st_stateid, + flags); + if (status) + goto out; + status = nfs4_check_openmode(stp, flags); + if (status) goto out; renew_client(stp->st_stateowner->so_client); if (filpp) *filpp = stp->st_vfs_file; - } else if (dp) { - if ((status = nfs4_check_delegmode(dp, flags))) - goto out; - renew_client(dp->dl_client); - if (flags & DELEG_RET) - unhash_delegation(dp); - if (filpp) - *filpp = dp->dl_vfs_file; } status = nfs_ok; out: @@ -2128,10 +2949,15 @@ setlkflg (int type) * Checks for sequence id mutating operations. */ static __be32 -nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *stateid, int flags, struct nfs4_stateowner **sopp, struct nfs4_stateid **stpp, struct nfsd4_lock *lock) +nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, + stateid_t *stateid, int flags, + struct nfs4_stateowner **sopp, + struct nfs4_stateid **stpp, struct nfsd4_lock *lock) { struct nfs4_stateid *stp; struct nfs4_stateowner *sop; + struct svc_fh *current_fh = &cstate->current_fh; + __be32 status; dprintk("NFSD: preprocess_seqid_op: seqid=%d " "stateid = (%08x/%08x/%08x/%08x)\n", seqid, @@ -2142,12 +2968,16 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei *sopp = NULL; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { - printk("NFSD: preprocess_seqid_op: magic stateid!\n"); + dprintk("NFSD: preprocess_seqid_op: magic stateid!\n"); return nfserr_bad_stateid; } if (STALE_STATEID(stateid)) return nfserr_stale_stateid; + + if (nfsd4_has_session(cstate)) + flags |= HAS_SESSION; + /* * We return BAD_STATEID if filehandle doesn't match stateid, * the confirmed flag is incorrecly set, or the generation @@ -2161,13 +2991,15 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei */ sop = search_close_lru(stateid->si_stateownerid, flags); if (sop == NULL) - return nfserr_bad_stateid; + return stateid_error_map(stateid); *sopp = sop; goto check_replay; } + *stpp = stp; + *sopp = sop = stp->st_stateowner; + if (lock) { - struct nfs4_stateowner *sop = stp->st_stateowner; clientid_t *lockclid = &lock->v.new.clientid; struct nfs4_client *clp = sop->so_client; int lkflg = 0; @@ -2176,58 +3008,49 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei lkflg = setlkflg(lock->lk_type); if (lock->lk_is_new) { - if (!sop->so_is_open_owner) - return nfserr_bad_stateid; - if (!cmp_clid(&clp->cl_clientid, lockclid)) - return nfserr_bad_stateid; - /* stp is the open stateid */ - status = nfs4_check_openmode(stp, lkflg); - if (status) - return status; - } else { - /* stp is the lock stateid */ - status = nfs4_check_openmode(stp->st_openstp, lkflg); - if (status) - return status; + if (!sop->so_is_open_owner) + return nfserr_bad_stateid; + if (!(flags & HAS_SESSION) && + !same_clid(&clp->cl_clientid, lockclid)) + return nfserr_bad_stateid; + /* stp is the open stateid */ + status = nfs4_check_openmode(stp, lkflg); + if (status) + return status; + } else { + /* stp is the lock stateid */ + status = nfs4_check_openmode(stp->st_openstp, lkflg); + if (status) + return status; } - } - if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp)) { - printk("NFSD: preprocess_seqid_op: fh-stateid mismatch!\n"); + if (nfs4_check_fh(current_fh, stp)) { + dprintk("NFSD: preprocess_seqid_op: fh-stateid mismatch!\n"); return nfserr_bad_stateid; } - *stpp = stp; - *sopp = sop = stp->st_stateowner; - /* * We now validate the seqid and stateid generation numbers. * For the moment, we ignore the possibility of * generation number wraparound. */ - if (seqid != sop->so_seqid) + if (!(flags & HAS_SESSION) && seqid != sop->so_seqid) goto check_replay; if (sop->so_confirmed && flags & CONFIRM) { - printk("NFSD: preprocess_seqid_op: expected" + dprintk("NFSD: preprocess_seqid_op: expected" " unconfirmed stateowner!\n"); return nfserr_bad_stateid; } if (!sop->so_confirmed && !(flags & CONFIRM)) { - printk("NFSD: preprocess_seqid_op: stateowner not" + dprintk("NFSD: preprocess_seqid_op: stateowner not" " confirmed yet!\n"); return nfserr_bad_stateid; } - if (stateid->si_generation > stp->st_stateid.si_generation) { - printk("NFSD: preprocess_seqid_op: future stateid?!\n"); - return nfserr_bad_stateid; - } - - if (stateid->si_generation < stp->st_stateid.si_generation) { - printk("NFSD: preprocess_seqid_op: old stateid!\n"); - return nfserr_old_stateid; - } + status = check_stateid_generation(stateid, &stp->st_stateid, flags); + if (status) + return status; renew_client(sop->so_client); return nfs_ok; @@ -2237,7 +3060,7 @@ check_replay: /* indicate replay to calling function */ return nfserr_replay_me; } - printk("NFSD: preprocess_seqid_op: bad seqid (expected %d, got %d)\n", + dprintk("NFSD: preprocess_seqid_op: bad seqid (expected %d, got %d)\n", sop->so_seqid, seqid); *sopp = NULL; return nfserr_bad_seqid; @@ -2261,9 +3084,9 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, oc->oc_seqid, &oc->oc_req_stateid, - CHECK_FH | CONFIRM | OPEN_STATE, + CONFIRM | OPEN_STATE, &oc->oc_stateowner, &stp, NULL))) goto out; @@ -2326,15 +3149,15 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, (int)cstate->current_fh.fh_dentry->d_name.len, cstate->current_fh.fh_dentry->d_name.name); - if (!access_valid(od->od_share_access) + if (!access_valid(od->od_share_access, cstate->minorversion) || !deny_valid(od->od_share_deny)) return nfserr_inval; nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, od->od_seqid, &od->od_stateid, - CHECK_FH | OPEN_STATE, + OPEN_STATE, &od->od_stateowner, &stp, NULL))) goto out; @@ -2384,10 +3207,10 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); /* check close_lru for replay */ - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, &close->cl_stateid, - CHECK_FH | OPEN_STATE | CLOSE_STATE, + OPEN_STATE | CLOSE_STATE, &close->cl_stateowner, &stp, NULL))) goto out; status = nfs_ok; @@ -2395,7 +3218,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, memcpy(&close->cl_stateid, &stp->st_stateid, sizeof(stateid_t)); /* release_stateid() calls nfsd_close() if needed */ - release_stateid(stp, OPEN_STATE); + release_open_stateid(stp); /* place unused nfs4_stateowners on so_close_lru list to be * released by the laundromat service after the lease period @@ -2416,16 +3239,42 @@ __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *dr) { + struct nfs4_delegation *dp; + stateid_t *stateid = &dr->dr_stateid; + struct inode *inode; __be32 status; + int flags = 0; if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) - goto out; + return status; + inode = cstate->current_fh.fh_dentry->d_inode; + if (nfsd4_has_session(cstate)) + flags |= HAS_SESSION; nfs4_lock_state(); - status = nfs4_preprocess_stateid_op(&cstate->current_fh, - &dr->dr_stateid, DELEG_RET, NULL); - nfs4_unlock_state(); + status = nfserr_bad_stateid; + if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) + goto out; + status = nfserr_stale_stateid; + if (STALE_STATEID(stateid)) + goto out; + status = nfserr_bad_stateid; + if (!is_delegation_stateid(stateid)) + goto out; + dp = find_delegation_stateid(inode, stateid); + if (!dp) { + status = stateid_error_map(stateid); + goto out; + } + status = check_stateid_generation(stateid, &dp->dl_stateid, flags); + if (status) + goto out; + renew_client(dp->dl_client); + + unhash_delegation(dp); out: + nfs4_unlock_state(); + return status; } @@ -2438,6 +3287,26 @@ out: #define LOCK_HASH_SIZE (1 << LOCK_HASH_BITS) #define LOCK_HASH_MASK (LOCK_HASH_SIZE - 1) +static inline u64 +end_offset(u64 start, u64 len) +{ + u64 end; + + end = start + len; + return end >= start ? end: NFS4_MAX_UINT64; +} + +/* last octet in a range */ +static inline u64 +last_byte_offset(u64 start, u64 len) +{ + u64 end; + + BUG_ON(!len); + end = start + len; + return end > start ? end - 1: NFS4_MAX_UINT64; +} + #define lockownerid_hashval(id) \ ((id) & LOCK_HASH_MASK) @@ -2457,13 +3326,13 @@ static struct list_head lockstateid_hashtbl[STATEID_HASH_SIZE]; static struct nfs4_stateid * find_stateid(stateid_t *stid, int flags) { - struct nfs4_stateid *local = NULL; + struct nfs4_stateid *local; u32 st_id = stid->si_stateownerid; u32 f_id = stid->si_fileid; unsigned int hashval; dprintk("NFSD: find_stateid flags 0x%x\n",flags); - if ((flags & LOCK_STATE) || (flags & RD_STATE) || (flags & WR_STATE)) { + if (flags & (LOCK_STATE | RD_STATE | WR_STATE)) { hashval = stateid_hashval(st_id, f_id); list_for_each_entry(local, &lockstateid_hashtbl[hashval], st_hash) { if ((local->st_stateid.si_stateownerid == st_id) && @@ -2471,7 +3340,8 @@ find_stateid(stateid_t *stid, int flags) return local; } } - if ((flags & OPEN_STATE) || (flags & RD_STATE) || (flags & WR_STATE)) { + + if (flags & (OPEN_STATE | RD_STATE | WR_STATE)) { hashval = stateid_hashval(st_id, f_id); list_for_each_entry(local, &stateid_hashtbl[hashval], st_hash) { if ((local->st_stateid.si_stateownerid == st_id) && @@ -2540,8 +3410,8 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) deny->ld_clientid.cl_id = 0; } deny->ld_start = fl->fl_start; - deny->ld_length = ~(u64)0; - if (fl->fl_end != ~(u64)0) + deny->ld_length = NFS4_MAX_UINT64; + if (fl->fl_end != NFS4_MAX_UINT64) deny->ld_length = fl->fl_end - fl->fl_start + 1; deny->ld_type = NFS4_READ_LT; if (fl->fl_type != F_RDLCK) @@ -2556,7 +3426,7 @@ find_lockstateowner_str(struct inode *inode, clientid_t *clid, struct nfs4_stateowner *op; list_for_each_entry(op, &lock_ownerstr_hashtbl[hashval], so_strhash) { - if (cmp_owner_str(op, owner, clid)) + if (same_owner_str(op, owner, clid)) return op; } return NULL; @@ -2622,7 +3492,7 @@ alloc_init_lock_stateid(struct nfs4_stateowner *sop, struct nfs4_file *fp, struc stp->st_stateowner = sop; get_nfs4_file(fp); stp->st_file = fp; - stp->st_stateid.si_boot = boot_time; + stp->st_stateid.si_boot = get_seconds(); stp->st_stateid.si_stateownerid = sop->so_id; stp->st_stateid.si_fileid = fp->fi_id; stp->st_stateid.si_generation = 0; @@ -2638,7 +3508,7 @@ out: static int check_lock_length(u64 offset, u64 length) { - return ((length == 0) || ((length != ~(u64)0) && + return ((length == 0) || ((length != NFS4_MAX_UINT64) && LOFF_OVERFLOW(offset, length))); } @@ -2657,6 +3527,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct file_lock conflock; __be32 status = 0; unsigned int strhashval; + unsigned int cmd; int err; dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n", @@ -2667,7 +3538,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; if ((status = fh_verify(rqstp, &cstate->current_fh, - S_IFREG, MAY_LOCK))) { + S_IFREG, NFSD_MAY_LOCK))) { dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } @@ -2684,14 +3555,15 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_file *fp; status = nfserr_stale_clientid; - if (STALE_CLIENTID(&lock->lk_new_clientid)) + if (!nfsd4_has_session(cstate) && + STALE_CLIENTID(&lock->lk_new_clientid)) goto out; /* validate and update open stateid and open seqid */ - status = nfs4_preprocess_seqid_op(&cstate->current_fh, + status = nfs4_preprocess_seqid_op(cstate, lock->lk_new_open_seqid, &lock->lk_new_open_stateid, - CHECK_FH | OPEN_STATE, + OPEN_STATE, &lock->lk_replay_owner, &open_stp, lock); if (status) @@ -2715,10 +3587,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } else { /* lock (lock owner + lock stateid) already exists */ - status = nfs4_preprocess_seqid_op(&cstate->current_fh, + status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, &lock->lk_old_lock_stateid, - CHECK_FH | LOCK_STATE, + LOCK_STATE, &lock->lk_replay_owner, &lock_stp, lock); if (status) goto out; @@ -2728,10 +3600,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, filp = lock_stp->st_vfs_file; status = nfserr_grace; - if (nfs4_in_grace() && !lock->lk_reclaim) + if (locks_in_grace() && !lock->lk_reclaim) goto out; status = nfserr_no_grace; - if (!nfs4_in_grace() && lock->lk_reclaim) + if (!locks_in_grace() && lock->lk_reclaim) goto out; locks_init_lock(&file_lock); @@ -2739,10 +3611,12 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, case NFS4_READ_LT: case NFS4_READW_LT: file_lock.fl_type = F_RDLCK; + cmd = F_SETLK; break; case NFS4_WRITE_LT: case NFS4_WRITEW_LT: file_lock.fl_type = F_WRLCK; + cmd = F_SETLK; break; default: status = nfserr_inval; @@ -2755,11 +3629,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, file_lock.fl_lmops = &nfsd_posix_mng_ops; file_lock.fl_start = lock->lk_offset; - if ((lock->lk_length == ~(u64)0) || - LOFF_OVERFLOW(lock->lk_offset, lock->lk_length)) - file_lock.fl_end = ~(u64)0; - else - file_lock.fl_end = lock->lk_offset + lock->lk_length - 1; + file_lock.fl_end = last_byte_offset(lock->lk_offset, lock->lk_length); nfs4_transform_lock_offset(&file_lock); /* @@ -2767,11 +3637,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * Note: locks.c uses the BKL to protect the inode's lock list. */ - /* XXX?: Just to divert the locks_release_private at the start of - * locks_copy_lock: */ - conflock.fl_ops = NULL; - conflock.fl_lmops = NULL; - err = posix_lock_file_conf(filp, &file_lock, &conflock); + err = vfs_lock_file(filp, cmd, &file_lock, &conflock); switch (-err) { case 0: /* success! */ update_stateid(&lock_stp->st_stateid); @@ -2788,13 +3654,13 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_deadlock; break; default: - dprintk("NFSD: nfsd4_lock: posix_lock_file_conf() failed! status %d\n",err); + dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err); status = nfserr_resource; break; } out: if (status && lock->lk_is_new && lock_sop) - release_stateowner(lock_sop); + release_lockowner(lock_sop); if (lock->lk_replay_owner) { nfs4_get_stateowner(lock->lk_replay_owner); cstate->replay_owner = lock->lk_replay_owner; @@ -2804,6 +3670,25 @@ out: } /* + * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN, + * so we do a temporary open here just to get an open file to pass to + * vfs_test_lock. (Arguably perhaps test_lock should be done with an + * inode operation.) + */ +static int nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock) +{ + struct file *file; + int err; + + err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); + if (err) + return err; + err = vfs_test_lock(file, lock); + nfsd_close(file); + return err; +} + +/* * LOCKT operation */ __be32 @@ -2811,12 +3696,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_lockt *lockt) { struct inode *inode; - struct file file; struct file_lock file_lock; - struct file_lock conflock; + int error; __be32 status; - if (nfs4_in_grace()) + if (locks_in_grace()) return nfserr_grace; if (check_lock_length(lockt->lt_offset, lockt->lt_length)) @@ -2826,7 +3710,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); status = nfserr_stale_clientid; - if (STALE_CLIENTID(&lockt->lt_clientid)) + if (!nfsd4_has_session(cstate) && STALE_CLIENTID(&lockt->lt_clientid)) goto out; if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) { @@ -2848,7 +3732,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, file_lock.fl_type = F_WRLCK; break; default: - printk("NFSD: nfs4_lockt: bad lock type!\n"); + dprintk("NFSD: nfs4_lockt: bad lock type!\n"); status = nfserr_inval; goto out; } @@ -2859,28 +3743,21 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, file_lock.fl_owner = (fl_owner_t)lockt->lt_stateowner; file_lock.fl_pid = current->tgid; file_lock.fl_flags = FL_POSIX; - file_lock.fl_lmops = &nfsd_posix_mng_ops; file_lock.fl_start = lockt->lt_offset; - if ((lockt->lt_length == ~(u64)0) || LOFF_OVERFLOW(lockt->lt_offset, lockt->lt_length)) - file_lock.fl_end = ~(u64)0; - else - file_lock.fl_end = lockt->lt_offset + lockt->lt_length - 1; + file_lock.fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length); nfs4_transform_lock_offset(&file_lock); - /* posix_test_lock uses the struct file _only_ to resolve the inode. - * since LOCKT doesn't require an OPEN, and therefore a struct - * file may not exist, pass posix_test_lock a struct file with - * only the dentry:inode set. - */ - memset(&file, 0, sizeof (struct file)); - file.f_path.dentry = cstate->current_fh.fh_dentry; - status = nfs_ok; - if (posix_test_lock(&file, &file_lock, &conflock)) { + error = nfsd_test_lock(rqstp, &cstate->current_fh, &file_lock); + if (error) { + status = nfserrno(error); + goto out; + } + if (file_lock.fl_type != F_UNLCK) { status = nfserr_denied; - nfs4_set_lock_denied(&conflock, &lockt->lt_denied); + nfs4_set_lock_denied(&file_lock, &lockt->lt_denied); } out: nfs4_unlock_state(); @@ -2906,10 +3783,10 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + if ((status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, &locku->lu_stateid, - CHECK_FH | LOCK_STATE, + LOCK_STATE, &locku->lu_stateowner, &stp, NULL))) goto out; @@ -2924,18 +3801,15 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, file_lock.fl_lmops = &nfsd_posix_mng_ops; file_lock.fl_start = locku->lu_offset; - if ((locku->lu_length == ~(u64)0) || LOFF_OVERFLOW(locku->lu_offset, locku->lu_length)) - file_lock.fl_end = ~(u64)0; - else - file_lock.fl_end = locku->lu_offset + locku->lu_length - 1; + file_lock.fl_end = last_byte_offset(locku->lu_offset, locku->lu_length); nfs4_transform_lock_offset(&file_lock); /* * Try to unlock the file in the VFS. */ - err = posix_lock_file(filp, &file_lock); + err = vfs_lock_file(filp, F_SETLK, &file_lock, NULL); if (err) { - dprintk("NFSD: nfs4_locku: posix_lock_file failed!\n"); + dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } /* @@ -3013,7 +3887,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, INIT_LIST_HEAD(&matches); for (i = 0; i < LOCK_HASH_SIZE; i++) { list_for_each_entry(sop, &lock_ownerid_hashtbl[i], so_idhash) { - if (!cmp_owner_str(sop, owner, clid)) + if (!same_owner_str(sop, owner, clid)) continue; list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) { @@ -3035,7 +3909,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, /* unhash_stateowner deletes so_perclient only * for openowners. */ list_del(&sop->so_perclient); - release_stateowner(sop); + release_lockowner(sop); } out: nfs4_unlock_state(); @@ -3049,12 +3923,12 @@ alloc_reclaim(void) } int -nfs4_has_reclaimed_state(const char *name) +nfs4_has_reclaimed_state(const char *name, bool use_exchange_id) { unsigned int strhashval = clientstr_hashval(name); struct nfs4_client *clp; - clp = find_confirmed_client_by_str(name, strhashval); + clp = find_confirmed_client_by_str(name, strhashval, use_exchange_id); return clp ? 1 : 0; } @@ -3137,17 +4011,22 @@ nfs4_check_open_reclaim(clientid_t *clid) /* initialization to perform at module load time: */ -void +int nfs4_state_init(void) { - int i; + int i, status; + status = nfsd4_init_slabs(); + if (status) + return status; for (i = 0; i < CLIENT_HASH_SIZE; i++) { INIT_LIST_HEAD(&conf_id_hashtbl[i]); INIT_LIST_HEAD(&conf_str_hashtbl[i]); INIT_LIST_HEAD(&unconf_str_hashtbl[i]); INIT_LIST_HEAD(&unconf_id_hashtbl[i]); } + for (i = 0; i < SESSION_HASH_SIZE; i++) + INIT_LIST_HEAD(&sessionid_hashtbl[i]); for (i = 0; i < FILE_HASH_SIZE; i++) { INIT_LIST_HEAD(&file_hashtbl[i]); } @@ -3170,6 +4049,7 @@ nfs4_state_init(void) for (i = 0; i < CLIENT_HASH_SIZE; i++) INIT_LIST_HEAD(&reclaim_str_hashtbl[i]); reclaim_str_hashtbl_size = 0; + return 0; } static void @@ -3185,42 +4065,60 @@ nfsd4_load_reboot_recovery_data(void) printk("NFSD: Failure reading reboot recovery data\n"); } +unsigned long +get_nfs4_grace_period(void) +{ + return max(user_lease_time, lease_time) * HZ; +} + +/* + * Since the lifetime of a delegation isn't limited to that of an open, a + * client may quite reasonably hang on to a delegation as long as it has + * the inode cached. This becomes an obvious problem the first time a + * client's inode cache approaches the size of the server's total memory. + * + * For now we avoid this problem by imposing a hard limit on the number + * of delegations, which varies according to the server's memory size. + */ +static void +set_max_delegations(void) +{ + /* + * Allow at most 4 delegations per megabyte of RAM. Quick + * estimates suggest that in the worst case (where every delegation + * is for a different inode), a delegation could take about 1.5K, + * giving a worst case usage of about 6% of memory. + */ + max_delegations = nr_free_buffer_pages() >> (20 - 2 - PAGE_SHIFT); +} + /* initialization to perform when the nfsd service is started: */ static void __nfs4_state_start(void) { - time_t grace_time; + unsigned long grace_time; boot_time = get_seconds(); - grace_time = max(user_lease_time, lease_time); + grace_time = get_nfs4_grace_period(); lease_time = user_lease_time; - in_grace = 1; - printk("NFSD: starting %ld-second grace period\n", grace_time); + locks_start_grace(&nfsd4_manager); + printk(KERN_INFO "NFSD: starting %ld-second grace period\n", + grace_time/HZ); laundry_wq = create_singlethread_workqueue("nfsd4"); - queue_delayed_work(laundry_wq, &laundromat_work, grace_time*HZ); + queue_delayed_work(laundry_wq, &laundromat_work, grace_time); + set_max_delegations(); } -int +void nfs4_state_start(void) { - int status; - if (nfs4_init) - return 0; - status = nfsd4_init_slabs(); - if (status) - return status; + return; nfsd4_load_reboot_recovery_data(); __nfs4_state_start(); nfs4_init = 1; - return 0; -} - -int -nfs4_in_grace(void) -{ - return in_grace; + return; } time_t @@ -3260,7 +4158,6 @@ __nfs4_state_shutdown(void) unhash_delegation(dp); } - cancel_delayed_work(&laundromat_work); nfsd4_shutdown_recdir(); nfs4_init = 0; } @@ -3270,19 +4167,21 @@ nfs4_state_shutdown(void) { cancel_rearming_delayed_workqueue(laundry_wq, &laundromat_work); destroy_workqueue(laundry_wq); + locks_end_grace(&nfsd4_manager); nfs4_lock_state(); nfs4_release_reclaim(); __nfs4_state_shutdown(); - nfsd4_free_slabs(); nfs4_unlock_state(); } +/* + * user_recovery_dirname is protected by the nfsd_mutex since it's only + * accessed when nfsd is starting. + */ static void nfs4_set_recdir(char *recdir) { - nfs4_lock_state(); strcpy(user_recovery_dirname, recdir); - nfs4_unlock_state(); } /* @@ -3292,20 +4191,26 @@ int nfs4_reset_recoverydir(char *recdir) { int status; - struct nameidata nd; + struct path path; - status = path_lookup(recdir, LOOKUP_FOLLOW, &nd); + status = kern_path(recdir, LOOKUP_FOLLOW, &path); if (status) return status; status = -ENOTDIR; - if (S_ISDIR(nd.dentry->d_inode->i_mode)) { + if (S_ISDIR(path.dentry->d_inode->i_mode)) { nfs4_set_recdir(recdir); status = 0; } - path_release(&nd); + path_put(&path); return status; } +char * +nfs4_recoverydir(void) +{ + return user_recovery_dirname; +} + /* * Called when leasetime is changed. * @@ -3314,11 +4219,12 @@ nfs4_reset_recoverydir(char *recdir) * we start to register any changes in lease time. If the administrator * really wants to change the lease time *now*, they can go ahead and bring * nfsd down and then back up again after changing the lease time. + * + * user_lease_time is protected by nfsd_mutex since it's only really accessed + * when nfsd is starting */ void nfs4_reset_lease(time_t leasetime) { - lock_kernel(); user_lease_time = leasetime; - unlock_kernel(); }