X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=fs%2Fnfsd%2Fnfs4state.c;h=6ae28e606afc9e82c61589cb9e10dab5b17ac344;hp=ebcf226a9e4a1fb65d04baa8e6ac10dc7f845071;hb=7e0f7cf582abd6c85232331dfe726a4e4b0fd98e;hpb=1a1d92c10dd24bbdc28b3d6e2d03ec199dd3a65b diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index ebcf226..6ae28e6 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 @@ -57,8 +62,6 @@ 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; @@ -72,7 +75,6 @@ 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); @@ -84,10 +86,10 @@ static void nfs4_set_recdir(char *recdir); */ static DEFINE_MUTEX(client_mutex); -static kmem_cache_t *stateowner_slab = NULL; -static kmem_cache_t *file_slab = NULL; -static kmem_cache_t *stateid_slab = NULL; -static kmem_cache_t *deleg_slab = NULL; +static struct kmem_cache *stateowner_slab = NULL; +static struct kmem_cache *file_slab = NULL; +static struct kmem_cache *stateid_slab = NULL; +static struct kmem_cache *deleg_slab = NULL; void nfs4_lock_state(void) @@ -114,10 +116,6 @@ 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 */ @@ -148,6 +146,7 @@ get_nfs4_file(struct nfs4_file *fi) } static int num_delegations; +unsigned int max_delegations; /* * Open owner state (share locks) @@ -191,7 +190,9 @@ 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) @@ -214,9 +215,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f 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 +249,7 @@ 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 +304,90 @@ 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 inline void renew_client(struct nfs4_client *clp) { @@ -334,29 +417,45 @@ 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); 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 +468,6 @@ 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 +477,6 @@ 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 +497,18 @@ 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); } 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); @@ -432,77 +517,77 @@ create_client(struct xdr_netobj name, char *recdir) { INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); 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 +626,7 @@ 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; @@ -554,7 +639,7 @@ 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; @@ -677,43 +762,11 @@ out_err: return; } -/* - * 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. - * - */ -int -nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_setclientid *setclid) +__be32 +nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_setclientid *setclid) { - u32 ip_addr = rqstp->rq_addr.sin_addr.s_addr; + struct sockaddr_in *sin = svc_addr_in(rqstp); struct xdr_netobj clname = { .len = setclid->se_namelen, .data = setclid->se_name, @@ -721,7 +774,8 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_setclientid *setclid) nfs4_verifier clverifier = setclid->se_verf; unsigned int strhashval; struct nfs4_client *conf, *unconf, *new; - int status; + __be32 status; + char *princ; char dname[HEXDIR_LEN]; if (!check_name(clname)) @@ -741,52 +795,37 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_setclientid *setclid) nfs4_lock_state(); conf = find_confirmed_client_by_str(dname, strhashval); 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 != ip_addr) { - printk("NFSD: setclientid: string in use by client" - "(clientid %08x/%08x)\n", - conf->cl_clientid.cl_boot, conf->cl_clientid.cl_id); + if (!same_creds(&conf->cl_cred, &rqstp->rq_cred) + || conf->cl_addr != sin->sin_addr.s_addr) { + dprintk("NFSD: setclientid: string in use by clientat %pI4\n", + &conf->cl_addr); goto out; } } + /* + * 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); 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 = ip_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 +838,44 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_setclientid *setclid) new = create_client(clname, dname); if (new == NULL) goto out; - copy_verf(new,&conf->cl_verifier); - new->cl_addr = ip_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 = ip_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 = ip_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)); @@ -869,20 +887,20 @@ 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. */ -int -nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confirm *setclientid_confirm) +__be32 +nfsd4_setclientid_confirm(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_setclientid_confirm *setclientid_confirm) { - u32 ip_addr = rqstp->rq_addr.sin_addr.s_addr; + struct sockaddr_in *sin = svc_addr_in(rqstp); struct nfs4_client *conf, *unconf; nfs4_verifier confirm = setclientid_confirm->sc_confirm; clientid_t * clid = &setclientid_confirm->sc_clientid; - int status; + __be32 status; if (STALE_CLIENTID(clid)) return nfserr_stale_clientid; @@ -897,22 +915,22 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confi unconf = find_unconfirmed_client(clid); status = nfserr_clid_inuse; - if (conf && conf->cl_addr != ip_addr) + if (conf && conf->cl_addr != sin->sin_addr.s_addr) goto out; - if (unconf && unconf->cl_addr != ip_addr) + 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 @@ -924,28 +942,23 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confi 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 = @@ -958,16 +971,15 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confi } 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 { @@ -975,8 +987,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confi status = nfserr_clid_inuse; } out: - if (!status) - nfsd4_probe_callback(conf); nfs4_unlock_state(); return status; } @@ -997,13 +1007,14 @@ alloc_init_file(struct inode *ino) list_add(&fp->fi_hash, &file_hashtbl[hashval]); fp->fi_inode = igrab(ino); fp->fi_id = current_fileid++; + fp->fi_had_conflict = false; return fp; } return NULL; } static void -nfsd4_free_slab(kmem_cache_t **slab) +nfsd4_free_slab(struct kmem_cache **slab) { if (*slab == NULL) return; @@ -1011,7 +1022,7 @@ nfsd4_free_slab(kmem_cache_t **slab) *slab = NULL; } -static void +void nfsd4_free_slabs(void) { nfsd4_free_slab(&stateowner_slab); @@ -1024,19 +1035,19 @@ 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; @@ -1103,48 +1114,6 @@ 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; @@ -1172,24 +1141,6 @@ init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open * } 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); @@ -1199,10 +1150,12 @@ 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 * @@ -1211,7 +1164,7 @@ 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; @@ -1233,16 +1186,39 @@ find_file(struct inode *ino) return NULL; } -static int access_valid(u32 x) +static inline int access_valid(u32 x) { - return (x > 0 && x < 4); + if (x < NFS4_SHARE_ACCESS_READ) + return 0; + if (x > NFS4_SHARE_ACCESS_BOTH) + 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; @@ -1280,13 +1256,13 @@ test_share(struct nfs4_stateid *stp, struct nfsd4_open *open) { * Called to check deny when READ with all zero stateid or * WRITE with all zero or all one stateid */ -static int +static __be32 nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) { struct inode *ino = current_fh->fh_dentry->d_inode; struct nfs4_file *fp; struct nfs4_stateid *stp; - int ret; + __be32 ret; dprintk("NFSD: nfs4_share_conflict\n"); @@ -1310,7 +1286,7 @@ 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_dentry->d_inode); + drop_file_write_access(filp); filp->f_mode = (filp->f_mode | FMODE_READ) & ~FMODE_WRITE; } } @@ -1323,8 +1299,7 @@ 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; } @@ -1353,6 +1328,7 @@ 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); @@ -1361,8 +1337,12 @@ 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)) { @@ -1371,6 +1351,7 @@ 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); } } @@ -1395,7 +1376,7 @@ 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) @@ -1409,7 +1390,7 @@ 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) @@ -1444,7 +1425,7 @@ static struct lock_manager_operations nfsd_lease_mng_ops = { }; -int +__be32 nfsd4_process_open1(struct nfsd4_open *open) { clientid_t *clientid = &open->op_clientid; @@ -1471,13 +1452,13 @@ nfsd4_process_open1(struct nfsd4_open *open) 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; } if (open->op_seqid == sop->so_seqid - 1) { if (sop->so_replay.rp_buflen) - return NFSERR_REPLAY_ME; + return nfserr_replay_me; /* The original OPEN failed so spectacularly * that we don't even have replay data saved! * Therefore, we have no choice but to continue @@ -1501,7 +1482,7 @@ renew: return nfs_ok; } -static inline int +static inline __be32 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags) { if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ)) @@ -1522,12 +1503,12 @@ find_delegation_file(struct nfs4_file *fp, stateid_t *stid) return NULL; } -static int +static __be32 nfs4_check_deleg(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_delegation **dp) { int flags; - int status = nfserr_bad_stateid; + __be32 status = nfserr_bad_stateid; *dp = find_delegation_file(fp, &open->op_delegate_stateid); if (*dp == NULL) @@ -1546,11 +1527,11 @@ out: return nfs_ok; } -static int +static __be32 nfs4_check_open(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_stateid **stpp) { struct nfs4_stateid *local; - int status = nfserr_share_denied; + __be32 status = nfserr_share_denied; struct nfs4_stateowner *sop = open->op_stateowner; list_for_each_entry(local, &fp->fi_stateids, st_perfile) { @@ -1575,7 +1556,7 @@ nfs4_alloc_stateid(void) return kmem_cache_alloc(stateid_slab, GFP_KERNEL); } -static int +static __be32 nfs4_new_open(struct svc_rqst *rqstp, struct nfs4_stateid **stpp, struct nfs4_delegation *dp, struct svc_fh *cur_fh, int flags) @@ -1590,7 +1571,7 @@ nfs4_new_open(struct svc_rqst *rqstp, struct nfs4_stateid **stpp, get_file(dp->dl_vfs_file); stp->st_vfs_file = dp->dl_vfs_file; } else { - int status; + __be32 status; status = nfsd_open(rqstp, cur_fh, S_IFREG, flags, &stp->st_vfs_file); if (status) { @@ -1604,7 +1585,7 @@ nfs4_new_open(struct svc_rqst *rqstp, struct nfs4_stateid **stpp, return 0; } -static inline int +static inline __be32 nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, struct nfsd4_open *open) { @@ -1619,22 +1600,26 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, return nfsd_setattr(rqstp, fh, &iattr, 0, (time_t)0); } -static int +static __be32 nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_stateid *stp, struct nfsd4_open *open) { struct file *filp = stp->st_vfs_file; - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; unsigned int share_access, new_writer; - int status; + __be32 status; set_access(&share_access, stp->st_access_bmap); new_writer = (~share_access) & open->op_share_access & NFS4_SHARE_ACCESS_WRITE; if (new_writer) { - status = get_write_access(inode); - if (status) - return nfserrno(status); + 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) { @@ -1644,8 +1629,8 @@ 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; } @@ -1683,7 +1668,7 @@ 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; @@ -1704,16 +1689,16 @@ 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; @@ -1731,21 +1716,21 @@ 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; } /* * called with nfs4_lock_state() held. */ -int +__be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { struct nfs4_file *fp = NULL; struct inode *ino = current_fh->fh_dentry->d_inode; struct nfs4_stateid *stp = NULL; struct nfs4_delegation *dp = NULL; - int status; + __be32 status; status = nfserr_inval; if (!access_valid(open->op_share_access) @@ -1787,16 +1772,16 @@ 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; } } @@ -1828,16 +1813,12 @@ out: return status; } -static struct workqueue_struct *laundry_wq; -static struct work_struct laundromat_work; -static void laundromat_main(void *); -static DECLARE_WORK(laundromat_work, laundromat_main, NULL); - -int -nfsd4_renew(clientid_t *clid) +__be32 +nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + clientid_t *clid) { struct nfs4_client *clp; - int status; + __be32 status; nfs4_lock_state(); dprintk("process_renew(%08x/%08x): starting\n", @@ -1863,12 +1844,15 @@ 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 @@ -1885,8 +1869,8 @@ 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)) { @@ -1931,7 +1915,7 @@ 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; @@ -1939,8 +1923,12 @@ nfs4_laundromat(void) return clientid_val; } -void -laundromat_main(void *not_used) +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; @@ -1966,7 +1954,7 @@ search_close_lru(u32 st_id, int flags) static inline int nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stateid *stp) { - return fhp->fh_dentry->d_inode != stp->st_vfs_file->f_dentry->d_inode; + return fhp->fh_dentry->d_inode != stp->st_vfs_file->f_path.dentry->d_inode; } static int @@ -1996,9 +1984,9 @@ access_permit_write(unsigned long access_bmap) } static -int nfs4_check_openmode(struct nfs4_stateid *stp, int flags) +__be32 nfs4_check_openmode(struct nfs4_stateid *stp, int flags) { - int status = nfserr_openmode; + __be32 status = nfserr_openmode; if ((flags & WR_STATE) && (!access_permit_write(stp->st_access_bmap))) goto out; @@ -2009,15 +1997,12 @@ out: return status; } -static inline int +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; @@ -2036,25 +2021,45 @@ check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags) static inline int io_during_grace_disallowed(struct inode *inode, int flags) { - return nfs4_in_grace() && (flags & (RD_STATE | WR_STATE)) - && MANDATORY_LOCK(inode); + return locks_in_grace() && mandatory_lock(inode); +} + +static int check_stateid_generation(stateid_t *in, stateid_t *ref) +{ + /* 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; + return nfs_ok; +} + +static int is_delegation_stateid(stateid_t *stateid) +{ + return stateid->si_fileid == 0; } /* * Checks for stateid operations */ -int +__be32 nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int flags, struct file **filpp) { struct nfs4_stateid *stp = NULL; struct nfs4_delegation *dp = NULL; - stateid_t *stidp; struct inode *ino = current_fh->fh_dentry->d_inode; - int status; + __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; @@ -2064,51 +2069,41 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl 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) goto out; - } - stidp = &dp->dl_stateid; + status = check_stateid_generation(stateid, &dp->dl_stateid); + 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) goto out; - } if ((flags & CHECK_FH) && 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); + 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: @@ -2125,11 +2120,12 @@ setlkflg (int type) /* * Checks for sequence id mutating operations. */ -static int +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) { struct nfs4_stateid *stp; struct nfs4_stateowner *sop; + __be32 status; dprintk("NFSD: preprocess_seqid_op: seqid=%d " "stateid = (%08x/%08x/%08x/%08x)\n", seqid, @@ -2140,7 +2136,7 @@ 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; } @@ -2164,41 +2160,39 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei 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; - int status; + __be32 status; lkflg = setlkflg(lock->lk_type); if (lock->lk_is_new) { - if (!sop->so_is_open_owner) + if (!sop->so_is_open_owner) + return nfserr_bad_stateid; + if (!same_clid(&clp->cl_clientid, lockclid)) 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; + /* 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 @@ -2208,24 +2202,18 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei 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); + if (status) + return status; renew_client(sop->so_client); return nfs_ok; @@ -2233,34 +2221,35 @@ check_replay: if (seqid == sop->so_seqid - 1) { dprintk("NFSD: preprocess_seqid_op: retransmission?\n"); /* indicate replay to calling function */ - return NFSERR_REPLAY_ME; + 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; } -int -nfsd4_open_confirm(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open_confirm *oc, struct nfs4_stateowner **replay_owner) +__be32 +nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_open_confirm *oc) { - int status; + __be32 status; struct nfs4_stateowner *sop; struct nfs4_stateid *stp; dprintk("NFSD: nfsd4_open_confirm on file %.*s\n", - (int)current_fh->fh_dentry->d_name.len, - current_fh->fh_dentry->d_name.name); + (int)cstate->current_fh.fh_dentry->d_name.len, + cstate->current_fh.fh_dentry->d_name.name); - status = fh_verify(rqstp, current_fh, S_IFREG, 0); + status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); if (status) return status; nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(current_fh, oc->oc_seqid, - &oc->oc_req_stateid, - CHECK_FH | CONFIRM | OPEN_STATE, + if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + oc->oc_seqid, &oc->oc_req_stateid, + CONFIRM | OPEN_STATE, &oc->oc_stateowner, &stp, NULL))) goto out; @@ -2279,7 +2268,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs out: if (oc->oc_stateowner) { nfs4_get_stateowner(oc->oc_stateowner); - *replay_owner = oc->oc_stateowner; + cstate->replay_owner = oc->oc_stateowner; } nfs4_unlock_state(); return status; @@ -2310,25 +2299,28 @@ reset_union_bmap_deny(unsigned long deny, unsigned long *bmap) } } -int -nfsd4_open_downgrade(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open_downgrade *od, struct nfs4_stateowner **replay_owner) +__be32 +nfsd4_open_downgrade(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_open_downgrade *od) { - int status; + __be32 status; struct nfs4_stateid *stp; unsigned int share_access; dprintk("NFSD: nfsd4_open_downgrade on file %.*s\n", - (int)current_fh->fh_dentry->d_name.len, - current_fh->fh_dentry->d_name.name); + (int)cstate->current_fh.fh_dentry->d_name.len, + cstate->current_fh.fh_dentry->d_name.name); if (!access_valid(od->od_share_access) || !deny_valid(od->od_share_deny)) return nfserr_inval; nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(current_fh, od->od_seqid, + if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + od->od_seqid, &od->od_stateid, - CHECK_FH | OPEN_STATE, + OPEN_STATE, &od->od_stateowner, &stp, NULL))) goto out; @@ -2356,7 +2348,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct n out: if (od->od_stateowner) { nfs4_get_stateowner(od->od_stateowner); - *replay_owner = od->od_stateowner; + cstate->replay_owner = od->od_stateowner; } nfs4_unlock_state(); return status; @@ -2365,21 +2357,23 @@ out: /* * nfs4_unlock_state() called after encode */ -int -nfsd4_close(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_close *close, struct nfs4_stateowner **replay_owner) +__be32 +nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_close *close) { - int status; + __be32 status; struct nfs4_stateid *stp; dprintk("NFSD: nfsd4_close on file %.*s\n", - (int)current_fh->fh_dentry->d_name.len, - current_fh->fh_dentry->d_name.name); + (int)cstate->current_fh.fh_dentry->d_name.len, + cstate->current_fh.fh_dentry->d_name.name); nfs4_lock_state(); /* check close_lru for replay */ - if ((status = nfs4_preprocess_seqid_op(current_fh, close->cl_seqid, + if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, + 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; @@ -2387,7 +2381,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_clos 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 @@ -2398,24 +2392,47 @@ nfsd4_close(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_clos out: if (close->cl_stateowner) { nfs4_get_stateowner(close->cl_stateowner); - *replay_owner = close->cl_stateowner; + cstate->replay_owner = close->cl_stateowner; } nfs4_unlock_state(); return status; } -int -nfsd4_delegreturn(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_delegreturn *dr) +__be32 +nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_delegreturn *dr) { - int status; + struct nfs4_delegation *dp; + stateid_t *stateid = &dr->dr_stateid; + struct inode *inode; + __be32 status; - if ((status = fh_verify(rqstp, current_fh, S_IFREG, 0))) - goto out; + if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) + return status; + inode = cstate->current_fh.fh_dentry->d_inode; nfs4_lock_state(); - status = nfs4_preprocess_stateid_op(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) + goto out; + status = check_stateid_generation(stateid, &dp->dl_stateid); + if (status) + goto out; + renew_client(dp->dl_client); + + unhash_delegation(dp); out: + nfs4_unlock_state(); + return status; } @@ -2428,6 +2445,26 @@ 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) @@ -2447,13 +2484,13 @@ 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) && @@ -2461,7 +2498,8 @@ 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) && @@ -2530,8 +2568,8 @@ 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) @@ -2546,7 +2584,7 @@ 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; @@ -2628,15 +2666,16 @@ 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))); } /* * LOCK operation */ -int -nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock *lock, struct nfs4_stateowner **replay_owner) +__be32 +nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_lock *lock) { struct nfs4_stateowner *open_sop = NULL; struct nfs4_stateowner *lock_sop = NULL; @@ -2644,8 +2683,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock struct file *filp; struct file_lock file_lock; struct file_lock conflock; - int status = 0; + __be32 status = 0; unsigned int strhashval; + unsigned int cmd; + int err; dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n", (long long) lock->lk_offset, @@ -2654,7 +2695,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock if (check_lock_length(lock->lk_offset, lock->lk_length)) return nfserr_inval; - if ((status = fh_verify(rqstp, current_fh, S_IFREG, MAY_LOCK))) { + if ((status = fh_verify(rqstp, &cstate->current_fh, + S_IFREG, NFSD_MAY_LOCK))) { dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } @@ -2675,10 +2717,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock goto out; /* validate and update open stateid and open seqid */ - status = nfs4_preprocess_seqid_op(current_fh, + status = nfs4_preprocess_seqid_op(&cstate->current_fh, 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) @@ -2702,10 +2744,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock goto out; } else { /* lock (lock owner + lock stateid) already exists */ - status = nfs4_preprocess_seqid_op(current_fh, + status = nfs4_preprocess_seqid_op(&cstate->current_fh, 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; @@ -2715,10 +2757,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock 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); @@ -2726,10 +2768,12 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock 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; @@ -2742,11 +2786,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock 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); /* @@ -2754,17 +2794,13 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock * 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; - status = posix_lock_file_conf(filp, &file_lock, &conflock); - dprintk("NFSD: nfsd4_lock: posix_lock_file_conf status %d\n",status); - switch (-status) { + err = vfs_lock_file(filp, cmd, &file_lock, &conflock); + switch (-err) { case 0: /* success! */ update_stateid(&lock_stp->st_stateid); memcpy(&lock->lk_resp_stateid, &lock_stp->st_stateid, sizeof(stateid_t)); + status = 0; break; case (EAGAIN): /* conflock holds conflicting lock */ status = nfserr_denied; @@ -2775,34 +2811,53 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock status = nfserr_deadlock; break; default: - dprintk("NFSD: nfsd4_lock: posix_lock_file_conf() failed! status %d\n",status); + 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); - *replay_owner = lock->lk_replay_owner; + cstate->replay_owner = lock->lk_replay_owner; } nfs4_unlock_state(); return status; } /* + * 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 */ -int -nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lockt *lockt) +__be32 +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 status; + 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)) @@ -2815,14 +2870,14 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock if (STALE_CLIENTID(&lockt->lt_clientid)) goto out; - if ((status = fh_verify(rqstp, current_fh, S_IFREG, 0))) { + if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) { dprintk("NFSD: nfsd4_lockt: fh_verify() failed!\n"); if (status == nfserr_symlink) status = nfserr_inval; goto out; } - inode = current_fh->fh_dentry->d_inode; + inode = cstate->current_fh.fh_dentry->d_inode; locks_init_lock(&file_lock); switch (lockt->lt_type) { case NFS4_READ_LT: @@ -2834,7 +2889,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock 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; } @@ -2845,41 +2900,36 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock 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_dentry = 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(); return status; } -int -nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_locku *locku, struct nfs4_stateowner **replay_owner) +__be32 +nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_locku *locku) { struct nfs4_stateid *stp; struct file *filp = NULL; struct file_lock file_lock; - int status; + __be32 status; + int err; dprintk("NFSD: nfsd4_locku: start=%Ld length=%Ld\n", (long long) locku->lu_offset, @@ -2890,10 +2940,10 @@ nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock nfs4_lock_state(); - if ((status = nfs4_preprocess_seqid_op(current_fh, + if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh, locku->lu_seqid, &locku->lu_stateid, - CHECK_FH | LOCK_STATE, + LOCK_STATE, &locku->lu_stateowner, &stp, NULL))) goto out; @@ -2908,18 +2958,15 @@ nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock 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. */ - status = posix_lock_file(filp, &file_lock); - if (status) { - dprintk("NFSD: nfs4_locku: posix_lock_file failed!\n"); + err = vfs_lock_file(filp, F_SETLK, &file_lock, NULL); + if (err) { + dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } /* @@ -2931,13 +2978,13 @@ nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock out: if (locku->lu_stateowner) { nfs4_get_stateowner(locku->lu_stateowner); - *replay_owner = locku->lu_stateowner; + cstate->replay_owner = locku->lu_stateowner; } nfs4_unlock_state(); return status; out_nfserr: - status = nfserrno(status); + status = nfserrno(err); goto out; } @@ -2950,7 +2997,7 @@ static int check_for_locks(struct file *filp, struct nfs4_stateowner *lowner) { struct file_lock **flpp; - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; int status = 0; lock_kernel(); @@ -2965,8 +3012,10 @@ out: return status; } -int -nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_release_lockowner *rlockowner) +__be32 +nfsd4_release_lockowner(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_release_lockowner *rlockowner) { clientid_t *clid = &rlockowner->rl_clientid; struct nfs4_stateowner *sop; @@ -2974,7 +3023,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_release_lockowner * struct xdr_netobj *owner = &rlockowner->rl_owner; struct list_head matches; int i; - int status; + __be32 status; dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); @@ -2995,7 +3044,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_release_lockowner * 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) { @@ -3017,7 +3066,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_release_lockowner * /* unhash_stateowner deletes so_perclient only * for openowners. */ list_del(&sop->so_perclient); - release_stateowner(sop); + release_lockowner(sop); } out: nfs4_unlock_state(); @@ -3111,7 +3160,7 @@ nfs4_find_reclaim_client(clientid_t *clid) /* * Called from OPEN. Look for clientid in reclaim list. */ -int +__be32 nfs4_check_open_reclaim(clientid_t *clid) { return nfs4_find_reclaim_client(clid) ? nfs_ok : nfserr_reclaim_bad; @@ -3119,11 +3168,14 @@ 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]); @@ -3152,6 +3204,7 @@ 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 @@ -3167,42 +3220,60 @@ 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 @@ -3242,7 +3313,6 @@ __nfs4_state_shutdown(void) unhash_delegation(dp); } - cancel_delayed_work(&laundromat_work); nfsd4_shutdown_recdir(); nfs4_init = 0; } @@ -3252,19 +3322,21 @@ 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(); } /* @@ -3274,20 +3346,26 @@ 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. * @@ -3296,11 +3374,12 @@ 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(); }