X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fnfsd%2Fnfs4state.c;h=6bbefd06f10dea127ee0bf406eb1ef01fcfd4247;hb=fa82a491275a613b15489aab4b99acecb00958d3;hp=72f2b6fdae6633986c160a356112136b989fd93d;hpb=28ce6054f1de89834e5e9522f9e451cd88a35f85;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 72f2b6f..b6f60f4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -48,50 +49,59 @@ #include #include #include +#include +#include +#include +#include +#include +#include #define NFSDDBG_FACILITY NFSDDBG_PROC /* Globals */ static time_t lease_time = 90; /* default lease time */ static time_t user_lease_time = 90; -time_t boot_time; -static time_t grace_end = 0; -static u32 current_clientid = 1; +static time_t boot_time; static u32 current_ownerid = 1; static u32 current_fileid = 1; static u32 current_delegid = 1; static u32 nfs4_init; -stateid_t zerostateid; /* bits all 0 */ -stateid_t onestateid; /* bits all 1 */ +static stateid_t zerostateid; /* bits all 0 */ +static stateid_t onestateid; /* bits all 1 */ + +#define ZERO_STATEID(stateid) (!memcmp((stateid), &zerostateid, sizeof(stateid_t))) +#define ONE_STATEID(stateid) (!memcmp((stateid), &onestateid, sizeof(stateid_t))) /* forward declarations */ -struct nfs4_stateid * find_stateid(stateid_t *stid, int flags); +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_sema: + * client_mutex: * protects clientid_hashtbl[], clientstr_hashtbl[], * unconfstr_hashtbl[], uncofid_hashtbl[]. */ -static DECLARE_MUTEX(client_sema); +static DEFINE_MUTEX(client_mutex); -kmem_cache_t *stateowner_slab = NULL; -kmem_cache_t *file_slab = NULL; -kmem_cache_t *stateid_slab = NULL; -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) { - down(&client_sema); + mutex_lock(&client_mutex); } void nfs4_unlock_state(void) { - up(&client_sema); + mutex_unlock(&client_mutex); } static inline u32 @@ -116,7 +126,7 @@ static void release_stateid(struct nfs4_stateid *stp, int flags); */ /* recall_lock protects the del_recall_lru */ -spinlock_t recall_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_SPINLOCK(recall_lock); static struct list_head del_recall_lru; static void @@ -140,6 +150,43 @@ get_nfs4_file(struct nfs4_file *fi) kref_get(&fi->fi_ref); } +static int num_delegations; +unsigned int max_delegations; + +/* + * Open owner state (share locks) + */ + +/* hash tables for nfs4_stateowner */ +#define OWNER_HASH_BITS 8 +#define OWNER_HASH_SIZE (1 << OWNER_HASH_BITS) +#define OWNER_HASH_MASK (OWNER_HASH_SIZE - 1) + +#define ownerid_hashval(id) \ + ((id) & OWNER_HASH_MASK) +#define ownerstr_hashval(clientid, ownername) \ + (((clientid) + opaque_hashval((ownername.data), (ownername.len))) & OWNER_HASH_MASK) + +static struct list_head ownerid_hashtbl[OWNER_HASH_SIZE]; +static struct list_head ownerstr_hashtbl[OWNER_HASH_SIZE]; + +/* hash table for nfs4_file */ +#define FILE_HASH_BITS 8 +#define FILE_HASH_SIZE (1 << FILE_HASH_BITS) +#define FILE_HASH_MASK (FILE_HASH_SIZE - 1) +/* hash table for (open)nfs4_stateid */ +#define STATEID_HASH_BITS 10 +#define STATEID_HASH_SIZE (1 << STATEID_HASH_BITS) +#define STATEID_HASH_MASK (STATEID_HASH_SIZE - 1) + +#define file_hashval(x) \ + hash_ptr(x, FILE_HASH_BITS) +#define stateid_hashval(owner_id, file_id) \ + (((owner_id) + (file_id)) & STATEID_HASH_MASK) + +static struct list_head file_hashtbl[FILE_HASH_SIZE]; +static struct list_head stateid_hashtbl[STATEID_HASH_SIZE]; + static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_fh *current_fh, u32 type) { @@ -148,11 +195,16 @@ 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 (fp->fi_had_conflict) + return NULL; + if (num_delegations > max_delegations) + return NULL; dp = kmem_cache_alloc(deleg_slab, GFP_KERNEL); if (dp == NULL) return dp; - INIT_LIST_HEAD(&dp->dl_del_perfile); - INIT_LIST_HEAD(&dp->dl_del_perclnt); + num_delegations++; + INIT_LIST_HEAD(&dp->dl_perfile); + INIT_LIST_HEAD(&dp->dl_perclnt); INIT_LIST_HEAD(&dp->dl_recall_lru); dp->dl_client = clp; get_nfs4_file(fp); @@ -173,8 +225,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f current_fh->fh_handle.fh_size); dp->dl_time = 0; atomic_set(&dp->dl_count, 1); - list_add(&dp->dl_del_perfile, &fp->fi_delegations); - list_add(&dp->dl_del_perclnt, &clp->cl_del_perclnt); + list_add(&dp->dl_perfile, &fp->fi_delegations); + list_add(&dp->dl_perclnt, &clp->cl_delegations); return dp; } @@ -185,6 +237,7 @@ nfs4_put_delegation(struct nfs4_delegation *dp) dprintk("NFSD: freeing dp %p\n",dp); put_nfs4_file(dp->dl_file); kmem_cache_free(deleg_slab, dp); + num_delegations--; } } @@ -203,7 +256,7 @@ 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); } @@ -211,8 +264,8 @@ nfs4_close_delegation(struct nfs4_delegation *dp) static void unhash_delegation(struct nfs4_delegation *dp) { - list_del_init(&dp->dl_del_perfile); - list_del_init(&dp->dl_del_perclnt); + list_del_init(&dp->dl_perfile); + list_del_init(&dp->dl_perclnt); spin_lock(&recall_lock); list_del_init(&dp->dl_recall_lru); spin_unlock(&recall_lock); @@ -287,30 +340,45 @@ 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 = kmalloc(sizeof(struct nfs4_client), GFP_KERNEL))!= NULL) { - memset(clp, 0, sizeof(*clp)); - 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); } @@ -327,26 +395,18 @@ expire_client(struct nfs4_client *clp) { struct nfs4_stateowner *sop; struct nfs4_delegation *dp; - struct nfs4_callback *cb = &clp->cl_callback; - struct rpc_clnt *clnt = clp->cl_callback.cb_client; struct list_head reaplist; dprintk("NFSD: expire_client cl_count %d\n", atomic_read(&clp->cl_count)); - /* shutdown rpc client, ending any outstanding recall rpcs */ - if (atomic_read(&cb->cb_set) == 1 && clnt) { - rpc_shutdown_client(clnt); - clnt = clp->cl_callback.cb_client = NULL; - } - INIT_LIST_HEAD(&reaplist); spin_lock(&recall_lock); - while (!list_empty(&clp->cl_del_perclnt)) { - dp = list_entry(clp->cl_del_perclnt.next, struct nfs4_delegation, dl_del_perclnt); + while (!list_empty(&clp->cl_delegations)) { + dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); dprintk("NFSD: expire client. dp %p, fp %p\n", dp, dp->dl_flock); - list_del_init(&dp->dl_del_perclnt); + list_del_init(&dp->dl_perclnt); list_move(&dp->dl_recall_lru, &reaplist); } spin_unlock(&recall_lock); @@ -358,105 +418,105 @@ expire_client(struct nfs4_client *clp) list_del(&clp->cl_idhash); list_del(&clp->cl_strhash); list_del(&clp->cl_lru); - while (!list_empty(&clp->cl_perclient)) { - sop = list_entry(clp->cl_perclient.next, struct nfs4_stateowner, so_perclient); + while (!list_empty(&clp->cl_openowners)) { + sop = list_entry(clp->cl_openowners.next, struct nfs4_stateowner, so_perclient); release_stateowner(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); - clp->cl_callback.cb_parsed = 0; INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_strhash); - INIT_LIST_HEAD(&clp->cl_perclient); - INIT_LIST_HEAD(&clp->cl_del_perclnt); + 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; } -void +static void add_to_unconfirmed(struct nfs4_client *clp, unsigned int strhashval) { unsigned int idhashval; @@ -468,7 +528,7 @@ add_to_unconfirmed(struct nfs4_client *clp, unsigned int strhashval) clp->cl_time = get_seconds(); } -void +static void move_to_confirmed(struct nfs4_client *clp) { unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id); @@ -476,8 +536,7 @@ move_to_confirmed(struct nfs4_client *clp) dprintk("NFSD: move_to_confirm nfs4_client %p\n", clp); list_del_init(&clp->cl_strhash); - list_del_init(&clp->cl_idhash); - list_add(&clp->cl_idhash, &conf_id_hashtbl[idhashval]); + list_move(&clp->cl_idhash, &conf_id_hashtbl[idhashval]); strhashval = clientstr_hashval(clp->cl_recdir); list_add(&clp->cl_strhash, &conf_str_hashtbl[strhashval]); renew_client(clp); @@ -490,7 +549,7 @@ 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; @@ -503,7 +562,7 @@ 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; @@ -567,7 +626,7 @@ parse_octet(unsigned int *lenp, char **addrp) } /* parse and set the setclientid ipv4 callback address */ -int +static int parse_ipv4(unsigned int addr_len, char *addr_val, unsigned int *cbaddrp, unsigned short *cbportp) { int temp = 0; @@ -603,7 +662,7 @@ parse_ipv4(unsigned int addr_len, char *addr_val, unsigned int *cbaddrp, unsigne return 1; } -void +static void gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se) { struct nfs4_callback *cb = &clp->cl_callback; @@ -617,54 +676,20 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se) goto out_err; cb->cb_prog = se->se_callback_prog; cb->cb_ident = se->se_callback_ident; - cb->cb_parsed = 1; return; out_err: - printk(KERN_INFO "NFSD: this client (clientid %08x/%08x) " + dprintk(KERN_INFO "NFSD: this client (clientid %08x/%08x) " "will not receive delegations\n", clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); - cb->cb_parsed = 0; 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, @@ -672,16 +697,16 @@ 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]; - status = nfserr_inval; if (!check_name(clname)) - goto out; + return nfserr_inval; status = nfs4_make_rec_clidname(dname, &clname); if (status) - goto out; + return status; /* * XXX The Duplicate Request Cache (DRC) has been checked (??) @@ -693,120 +718,87 @@ 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) && - cmp_verf(&unconf->cl_verifier, &conf->cl_verifier) && - cmp_clid(&unconf->cl_clientid, &conf->cl_clientid)) { - expire_client(unconf); + if (unconf) { + /* Note this is removing unconfirmed {*x***}, + * which is stronger than RFC recommended {vxc**}. + * This has the advantage that there is at most + * one {*x***} in either list at any time. + */ + expire_client(unconf); } 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)); @@ -818,20 +810,20 @@ 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 nfs4_client *clp, *conf = NULL, *unconf = NULL; + 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; @@ -841,140 +833,87 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confi */ nfs4_lock_state(); - clp = find_confirmed_client(clid); - if (clp) { - status = nfserr_inval; - /* - * Found a record for this clientid. If the IP addresses - * don't match, return ERR_INVAL just as if the record had - * not been found. + + conf = find_confirmed_client(clid); + unconf = find_unconfirmed_client(clid); + + status = nfserr_clid_inuse; + if (conf && conf->cl_addr != sin->sin_addr.s_addr) + goto out; + if (unconf && unconf->cl_addr != sin->sin_addr.s_addr) + goto out; + + /* + * 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 (clp->cl_addr != ip_addr) { - printk("NFSD: setclientid: string in use by client" - "(clientid %08x/%08x)\n", - clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); - goto out; - } - conf = clp; - } - clp = find_unconfirmed_client(clid); - if (clp) { - status = nfserr_inval; - if (clp->cl_addr != ip_addr) { - printk("NFSD: setclientid: string in use by client" - "(clientid %08x/%08x)\n", - clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); - goto out; - } - unconf = clp; - } - /* 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 ((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))) { - if (!cmp_creds(&conf->cl_cred, &unconf->cl_cred)) + if (!same_creds(&conf->cl_cred, &unconf->cl_cred)) status = nfserr_clid_inuse; else { - expire_client(conf); - clp = unconf; - move_to_confirmed(unconf); + /* XXX: We just turn off callbacks until we can handle + * change request correctly. */ + atomic_set(&conf->cl_callback.cb_set, 0); + gen_confirm(conf); + nfsd4_remove_clid_dir(unconf); + expire_client(unconf); status = nfs_ok; + } - goto out; - } - /* CASE 2: - * conf record that matches input clientid. - * if unconf record that matches input clientid, then unconf->cl_name - * or unconf->cl_verifier don't match the conf record. - */ - if ((conf && !unconf) || - ((conf && unconf) && - (!cmp_verf(&conf->cl_verifier, &unconf->cl_verifier) || - !same_name(conf->cl_recdir, unconf->cl_recdir)))) { - if (!cmp_creds(&conf->cl_cred,&rqstp->rq_cred)) { + } else if (conf && !unconf) { + /* + * RFC 3530 14.2.34 CASE 2: + * probable retransmitted request; play it safe and + * do nothing. + */ + if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) status = nfserr_clid_inuse; - } else { - clp = conf; + else status = nfs_ok; - } - goto out; - } - /* CASE 3: - * conf record not found. - * unconf record found. - * unconf->cl_confirm matches input confirm - */ - if (!conf && unconf && cmp_verf(&unconf->cl_confirm, &confirm)) { - if (!cmp_creds(&unconf->cl_cred, &rqstp->rq_cred)) { + } else if (!conf && unconf + && same_verf(&unconf->cl_confirm, &confirm)) { + /* + * RFC 3530 14.2.34 CASE 3: + * Normal case; new or rebooted client: + */ + if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { status = nfserr_clid_inuse; } else { - status = nfs_ok; - clp = unconf; + unsigned int hash = + clientstr_hashval(unconf->cl_recdir); + conf = find_confirmed_client_by_str(unconf->cl_recdir, + hash); + if (conf) { + nfsd4_remove_clid_dir(conf); + expire_client(conf); + } move_to_confirmed(unconf); + conf = unconf; + nfsd4_probe_callback(conf); + status = nfs_ok; } - goto out; - } - /* CASE 4: - * conf record not found, or if conf, then conf->cl_confirm does not - * match input confirm. - * unconf record not found, or if unconf, then unconf->cl_confirm - * does not match input confirm. - */ - if ((!conf || (conf && !cmp_verf(&conf->cl_confirm, &confirm))) && - (!unconf || (unconf && !cmp_verf(&unconf->cl_confirm, &confirm)))) { + } else if ((!conf || (conf && !same_verf(&conf->cl_confirm, &confirm))) + && (!unconf || (unconf && !same_verf(&unconf->cl_confirm, + &confirm)))) { + /* + * RFC 3530 14.2.34 CASE 4: + * Client probably hasn't noticed that we rebooted yet. + */ status = nfserr_stale_clientid; - goto out; + } else { + /* check that we have hit one of the cases...*/ + status = nfserr_clid_inuse; } - /* check that we have hit one of the cases...*/ - status = nfserr_inval; - goto out; out: - if (!status) - nfsd4_probe_callback(clp); nfs4_unlock_state(); return status; } -/* - * Open owner state (share locks) - */ - -/* hash tables for nfs4_stateowner */ -#define OWNER_HASH_BITS 8 -#define OWNER_HASH_SIZE (1 << OWNER_HASH_BITS) -#define OWNER_HASH_MASK (OWNER_HASH_SIZE - 1) - -#define ownerid_hashval(id) \ - ((id) & OWNER_HASH_MASK) -#define ownerstr_hashval(clientid, ownername) \ - (((clientid) + opaque_hashval((ownername.data), (ownername.len))) & OWNER_HASH_MASK) - -static struct list_head ownerid_hashtbl[OWNER_HASH_SIZE]; -static struct list_head ownerstr_hashtbl[OWNER_HASH_SIZE]; - -/* hash table for nfs4_file */ -#define FILE_HASH_BITS 8 -#define FILE_HASH_SIZE (1 << FILE_HASH_BITS) -#define FILE_HASH_MASK (FILE_HASH_SIZE - 1) -/* hash table for (open)nfs4_stateid */ -#define STATEID_HASH_BITS 10 -#define STATEID_HASH_SIZE (1 << STATEID_HASH_BITS) -#define STATEID_HASH_MASK (STATEID_HASH_SIZE - 1) - -#define file_hashval(x) \ - hash_ptr(x, FILE_HASH_BITS) -#define stateid_hashval(owner_id, file_id) \ - (((owner_id) + (file_id)) & STATEID_HASH_MASK) - -static struct list_head file_hashtbl[FILE_HASH_SIZE]; -static struct list_head stateid_hashtbl[STATEID_HASH_SIZE]; - /* OPEN Share state helper functions */ static inline struct nfs4_file * alloc_init_file(struct inode *ino) @@ -991,24 +930,22 @@ 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) { - int status; - if (*slab == NULL) return; - status = kmem_cache_destroy(*slab); + kmem_cache_destroy(*slab); *slab = NULL; - WARN_ON(status); } -static void +void nfsd4_free_slabs(void) { nfsd4_free_slab(&stateowner_slab); @@ -1021,19 +958,19 @@ 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; @@ -1081,20 +1018,20 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp, str INIT_LIST_HEAD(&sop->so_idhash); INIT_LIST_HEAD(&sop->so_strhash); INIT_LIST_HEAD(&sop->so_perclient); - INIT_LIST_HEAD(&sop->so_perfilestate); - INIT_LIST_HEAD(&sop->so_perlockowner); /* not used */ + INIT_LIST_HEAD(&sop->so_stateids); + INIT_LIST_HEAD(&sop->so_perstateid); /* not used */ INIT_LIST_HEAD(&sop->so_close_lru); sop->so_time = 0; list_add(&sop->so_idhash, &ownerid_hashtbl[idhashval]); list_add(&sop->so_strhash, &ownerstr_hashtbl[strhashval]); - list_add(&sop->so_perclient, &clp->cl_perclient); + list_add(&sop->so_perclient, &clp->cl_openowners); sop->so_is_open_owner = 1; sop->so_id = current_ownerid++; sop->so_client = clp; sop->so_seqid = open->op_seqid; sop->so_confirmed = 0; rp = &sop->so_replay; - rp->rp_status = NFSERR_SERVERFAULT; + rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; return sop; @@ -1105,10 +1042,10 @@ release_stateid_lockowners(struct nfs4_stateid *open_stp) { struct nfs4_stateowner *lock_sop; - while (!list_empty(&open_stp->st_perlockowner)) { - lock_sop = list_entry(open_stp->st_perlockowner.next, - struct nfs4_stateowner, so_perlockowner); - /* list_del(&open_stp->st_perlockowner); */ + 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); } @@ -1123,10 +1060,10 @@ unhash_stateowner(struct nfs4_stateowner *sop) list_del(&sop->so_strhash); if (sop->so_is_open_owner) list_del(&sop->so_perclient); - list_del(&sop->so_perlockowner); - while (!list_empty(&sop->so_perfilestate)) { - stp = list_entry(sop->so_perfilestate.next, - struct nfs4_stateid, st_perfilestate); + 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 @@ -1148,11 +1085,11 @@ init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open * unsigned int hashval = stateid_hashval(sop->so_id, fp->fi_id); INIT_LIST_HEAD(&stp->st_hash); - INIT_LIST_HEAD(&stp->st_perfilestate); - INIT_LIST_HEAD(&stp->st_perlockowner); + INIT_LIST_HEAD(&stp->st_perstateowner); + INIT_LIST_HEAD(&stp->st_lockowners); INIT_LIST_HEAD(&stp->st_perfile); list_add(&stp->st_hash, &stateid_hashtbl[hashval]); - list_add(&stp->st_perfilestate, &sop->so_perfilestate); + list_add(&stp->st_perstateowner, &sop->so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); stp->st_stateowner = sop; get_nfs4_file(fp); @@ -1165,6 +1102,7 @@ init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open * stp->st_deny_bmap = 0; __set_bit(open->op_share_access, &stp->st_access_bmap); __set_bit(open->op_share_deny, &stp->st_deny_bmap); + stp->st_openstp = NULL; } static void @@ -1174,7 +1112,7 @@ release_stateid(struct nfs4_stateid *stp, int flags) list_del(&stp->st_hash); list_del(&stp->st_perfile); - list_del(&stp->st_perfilestate); + list_del(&stp->st_perstateowner); if (flags & OPEN_STATE) { release_stateid_lockowners(stp); stp->st_vfs_file = NULL; @@ -1183,40 +1121,24 @@ release_stateid(struct nfs4_stateid *stp, int flags) locks_remove_posix(filp, (fl_owner_t) stp->st_stateowner); put_nfs4_file(stp->st_file); kmem_cache_free(stateid_slab, stp); - stp = NULL; } -void +static void move_to_close_lru(struct nfs4_stateowner *sop) { dprintk("NFSD: move_to_close_lru nfs4_stateowner %p\n", sop); - unhash_stateowner(sop); - list_add_tail(&sop->so_close_lru, &close_lru); + list_move_tail(&sop->so_close_lru, &close_lru); sop->so_time = get_seconds(); } -void -release_state_owner(struct nfs4_stateid *stp, int flag) -{ - struct nfs4_stateowner *sop = stp->st_stateowner; - - dprintk("NFSD: release_state_owner\n"); - release_stateid(stp, flag); - - /* place unused nfs4_stateowners on so_close_lru list to be - * released by the laundromat service after the lease period - * to enable us to handle CLOSE replay - */ - if (sop->so_confirmed && list_empty(&sop->so_perfilestate)) - move_to_close_lru(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 * @@ -1225,7 +1147,7 @@ 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; @@ -1247,10 +1169,40 @@ find_file(struct inode *ino) return NULL; } -#define TEST_ACCESS(x) ((x > 0 || x < 4)?1:0) -#define TEST_DENY(x) ((x >= 0 || x < 5)?1:0) +static inline int access_valid(u32 x) +{ + if (x < NFS4_SHARE_ACCESS_READ) + return 0; + if (x > NFS4_SHARE_ACCESS_BOTH) + return 0; + return 1; +} + +static inline int deny_valid(u32 x) +{ + /* Note: unlike access bits, deny bits may be zero. */ + return x <= NFS4_SHARE_DENY_BOTH; +} -void +/* + * 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; @@ -1261,7 +1213,7 @@ set_access(unsigned int *access, unsigned long bmap) { } } -void +static void set_deny(unsigned int *deny, unsigned long bmap) { int i; @@ -1287,20 +1239,20 @@ 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 */ -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"); fp = find_file(ino); if (!fp) return nfs_ok; - ret = nfserr_share_denied; + ret = nfserr_locked; /* Search for conflicting share reservations */ list_for_each_entry(stp, &fp->fi_stateids, st_perfile) { if (test_bit(deny_type, &stp->st_deny_bmap) || @@ -1317,7 +1269,7 @@ 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; } } @@ -1330,8 +1282,7 @@ 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; } @@ -1360,6 +1311,7 @@ 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); @@ -1368,8 +1320,12 @@ 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)) { @@ -1378,6 +1334,7 @@ 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); } } @@ -1402,7 +1359,7 @@ 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) @@ -1416,7 +1373,7 @@ 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) @@ -1442,7 +1399,7 @@ int nfsd_change_deleg_cb(struct file_lock **onlist, int arg) return -EAGAIN; } -struct lock_manager_operations nfsd_lease_mng_ops = { +static struct lock_manager_operations nfsd_lease_mng_ops = { .fl_break = nfsd_break_deleg_cb, .fl_release_private = nfsd_release_deleg_cb, .fl_copy_lock = nfsd_copy_lock_deleg_cb, @@ -1451,97 +1408,64 @@ struct lock_manager_operations nfsd_lease_mng_ops = { }; -/* - * nfsd4_process_open1() - * lookup stateowner. - * found: - * check confirmed - * confirmed: - * check seqid - * not confirmed: - * delete owner - * create new owner - * notfound: - * verify clientid - * create new owner - * - * called with nfs4_lock_state() held. - */ -int +__be32 nfsd4_process_open1(struct nfsd4_open *open) { - int status; clientid_t *clientid = &open->op_clientid; struct nfs4_client *clp = NULL; unsigned int strhashval; struct nfs4_stateowner *sop = NULL; - status = nfserr_inval; if (!check_name(open->op_owner)) - goto out; + return nfserr_inval; if (STALE_CLIENTID(&open->op_clientid)) return nfserr_stale_clientid; strhashval = ownerstr_hashval(clientid->cl_id, open->op_owner); sop = find_openstateowner_str(strhashval, open); - if (sop) { - open->op_stateowner = sop; - /* check for replay */ - if (open->op_seqid == sop->so_seqid){ - if (sop->so_replay.rp_buflen) - return NFSERR_REPLAY_ME; - else { - /* The original OPEN failed so spectacularly - * that we don't even have replay data saved! - * Therefore, we have no choice but to continue - * processing this OPEN; presumably, we'll - * fail again for the same reason. - */ - dprintk("nfsd4_process_open1:" - " replay with no replay cache\n"); - goto renew; - } - } else if (sop->so_confirmed) { - if (open->op_seqid == sop->so_seqid + 1) - goto renew; - status = nfserr_bad_seqid; - goto out; - } else { - /* If we get here, we received an OPEN for an - * unconfirmed nfs4_stateowner. Since the seqid's are - * different, purge the existing nfs4_stateowner, and - * instantiate a new one. - */ - clp = sop->so_client; - release_stateowner(sop); - } - } else { - /* nfs4_stateowner not found. - * Verify clientid and instantiate new nfs4_stateowner. - * If verify fails this is presumably the result of the - * client's lease expiring. - */ - status = nfserr_expired; + open->op_stateowner = sop; + if (!sop) { + /* Make sure the client's lease hasn't expired. */ clp = find_confirmed_client(clientid); if (clp == NULL) - goto out; + return nfserr_expired; + goto renew; } - status = nfserr_resource; - sop = alloc_init_open_stateowner(strhashval, clp, open); - if (sop == NULL) - goto out; - open->op_stateowner = sop; + if (!sop->so_confirmed) { + /* Replace unconfirmed owners without checking for replay. */ + clp = sop->so_client; + release_stateowner(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; + /* The original OPEN failed so spectacularly + * that we don't even have replay data saved! + * Therefore, we have no choice but to continue + * processing this OPEN; presumably, we'll + * fail again for the same reason. + */ + dprintk("nfsd4_process_open1: replay with no replay cache\n"); + goto renew; + } + if (open->op_seqid != sop->so_seqid) + return nfserr_bad_seqid; renew: - status = nfs_ok; + if (open->op_stateowner == NULL) { + sop = alloc_init_open_stateowner(strhashval, clp, open); + if (sop == NULL) + return nfserr_resource; + open->op_stateowner = sop; + } + list_del_init(&sop->so_close_lru); renew_client(sop->so_client); -out: - if (status && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) - status = nfserr_reclaim_bad; - return status; + 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)) @@ -1555,19 +1479,19 @@ find_delegation_file(struct nfs4_file *fp, stateid_t *stid) { struct nfs4_delegation *dp; - list_for_each_entry(dp, &fp->fi_delegations, dl_del_perfile) { + list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) { if (dp->dl_stateid.si_stateownerid == stid->si_stateownerid) return dp; } 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) @@ -1586,11 +1510,11 @@ 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) { @@ -1615,7 +1539,7 @@ 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) @@ -1630,7 +1554,7 @@ 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) { @@ -1644,7 +1568,7 @@ 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) { @@ -1655,54 +1579,51 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, if (!open->op_truncate) return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) - return -EINVAL; + return nfserr_inval; 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; - unsigned int share_access; - int status; + struct inode *inode = filp->f_path.dentry->d_inode; + unsigned int share_access, new_writer; + __be32 status; set_access(&share_access, stp->st_access_bmap); - share_access = ~share_access; - share_access &= open->op_share_access; - - if (!(share_access & NFS4_SHARE_ACCESS_WRITE)) - return nfsd4_truncate(rqstp, cur_fh, open); - - status = get_write_access(inode); - if (status) - return nfserrno(status); + new_writer = (~share_access) & open->op_share_access + & NFS4_SHARE_ACCESS_WRITE; + + if (new_writer) { + 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) { - put_write_access(inode); + if (new_writer) + put_write_access(inode); return status; } /* remember the open */ - filp->f_mode = (filp->f_mode | FMODE_WRITE) & ~FMODE_READ; - set_bit(open->op_share_access, &stp->st_access_bmap); - set_bit(open->op_share_deny, &stp->st_deny_bmap); + 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); return nfs_ok; } -/* decrement seqid on successful reclaim, it will be bumped in encode_open */ static void -nfs4_set_claim_prev(struct nfsd4_open *open, int *status) +nfs4_set_claim_prev(struct nfsd4_open *open) { - if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) { - if (*status) - *status = nfserr_reclaim_bad; - else { - open->op_stateowner->so_confirmed = 1; - open->op_stateowner->so_seqid--; - } - } + open->op_stateowner->so_confirmed = 1; + open->op_stateowner->so_client->cl_firststate = 1; } /* @@ -1730,7 +1651,7 @@ 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; @@ -1751,16 +1672,16 @@ 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; @@ -1778,24 +1699,25 @@ 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 (!TEST_ACCESS(open->op_share_access) || !TEST_DENY(open->op_share_deny)) + if (!access_valid(open->op_share_access) + || !deny_valid(open->op_share_deny)) goto out; /* * Lookup file; if found, lookup stateid and check open request, @@ -1828,13 +1750,14 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs4_upgrade_open(rqstp, current_fh, stp, open); if (status) goto out; + update_stateid(&stp->st_stateid); } else { /* Stateid was not found, this is a new OPEN */ int flags = 0; + if (open->op_share_access & NFS4_SHARE_ACCESS_READ) + flags |= NFSD_MAY_READ; if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) - flags = MAY_WRITE; - else - flags = MAY_READ; + flags |= NFSD_MAY_WRITE; status = nfs4_new_open(rqstp, &stp, dp, current_fh, flags); if (status) goto out; @@ -1861,8 +1784,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf out: if (fp) put_nfs4_file(fp); - /* CLAIM_PREVIOUS has different error returns */ - nfs4_set_claim_prev(open, &status); + if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) + nfs4_set_claim_prev(open); /* * To finish the open response, we just need to set the rflags. */ @@ -1873,16 +1796,12 @@ 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", @@ -1899,7 +1818,7 @@ nfsd4_renew(clientid_t *clid) } renew_client(clp); status = nfserr_cb_path_down; - if (!list_empty(&clp->cl_del_perclnt) + if (!list_empty(&clp->cl_delegations) && !atomic_read(&clp->cl_callback.cb_set)) goto out; status = nfs_ok; @@ -1908,7 +1827,18 @@ out: return status; } -time_t +struct lock_manager nfsd4_manager = { +}; + +static void +nfsd4_end_grace(void) +{ + dprintk("NFSD: end of grace period\n"); + nfsd4_recdir_purge_old(); + locks_end_grace(&nfsd4_manager); +} + +static time_t nfs4_laundromat(void) { struct nfs4_client *clp; @@ -1922,6 +1852,8 @@ nfs4_laundromat(void) nfs4_lock_state(); dprintk("NFSD: laundromat service - starting\n"); + 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)) { @@ -1932,6 +1864,7 @@ nfs4_laundromat(void) } dprintk("NFSD: purging unused client (clientid %08x)\n", clp->cl_clientid.cl_id); + nfsd4_remove_clid_dir(clp); expire_client(clp); } INIT_LIST_HEAD(&reaplist); @@ -1965,8 +1898,7 @@ nfs4_laundromat(void) } dprintk("NFSD: purging unused open stateowner (so_id %d)\n", sop->so_id); - list_del(&sop->so_close_lru); - nfs4_put_stateowner(sop); + release_stateowner(sop); } if (clientid_val < NFSD_LAUNDROMAT_MINTIMEOUT) clientid_val = NFSD_LAUNDROMAT_MINTIMEOUT; @@ -1974,8 +1906,12 @@ 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; @@ -1984,14 +1920,11 @@ laundromat_main(void *not_used) queue_delayed_work(laundry_wq, &laundromat_work, t*HZ); } -/* search ownerid_hashtbl[] and close_lru for stateid owner - * (stateid->si_stateownerid) - */ -struct nfs4_stateowner * -find_openstateowner_id(u32 st_id, int flags) { +static struct nfs4_stateowner * +search_close_lru(u32 st_id, int flags) +{ struct nfs4_stateowner *local = NULL; - dprintk("NFSD: find_openstateowner_id %d\n", st_id); if (flags & CLOSE_STATE) { list_for_each_entry(local, &close_lru, so_close_lru) { if (local->so_id == st_id) @@ -2004,7 +1937,7 @@ find_openstateowner_id(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 @@ -2012,7 +1945,7 @@ STALE_STATEID(stateid_t *stateid) { if (stateid->si_boot == boot_time) return 0; - printk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n", + dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n", stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid, stateid->si_generation); return 1; @@ -2034,9 +1967,9 @@ 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; @@ -2047,7 +1980,7 @@ 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: */ @@ -2055,7 +1988,7 @@ check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags) return nfserr_bad_stateid; else 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; @@ -2074,21 +2007,41 @@ 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() && (flags & (RD_STATE | WR_STATE)) + && 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; } /* * 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, @@ -2112,16 +2065,12 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl if (!stateid->si_fileid) { /* delegation stateid */ if(!(dp = find_delegation_stateid(ino, stateid))) { dprintk("NFSD: delegation stateid not found\n"); - if (nfs4_in_grace()) - status = nfserr_grace; goto out; } stidp = &dp->dl_stateid; } else { /* open or lock stateid */ if (!(stp = find_stateid(stateid, flags))) { dprintk("NFSD: open or lock stateid not found\n"); - if (nfs4_in_grace()) - status = nfserr_grace; goto out; } if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp)) @@ -2130,12 +2079,8 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl 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) + status = check_stateid_generation(stateid, stidp); + if (status) goto out; if (stp) { if ((status = nfs4_check_openmode(stp,flags))) @@ -2143,7 +2088,7 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl renew_client(stp->st_stateowner->so_client); if (filpp) *filpp = stp->st_vfs_file; - } else if (dp) { + } else { if ((status = nfs4_check_delegmode(dp, flags))) goto out; renew_client(dp->dl_client); @@ -2157,156 +2102,146 @@ out: return status; } +static inline int +setlkflg (int type) +{ + return (type == NFS4_READW_LT || type == NFS4_READ_LT) ? + RD_STATE : WR_STATE; +} /* * Checks for sequence id mutating operations. */ -int -nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *stateid, int flags, struct nfs4_stateowner **sopp, struct nfs4_stateid **stpp, clientid_t *lockclid) +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) { - int status; struct nfs4_stateid *stp; struct nfs4_stateowner *sop; + __be32 status; dprintk("NFSD: preprocess_seqid_op: seqid=%d " "stateid = (%08x/%08x/%08x/%08x)\n", seqid, stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid, stateid->si_generation); - + *stpp = NULL; *sopp = NULL; - status = nfserr_bad_stateid; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { - printk("NFSD: preprocess_seqid_op: magic stateid!\n"); - goto out; + dprintk("NFSD: preprocess_seqid_op: magic stateid!\n"); + return nfserr_bad_stateid; } - status = nfserr_stale_stateid; if (STALE_STATEID(stateid)) - goto out; + return nfserr_stale_stateid; /* * We return BAD_STATEID if filehandle doesn't match stateid, * the confirmed flag is incorrecly set, or the generation * number is incorrect. - * If there is no entry in the openfile table for this id, - * we can't always return BAD_STATEID; - * this might be a retransmitted CLOSE which has arrived after - * the openfile has been released. */ - if (!(stp = find_stateid(stateid, flags))) - goto no_nfs4_stateid; + stp = find_stateid(stateid, flags); + if (stp == NULL) { + /* + * Also, we should make sure this isn't just the result of + * a replayed close: + */ + sop = search_close_lru(stateid->si_stateownerid, flags); + if (sop == NULL) + return nfserr_bad_stateid; + *sopp = sop; + goto check_replay; + } - status = nfserr_bad_stateid; + *stpp = stp; + *sopp = sop = stp->st_stateowner; - /* for new lock stateowners: - * check that the lock->v.new.open_stateid - * refers to an open stateowner - * - * check that the lockclid (nfs4_lock->v.new.clientid) is the same - * as the open_stateid->st_stateowner->so_client->clientid - */ - if (lockclid) { - struct nfs4_stateowner *sop = stp->st_stateowner; + if (lock) { + clientid_t *lockclid = &lock->v.new.clientid; struct nfs4_client *clp = sop->so_client; - - if (!sop->so_is_open_owner) - goto out; - if (!cmp_clid(&clp->cl_clientid, lockclid)) - goto out; + int lkflg = 0; + __be32 status; + + lkflg = setlkflg(lock->lk_type); + + if (lock->lk_is_new) { + if (!sop->so_is_open_owner) + return nfserr_bad_stateid; + if (!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"); - goto out; + 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 + 1) + if (seqid != sop->so_seqid) goto check_replay; - if (sop->so_confirmed) { - if (flags & CONFIRM) { - printk("NFSD: preprocess_seqid_op: expected unconfirmed stateowner!\n"); - goto out; - } - } - else { - if (!(flags & CONFIRM)) { - printk("NFSD: preprocess_seqid_op: stateowner not confirmed yet!\n"); - goto out; - } - } - if (stateid->si_generation > stp->st_stateid.si_generation) { - printk("NFSD: preprocess_seqid_op: future stateid?!\n"); - goto out; - } - - status = nfserr_old_stateid; - if (stateid->si_generation < stp->st_stateid.si_generation) { - printk("NFSD: preprocess_seqid_op: old stateid!\n"); - goto out; + if (sop->so_confirmed && flags & CONFIRM) { + dprintk("NFSD: preprocess_seqid_op: expected" + " unconfirmed stateowner!\n"); + return nfserr_bad_stateid; } - /* XXX renew the client lease here */ - status = nfs_ok; - -out: - return status; - -no_nfs4_stateid: - - /* - * We determine whether this is a bad stateid or a replay, - * starting by trying to look up the stateowner. - * If stateowner is not found - stateid is bad. - */ - if (!(sop = find_openstateowner_id(stateid->si_stateownerid, flags))) { - printk("NFSD: preprocess_seqid_op: no stateowner or nfs4_stateid!\n"); - status = nfserr_bad_stateid; - goto out; + if (!sop->so_confirmed && !(flags & CONFIRM)) { + dprintk("NFSD: preprocess_seqid_op: stateowner not" + " confirmed yet!\n"); + return nfserr_bad_stateid; } - *sopp = sop; + status = check_stateid_generation(stateid, &stp->st_stateid); + if (status) + return status; + renew_client(sop->so_client); + return nfs_ok; check_replay: - if (seqid == sop->so_seqid) { - printk("NFSD: preprocess_seqid_op: retransmission?\n"); + if (seqid == sop->so_seqid - 1) { + dprintk("NFSD: preprocess_seqid_op: retransmission?\n"); /* indicate replay to calling function */ - status = NFSERR_REPLAY_ME; - } else { - printk("NFSD: preprocess_seqid_op: bad seqid (expected %d, got %d\n", sop->so_seqid +1, seqid); - - *sopp = NULL; - status = nfserr_bad_seqid; + return nfserr_replay_me; } - goto out; + 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) +__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); - if ((status = fh_verify(rqstp, current_fh, S_IFREG, 0))) - goto out; + 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; @@ -2320,9 +2255,13 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs stp->st_stateid.si_stateownerid, stp->st_stateid.si_fileid, stp->st_stateid.si_generation); + + nfsd4_create_clid_dir(sop->so_client); out: - if (oc->oc_stateowner) + if (oc->oc_stateowner) { nfs4_get_stateowner(oc->oc_stateowner); + cstate->replay_owner = oc->oc_stateowner; + } nfs4_unlock_state(); return status; } @@ -2352,24 +2291,28 @@ 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) +__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 (!TEST_ACCESS(od->od_share_access) || !TEST_DENY(od->od_share_deny)) + 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; @@ -2395,8 +2338,10 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct n memcpy(&od->od_stateid, &stp->st_stateid, sizeof(stateid_t)); status = nfs_ok; out: - if (od->od_stateowner) + if (od->od_stateowner) { nfs4_get_stateowner(od->od_stateowner); + cstate->replay_owner = od->od_stateowner; + } nfs4_unlock_state(); return status; } @@ -2404,49 +2349,59 @@ out: /* * nfs4_unlock_state() called after encode */ -int -nfsd4_close(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_close *close) +__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; - /* - * Return success, but first update the stateid. - */ status = nfs_ok; update_stateid(&stp->st_stateid); memcpy(&close->cl_stateid, &stp->st_stateid, sizeof(stateid_t)); - /* release_state_owner() calls nfsd_close() if needed */ - release_state_owner(stp, OPEN_STATE); + /* release_stateid() calls nfsd_close() if needed */ + release_stateid(stp, OPEN_STATE); + + /* place unused nfs4_stateowners on so_close_lru list to be + * released by the laundromat service after the lease period + * to enable us to handle CLOSE replay + */ + if (list_empty(&close->cl_stateowner->so_stateids)) + move_to_close_lru(close->cl_stateowner); out: - if (close->cl_stateowner) + if (close->cl_stateowner) { nfs4_get_stateowner(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; + __be32 status; - if ((status = fh_verify(rqstp, current_fh, S_IFREG, 0))) + if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) goto out; nfs4_lock_state(); - status = nfs4_preprocess_stateid_op(current_fh, &dr->dr_stateid, DELEG_RET, NULL); + status = nfs4_preprocess_stateid_op(&cstate->current_fh, + &dr->dr_stateid, DELEG_RET, NULL); nfs4_unlock_state(); out: return status; @@ -2461,6 +2416,26 @@ 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) @@ -2477,16 +2452,16 @@ static struct list_head lock_ownerid_hashtbl[LOCK_HASH_SIZE]; static struct list_head lock_ownerstr_hashtbl[LOCK_HASH_SIZE]; static struct list_head lockstateid_hashtbl[STATEID_HASH_SIZE]; -struct nfs4_stateid * +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) && @@ -2494,15 +2469,15 @@ 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) && (local->st_stateid.si_fileid == f_id)) return local; } - } else - printk("NFSD: find_stateid: ERROR: no state flag\n"); + } return NULL; } @@ -2541,40 +2516,31 @@ nfs4_transform_lock_offset(struct file_lock *lock) lock->fl_end = OFFSET_MAX; } -int -nfs4_verify_lock_stateowner(struct nfs4_stateowner *sop, unsigned int hashval) -{ - struct nfs4_stateowner *local = NULL; - int status = 0; - - if (hashval >= LOCK_HASH_SIZE) - goto out; - list_for_each_entry(local, &lock_ownerid_hashtbl[hashval], so_idhash) { - if (local == sop) { - status = 1; - goto out; - } - } -out: - return status; -} - +/* Hack!: For now, we're defining this just so we can use a pointer to it + * as a unique cookie to identify our (NFSv4's) posix locks. */ +static struct lock_manager_operations nfsd_posix_mng_ops = { +}; static inline void nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) { - struct nfs4_stateowner *sop = (struct nfs4_stateowner *) fl->fl_owner; - unsigned int hval = lockownerid_hashval(sop->so_id); + struct nfs4_stateowner *sop; + unsigned int hval; - deny->ld_sop = NULL; - if (nfs4_verify_lock_stateowner(sop, hval)) { + if (fl->fl_lmops == &nfsd_posix_mng_ops) { + sop = (struct nfs4_stateowner *) fl->fl_owner; + hval = lockownerid_hashval(sop->so_id); kref_get(&sop->so_ref); deny->ld_sop = sop; deny->ld_clientid = sop->so_client->cl_clientid; + } else { + deny->ld_sop = NULL; + deny->ld_clientid.cl_boot = 0; + 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) @@ -2582,22 +2548,6 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) } static struct nfs4_stateowner * -find_lockstateowner(struct xdr_netobj *owner, clientid_t *clid) -{ - struct nfs4_stateowner *local = NULL; - int i; - - for (i = 0; i < LOCK_HASH_SIZE; i++) { - list_for_each_entry(local, &lock_ownerid_hashtbl[i], so_idhash) { - if (!cmp_owner_str(local, owner, clid)) - continue; - return local; - } - } - return NULL; -} - -static struct nfs4_stateowner * find_lockstateowner_str(struct inode *inode, clientid_t *clid, struct xdr_netobj *owner) { @@ -2605,7 +2555,7 @@ 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; @@ -2617,7 +2567,6 @@ find_lockstateowner_str(struct inode *inode, clientid_t *clid, * occured. * * strhashval = lock_ownerstr_hashval - * so_seqid = lock->lk_new_lock_seqid - 1: it gets bumped in encode */ static struct nfs4_stateowner * @@ -2632,26 +2581,28 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str INIT_LIST_HEAD(&sop->so_idhash); INIT_LIST_HEAD(&sop->so_strhash); INIT_LIST_HEAD(&sop->so_perclient); - INIT_LIST_HEAD(&sop->so_perfilestate); - INIT_LIST_HEAD(&sop->so_perlockowner); + INIT_LIST_HEAD(&sop->so_stateids); + INIT_LIST_HEAD(&sop->so_perstateid); INIT_LIST_HEAD(&sop->so_close_lru); /* not used */ sop->so_time = 0; list_add(&sop->so_idhash, &lock_ownerid_hashtbl[idhashval]); list_add(&sop->so_strhash, &lock_ownerstr_hashtbl[strhashval]); - list_add(&sop->so_perlockowner, &open_stp->st_perlockowner); + list_add(&sop->so_perstateid, &open_stp->st_lockowners); sop->so_is_open_owner = 0; sop->so_id = current_ownerid++; sop->so_client = clp; - sop->so_seqid = lock->lk_new_lock_seqid - 1; + /* It is the openowner seqid that will be incremented in encode in the + * case of new lockowners; so increment the lock seqid manually: */ + sop->so_seqid = lock->lk_new_lock_seqid + 1; sop->so_confirmed = 1; rp = &sop->so_replay; - rp->rp_status = NFSERR_SERVERFAULT; + rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; return sop; } -struct nfs4_stateid * +static struct nfs4_stateid * alloc_init_lock_stateid(struct nfs4_stateowner *sop, struct nfs4_file *fp, struct nfs4_stateid *open_stp) { struct nfs4_stateid *stp; @@ -2662,11 +2613,11 @@ alloc_init_lock_stateid(struct nfs4_stateowner *sop, struct nfs4_file *fp, struc goto out; INIT_LIST_HEAD(&stp->st_hash); INIT_LIST_HEAD(&stp->st_perfile); - INIT_LIST_HEAD(&stp->st_perfilestate); - INIT_LIST_HEAD(&stp->st_perlockowner); /* not used */ + INIT_LIST_HEAD(&stp->st_perstateowner); + INIT_LIST_HEAD(&stp->st_lockowners); /* not used */ list_add(&stp->st_hash, &lockstateid_hashtbl[hashval]); list_add(&stp->st_perfile, &fp->fi_stateids); - list_add(&stp->st_perfilestate, &sop->so_perfilestate); + list_add(&stp->st_perstateowner, &sop->so_stateids); stp->st_stateowner = sop; get_nfs4_file(fp); stp->st_file = fp; @@ -2677,147 +2628,136 @@ alloc_init_lock_stateid(struct nfs4_stateowner *sop, struct nfs4_file *fp, struc stp->st_vfs_file = open_stp->st_vfs_file; /* FIXME refcount?? */ stp->st_access_bmap = open_stp->st_access_bmap; stp->st_deny_bmap = open_stp->st_deny_bmap; + stp->st_openstp = open_stp; out: return stp; } -int +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) +__be32 +nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + struct nfsd4_lock *lock) { - struct nfs4_stateowner *lock_sop = NULL, *open_sop = NULL; + struct nfs4_stateowner *open_sop = NULL; + struct nfs4_stateowner *lock_sop = NULL; struct nfs4_stateid *lock_stp; struct file *filp; struct file_lock file_lock; - struct file_lock *conflock; - int status = 0; + struct file_lock conflock; + __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, (long long) lock->lk_length); - if (nfs4_in_grace() && !lock->lk_reclaim) - return nfserr_grace; - if (!nfs4_in_grace() && lock->lk_reclaim) - return nfserr_no_grace; - if (check_lock_length(lock->lk_offset, lock->lk_length)) return nfserr_inval; + if ((status = fh_verify(rqstp, &cstate->current_fh, + S_IFREG, NFSD_MAY_LOCK))) { + dprintk("NFSD: nfsd4_lock: permission denied!\n"); + return status; + } + nfs4_lock_state(); if (lock->lk_is_new) { - /* - * Client indicates that this is a new lockowner. - * Use open owner and open stateid to create lock owner and lock - * stateid. - */ + /* + * Client indicates that this is a new lockowner. + * Use open owner and open stateid to create lock owner and + * lock stateid. + */ struct nfs4_stateid *open_stp = NULL; struct nfs4_file *fp; status = nfserr_stale_clientid; - if (STALE_CLIENTID(&lock->lk_new_clientid)) { - printk("NFSD: nfsd4_lock: clientid is stale!\n"); - goto out; - } - - /* is the new lock seqid presented by the client zero? */ - status = nfserr_bad_seqid; - if (lock->v.new.lock_seqid != 0) + if (STALE_CLIENTID(&lock->lk_new_clientid)) 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_sop, &open_stp, - &lock->v.new.clientid); - if (status) { - if (lock->lk_reclaim) - status = nfserr_reclaim_bad; + OPEN_STATE, + &lock->lk_replay_owner, &open_stp, + lock); + if (status) goto out; - } + open_sop = lock->lk_replay_owner; /* create lockowner and lock stateid */ fp = open_stp->st_file; strhashval = lock_ownerstr_hashval(fp->fi_inode, open_sop->so_client->cl_clientid.cl_id, &lock->v.new.owner); - /* - * If we already have this lock owner, the client is in - * error (or our bookeeping is wrong!) - * for asking for a 'new lock'. - */ - status = nfserr_bad_stateid; - lock_sop = find_lockstateowner(&lock->v.new.owner, - &lock->v.new.clientid); - if (lock_sop) - goto out; + /* XXX: Do we need to check for duplicate stateowners on + * the same file, or should they just be allowed (and + * create new stateids)? */ status = nfserr_resource; - if (!(lock->lk_stateowner = alloc_init_lock_stateowner(strhashval, open_sop->so_client, open_stp, lock))) + lock_sop = alloc_init_lock_stateowner(strhashval, + open_sop->so_client, open_stp, lock); + if (lock_sop == NULL) goto out; - if ((lock_stp = alloc_init_lock_stateid(lock->lk_stateowner, - fp, open_stp)) == NULL) { - release_stateowner(lock->lk_stateowner); - lock->lk_stateowner = NULL; + lock_stp = alloc_init_lock_stateid(lock_sop, fp, open_stp); + if (lock_stp == NULL) goto out; - } - /* bump the open seqid used to create the lock */ - open_sop->so_seqid++; } 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->lk_stateowner, &lock_stp, NULL); + LOCK_STATE, + &lock->lk_replay_owner, &lock_stp, lock); if (status) goto out; + lock_sop = lock->lk_replay_owner; } - /* lock->lk_stateowner and lock_stp have been created or found */ + /* lock->lk_replay_owner and lock_stp have been created or found */ filp = lock_stp->st_vfs_file; - if ((status = fh_verify(rqstp, current_fh, S_IFREG, MAY_LOCK))) { - printk("NFSD: nfsd4_lock: permission denied!\n"); + status = nfserr_grace; + if (locks_in_grace() && !lock->lk_reclaim) + goto out; + status = nfserr_no_grace; + if (!locks_in_grace() && lock->lk_reclaim) goto out; - } locks_init_lock(&file_lock); switch (lock->lk_type) { 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; goto out; } - file_lock.fl_owner = (fl_owner_t) lock->lk_stateowner; + file_lock.fl_owner = (fl_owner_t)lock_sop; file_lock.fl_pid = current->tgid; file_lock.fl_file = filp; file_lock.fl_flags = FL_POSIX; + 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); /* @@ -2825,69 +2765,70 @@ 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. */ - status = posix_lock_file(filp, &file_lock); - if (file_lock.fl_ops && file_lock.fl_ops->fl_release_private) - file_lock.fl_ops->fl_release_private(&file_lock); - dprintk("NFSD: nfsd4_lock: posix_lock_file 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)); - goto out; - case (EAGAIN): - goto conflicting_lock; + status = 0; + break; + case (EAGAIN): /* conflock holds conflicting lock */ + status = nfserr_denied; + dprintk("NFSD: nfsd4_lock: conflicting lock found!\n"); + nfs4_set_lock_denied(&conflock, &lock->lk_denied); + break; case (EDEADLK): status = nfserr_deadlock; + break; default: - dprintk("NFSD: nfsd4_lock: posix_lock_file() failed! status %d\n",status); - goto out_destroy_new_stateid; - } - -conflicting_lock: - dprintk("NFSD: nfsd4_lock: conflicting lock found!\n"); - status = nfserr_denied; - /* XXX There is a race here. Future patch needed to provide - * an atomic posix_lock_and_test_file - */ - if (!(conflock = posix_test_lock(filp, &file_lock))) { - status = nfserr_serverfault; - goto out; - } - nfs4_set_lock_denied(conflock, &lock->lk_denied); - -out_destroy_new_stateid: - if (lock->lk_is_new) { - dprintk("NFSD: nfsd4_lock: destroy new stateid!\n"); - /* - * An error encountered after instantiation of the new - * stateid has forced us to destroy it. - */ - if (!seqid_mutating_err(status)) - open_sop->so_seqid--; - - release_state_owner(lock_stp, LOCK_STATE); + dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err); + status = nfserr_resource; + break; } out: - if (lock->lk_stateowner) - nfs4_get_stateowner(lock->lk_stateowner); + if (status && lock->lk_is_new && lock_sop) + release_stateowner(lock_sop); + if (lock->lk_replay_owner) { + nfs4_get_stateowner(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 *conflicting_lock; - 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)) @@ -2897,19 +2838,17 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock nfs4_lock_state(); status = nfserr_stale_clientid; - if (STALE_CLIENTID(&lockt->lt_clientid)) { - printk("NFSD: nfsd4_lockt: clientid is stale!\n"); + if (STALE_CLIENTID(&lockt->lt_clientid)) goto out; - } - if ((status = fh_verify(rqstp, current_fh, S_IFREG, 0))) { - printk("NFSD: nfsd4_lockt: fh_verify() failed!\n"); + 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: @@ -2921,7 +2860,7 @@ 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; } @@ -2934,39 +2873,34 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock file_lock.fl_flags = FL_POSIX; 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; - conflicting_lock = posix_test_lock(&file, &file_lock); - if (conflicting_lock) { + 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(conflicting_lock, &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) +__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, @@ -2977,10 +2911,10 @@ 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; @@ -2992,22 +2926,18 @@ nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock file_lock.fl_pid = current->tgid; file_lock.fl_file = filp; file_lock.fl_flags = FL_POSIX; + 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 (file_lock.fl_ops && file_lock.fl_ops->fl_release_private) - file_lock.fl_ops->fl_release_private(&file_lock); - if (status) { - printk("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; } /* @@ -3017,13 +2947,15 @@ nfsd4_locku(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock memcpy(&locku->lu_stateid, &stp->st_stateid, sizeof(stateid_t)); out: - if (locku->lu_stateowner) + if (locku->lu_stateowner) { nfs4_get_stateowner(locku->lu_stateowner); + cstate->replay_owner = locku->lu_stateowner; + } nfs4_unlock_state(); return status; out_nfserr: - status = nfserrno(status); + status = nfserrno(err); goto out; } @@ -3036,27 +2968,33 @@ 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(); for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) { - if ((*flpp)->fl_owner == (fl_owner_t)lowner) + if ((*flpp)->fl_owner == (fl_owner_t)lowner) { status = 1; goto out; + } } out: unlock_kernel(); 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 *local = NULL; + struct nfs4_stateowner *sop; + struct nfs4_stateid *stp; struct xdr_netobj *owner = &rlockowner->rl_owner; - int status; + struct list_head matches; + int i; + __be32 status; dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); @@ -3064,29 +3002,42 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_release_lockowner * /* XXX check for lease expiration */ status = nfserr_stale_clientid; - if (STALE_CLIENTID(clid)) { - printk("NFSD: nfsd4_release_lockowner: clientid is stale!\n"); + if (STALE_CLIENTID(clid)) return status; - } nfs4_lock_state(); - status = nfs_ok; - local = find_lockstateowner(owner, clid); - if (local) { - struct nfs4_stateid *stp; - - /* check for any locks held by any stateid - * associated with the (lock) stateowner */ - status = nfserr_locks_held; - list_for_each_entry(stp, &local->so_perfilestate, - st_perfilestate) { - if (check_for_locks(stp->st_vfs_file, local)) - goto out; + status = nfserr_locks_held; + /* XXX: we're doing a linear search through all the lockowners. + * Yipes! For now we'll just hope clients aren't really using + * release_lockowner much, but eventually we have to fix these + * data structures. */ + INIT_LIST_HEAD(&matches); + for (i = 0; i < LOCK_HASH_SIZE; i++) { + list_for_each_entry(sop, &lock_ownerid_hashtbl[i], so_idhash) { + if (!same_owner_str(sop, owner, clid)) + continue; + list_for_each_entry(stp, &sop->so_stateids, + st_perstateowner) { + if (check_for_locks(stp->st_vfs_file, sop)) + goto out; + /* Note: so_perclient unused for lockowners, + * so it's OK to fool with here. */ + list_add(&sop->so_perclient, &matches); + } } - /* no locks held by (lock) stateowner */ - status = nfs_ok; - release_stateowner(local); + } + /* Clients probably won't expect us to return with some (but not all) + * of the lockowner state released; so don't release any until all + * have been checked. */ + status = nfs_ok; + while (!list_empty(&matches)) { + sop = list_entry(matches.next, struct nfs4_stateowner, + so_perclient); + /* unhash_stateowner deletes so_perclient only + * for openowners. */ + list_del(&sop->so_perclient); + release_stateowner(sop); } out: nfs4_unlock_state(); @@ -3099,11 +3050,21 @@ alloc_reclaim(void) return kmalloc(sizeof(struct nfs4_client_reclaim), GFP_KERNEL); } +int +nfs4_has_reclaimed_state(const char *name) +{ + unsigned int strhashval = clientstr_hashval(name); + struct nfs4_client *clp; + + clp = find_confirmed_client_by_str(name, strhashval); + return clp ? 1 : 0; +} + /* * failure => all reset bets are off, nfserr_no_grace... */ -static int -nfs4_client_to_reclaim(char *name) +int +nfs4_client_to_reclaim(const char *name) { unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; @@ -3140,7 +3101,7 @@ nfs4_release_reclaim(void) /* * called from OPEN, CLAIM_PREVIOUS with a new clientid. */ -struct nfs4_client_reclaim * +static struct nfs4_client_reclaim * nfs4_find_reclaim_client(clientid_t *clid) { unsigned int strhashval; @@ -3170,7 +3131,7 @@ 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; @@ -3178,11 +3139,14 @@ 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]); @@ -3211,6 +3175,47 @@ 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 +nfsd4_load_reboot_recovery_data(void) +{ + int status; + + nfs4_lock_state(); + nfsd4_init_recdir(user_recovery_dirname); + status = nfsd4_recdir_load(); + nfs4_unlock_state(); + if (status) + 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: */ @@ -3218,43 +3223,28 @@ nfs4_state_init(void) 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; - printk("NFSD: starting %ld-second grace period\n", grace_time); - grace_end = boot_time + 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, NFSD_LEASE_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 get_seconds() < grace_end; -} - -void -set_no_grace(void) -{ - printk("NFSD: ERROR in reboot recovery. State reclaims will fail.\n"); - grace_end = get_seconds(); + return; } time_t @@ -3269,15 +3259,8 @@ __nfs4_state_shutdown(void) int i; struct nfs4_client *clp = NULL; struct nfs4_delegation *dp = NULL; - struct nfs4_stateowner *sop = NULL; struct list_head *pos, *next, reaplist; - list_for_each_safe(pos, next, &close_lru) { - sop = list_entry(pos, struct nfs4_stateowner, so_close_lru); - list_del(&sop->so_close_lru); - nfs4_put_stateowner(sop); - } - for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&conf_id_hashtbl[i])) { clp = list_entry(conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); @@ -3301,23 +3284,60 @@ __nfs4_state_shutdown(void) unhash_delegation(dp); } - cancel_delayed_work(&laundromat_work); - flush_workqueue(laundry_wq); - destroy_workqueue(laundry_wq); + nfsd4_shutdown_recdir(); nfs4_init = 0; } void 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) +{ + strcpy(user_recovery_dirname, recdir); +} + +/* + * Change the NFSv4 recovery directory to recdir. + */ +int +nfs4_reset_recoverydir(char *recdir) +{ + int status; + struct path path; + + status = kern_path(recdir, LOOKUP_FOLLOW, &path); + if (status) + return status; + status = -ENOTDIR; + if (S_ISDIR(path.dentry->d_inode->i_mode)) { + nfs4_set_recdir(recdir); + status = 0; + } + path_put(&path); + return status; +} + +char * +nfs4_recoverydir(void) +{ + return user_recovery_dirname; +} + +/* * Called when leasetime is changed. * * The only way the protocol gives us to handle on-the-fly lease changes is to @@ -3325,11 +3345,12 @@ nfs4_state_shutdown(void) * 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(); }