#include <linux/mutex.h>
#include <linux/lockd/bind.h>
#include <linux/module.h>
+#include <linux/sunrpc/svcauth_gss.h>
+#include <linux/sunrpc/clnt.h>
#define NFSDDBG_FACILITY NFSDDBG_PROC
static time_t lease_time = 90; /* default lease time */
static time_t user_lease_time = 90;
static time_t boot_time;
-static int in_grace = 1;
static u32 current_ownerid = 1;
static u32 current_fileid = 1;
static u32 current_delegid = 1;
static u32 nfs4_init;
static stateid_t zerostateid; /* bits all 0 */
static stateid_t onestateid; /* bits all 1 */
+static u64 current_sessionid = 1;
#define ZERO_STATEID(stateid) (!memcmp((stateid), &zerostateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid) (!memcmp((stateid), &onestateid, sizeof(stateid_t)))
/* forward declarations */
static struct nfs4_stateid * find_stateid(stateid_t *stid, int flags);
static struct nfs4_delegation * find_delegation_stateid(struct inode *ino, stateid_t *stid);
-static void release_stateid_lockowners(struct nfs4_stateid *open_stp);
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
static void nfs4_set_recdir(char *recdir);
-/* Locking:
- *
- * client_mutex:
- * protects clientid_hashtbl[], clientstr_hashtbl[],
- * unconfstr_hashtbl[], uncofid_hashtbl[].
- */
+/* Locking: */
+
+/* Currently used for almost all code touching nfsv4 state: */
static DEFINE_MUTEX(client_mutex);
+/*
+ * Currently used for the del_recall_lru and file hash table. In an
+ * effort to decrease the scope of the client_mutex, this spinlock may
+ * eventually cover more:
+ */
+static DEFINE_SPINLOCK(recall_lock);
+
static struct kmem_cache *stateowner_slab = NULL;
static struct kmem_cache *file_slab = NULL;
static struct kmem_cache *stateid_slab = NULL;
return x;
}
-/* forward declarations */
-static void release_stateowner(struct nfs4_stateowner *sop);
-static void release_stateid(struct nfs4_stateid *stp, int flags);
-
-/*
- * Delegation state
- */
-
-/* recall_lock protects the del_recall_lru */
-static DEFINE_SPINLOCK(recall_lock);
static struct list_head del_recall_lru;
-static void
-free_nfs4_file(struct kref *kref)
-{
- struct nfs4_file *fp = container_of(kref, struct nfs4_file, fi_ref);
- list_del(&fp->fi_hash);
- iput(fp->fi_inode);
- kmem_cache_free(file_slab, fp);
-}
-
static inline void
put_nfs4_file(struct nfs4_file *fi)
{
- kref_put(&fi->fi_ref, free_nfs4_file);
+ if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) {
+ list_del(&fi->fi_hash);
+ spin_unlock(&recall_lock);
+ iput(fi->fi_inode);
+ kmem_cache_free(file_slab, fi);
+ }
}
static inline void
get_nfs4_file(struct nfs4_file *fi)
{
- kref_get(&fi->fi_ref);
+ atomic_inc(&fi->fi_ref);
}
static int num_delegations;
{
struct nfs4_delegation *dp;
struct nfs4_file *fp = stp->st_file;
- struct nfs4_callback *cb = &stp->st_stateowner->so_client->cl_callback;
+ struct nfs4_cb_conn *cb = &stp->st_stateowner->so_client->cl_cb_conn;
dprintk("NFSD alloc_init_deleg\n");
if (fp->fi_had_conflict)
get_file(stp->st_vfs_file);
dp->dl_vfs_file = stp->st_vfs_file;
dp->dl_type = type;
- dp->dl_recall.cbr_dp = NULL;
- dp->dl_recall.cbr_ident = cb->cb_ident;
- dp->dl_recall.cbr_trunc = 0;
- dp->dl_stateid.si_boot = boot_time;
+ dp->dl_ident = cb->cb_ident;
+ dp->dl_stateid.si_boot = get_seconds();
dp->dl_stateid.si_stateownerid = current_delegid++;
dp->dl_stateid.si_fileid = 0;
dp->dl_stateid.si_generation = 0;
- dp->dl_fhlen = current_fh->fh_handle.fh_size;
- memcpy(dp->dl_fhval, ¤t_fh->fh_handle.fh_base,
- current_fh->fh_handle.fh_size);
+ fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
dp->dl_time = 0;
atomic_set(&dp->dl_count, 1);
list_add(&dp->dl_perfile, &fp->fi_delegations);
static struct list_head client_lru;
static struct list_head close_lru;
+static void unhash_generic_stateid(struct nfs4_stateid *stp)
+{
+ list_del(&stp->st_hash);
+ list_del(&stp->st_perfile);
+ list_del(&stp->st_perstateowner);
+}
+
+static void free_generic_stateid(struct nfs4_stateid *stp)
+{
+ put_nfs4_file(stp->st_file);
+ kmem_cache_free(stateid_slab, stp);
+}
+
+static void release_lock_stateid(struct nfs4_stateid *stp)
+{
+ unhash_generic_stateid(stp);
+ locks_remove_posix(stp->st_vfs_file, (fl_owner_t)stp->st_stateowner);
+ free_generic_stateid(stp);
+}
+
+static void unhash_lockowner(struct nfs4_stateowner *sop)
+{
+ struct nfs4_stateid *stp;
+
+ list_del(&sop->so_idhash);
+ list_del(&sop->so_strhash);
+ list_del(&sop->so_perstateid);
+ while (!list_empty(&sop->so_stateids)) {
+ stp = list_first_entry(&sop->so_stateids,
+ struct nfs4_stateid, st_perstateowner);
+ release_lock_stateid(stp);
+ }
+}
+
+static void release_lockowner(struct nfs4_stateowner *sop)
+{
+ unhash_lockowner(sop);
+ nfs4_put_stateowner(sop);
+}
+
+static void
+release_stateid_lockowners(struct nfs4_stateid *open_stp)
+{
+ struct nfs4_stateowner *lock_sop;
+
+ while (!list_empty(&open_stp->st_lockowners)) {
+ lock_sop = list_entry(open_stp->st_lockowners.next,
+ struct nfs4_stateowner, so_perstateid);
+ /* list_del(&open_stp->st_lockowners); */
+ BUG_ON(lock_sop->so_is_open_owner);
+ release_lockowner(lock_sop);
+ }
+}
+
+static void release_open_stateid(struct nfs4_stateid *stp)
+{
+ unhash_generic_stateid(stp);
+ release_stateid_lockowners(stp);
+ nfsd_close(stp->st_vfs_file);
+ free_generic_stateid(stp);
+}
+
+static void unhash_openowner(struct nfs4_stateowner *sop)
+{
+ struct nfs4_stateid *stp;
+
+ list_del(&sop->so_idhash);
+ list_del(&sop->so_strhash);
+ list_del(&sop->so_perclient);
+ list_del(&sop->so_perstateid); /* XXX: necessary? */
+ while (!list_empty(&sop->so_stateids)) {
+ stp = list_first_entry(&sop->so_stateids,
+ struct nfs4_stateid, st_perstateowner);
+ release_open_stateid(stp);
+ }
+}
+
+static void release_openowner(struct nfs4_stateowner *sop)
+{
+ unhash_openowner(sop);
+ list_del(&sop->so_close_lru);
+ nfs4_put_stateowner(sop);
+}
+
+static DEFINE_SPINLOCK(sessionid_lock);
+#define SESSION_HASH_SIZE 512
+static struct list_head sessionid_hashtbl[SESSION_HASH_SIZE];
+
+static inline int
+hash_sessionid(struct nfs4_sessionid *sessionid)
+{
+ struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid;
+
+ return sid->sequence % SESSION_HASH_SIZE;
+}
+
+static inline void
+dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
+{
+ u32 *ptr = (u32 *)(&sessionid->data[0]);
+ dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]);
+}
+
+static void
+gen_sessionid(struct nfsd4_session *ses)
+{
+ struct nfs4_client *clp = ses->se_client;
+ struct nfsd4_sessionid *sid;
+
+ sid = (struct nfsd4_sessionid *)ses->se_sessionid.data;
+ sid->clientid = clp->cl_clientid;
+ sid->sequence = current_sessionid++;
+ sid->reserved = 0;
+}
+
+/*
+ * The protocol defines ca_maxresponssize_cached to include the size of
+ * the rpc header, but all we need to cache is the data starting after
+ * the end of the initial SEQUENCE operation--the rest we regenerate
+ * each time. Therefore we can advertise a ca_maxresponssize_cached
+ * value that is the number of bytes in our cache plus a few additional
+ * bytes. In order to stay on the safe side, and not promise more than
+ * we can cache, those additional bytes must be the minimum possible: 24
+ * bytes of rpc header (xid through accept state, with AUTH_NULL
+ * verifier), 12 for the compound header (with zero-length tag), and 44
+ * for the SEQUENCE op response:
+ */
+#define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44)
+
+/*
+ * Give the client the number of ca_maxresponsesize_cached slots it
+ * requests, of size bounded by NFSD_SLOT_CACHE_SIZE,
+ * NFSD_MAX_MEM_PER_SESSION, and nfsd_drc_max_mem. Do not allow more
+ * than NFSD_MAX_SLOTS_PER_SESSION.
+ *
+ * If we run out of reserved DRC memory we should (up to a point)
+ * re-negotiate active sessions and reduce their slot usage to make
+ * rooom for new connections. For now we just fail the create session.
+ */
+static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan)
+{
+ int mem, size = fchan->maxresp_cached;
+
+ if (fchan->maxreqs < 1)
+ return nfserr_inval;
+
+ if (size < NFSD_MIN_HDR_SEQ_SZ)
+ size = NFSD_MIN_HDR_SEQ_SZ;
+ size -= NFSD_MIN_HDR_SEQ_SZ;
+ if (size > NFSD_SLOT_CACHE_SIZE)
+ size = NFSD_SLOT_CACHE_SIZE;
+
+ /* bound the maxreqs by NFSD_MAX_MEM_PER_SESSION */
+ mem = fchan->maxreqs * size;
+ if (mem > NFSD_MAX_MEM_PER_SESSION) {
+ fchan->maxreqs = NFSD_MAX_MEM_PER_SESSION / size;
+ if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
+ fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
+ mem = fchan->maxreqs * size;
+ }
+
+ spin_lock(&nfsd_drc_lock);
+ /* bound the total session drc memory ussage */
+ if (mem + nfsd_drc_mem_used > nfsd_drc_max_mem) {
+ fchan->maxreqs = (nfsd_drc_max_mem - nfsd_drc_mem_used) / size;
+ mem = fchan->maxreqs * size;
+ }
+ nfsd_drc_mem_used += mem;
+ spin_unlock(&nfsd_drc_lock);
+
+ if (fchan->maxreqs == 0)
+ return nfserr_serverfault;
+
+ fchan->maxresp_cached = size + NFSD_MIN_HDR_SEQ_SZ;
+ return 0;
+}
+
+/*
+ * fchan holds the client values on input, and the server values on output
+ */
+static int init_forechannel_attrs(struct svc_rqst *rqstp,
+ struct nfsd4_channel_attrs *session_fchan,
+ struct nfsd4_channel_attrs *fchan)
+{
+ int status = 0;
+ __u32 maxcount = svc_max_payload(rqstp);
+
+ /* headerpadsz set to zero in encode routine */
+
+ /* Use the client's max request and max response size if possible */
+ if (fchan->maxreq_sz > maxcount)
+ fchan->maxreq_sz = maxcount;
+ session_fchan->maxreq_sz = fchan->maxreq_sz;
+
+ if (fchan->maxresp_sz > maxcount)
+ fchan->maxresp_sz = maxcount;
+ session_fchan->maxresp_sz = fchan->maxresp_sz;
+
+ /* Use the client's maxops if possible */
+ if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND)
+ fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND;
+ session_fchan->maxops = fchan->maxops;
+
+ /* FIXME: Error means no more DRC pages so the server should
+ * recover pages from existing sessions. For now fail session
+ * creation.
+ */
+ status = set_forechannel_drc_size(fchan);
+
+ session_fchan->maxresp_cached = fchan->maxresp_cached;
+ session_fchan->maxreqs = fchan->maxreqs;
+
+ dprintk("%s status %d\n", __func__, status);
+ return status;
+}
+
+static void
+free_session_slots(struct nfsd4_session *ses)
+{
+ int i;
+
+ for (i = 0; i < ses->se_fchannel.maxreqs; i++)
+ kfree(ses->se_slots[i]);
+}
+
+static int
+alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
+ struct nfsd4_create_session *cses)
+{
+ struct nfsd4_session *new, tmp;
+ struct nfsd4_slot *sp;
+ int idx, slotsize, cachesize, i;
+ int status;
+
+ memset(&tmp, 0, sizeof(tmp));
+
+ /* FIXME: For now, we just accept the client back channel attributes. */
+ tmp.se_bchannel = cses->back_channel;
+ status = init_forechannel_attrs(rqstp, &tmp.se_fchannel,
+ &cses->fore_channel);
+ if (status)
+ goto out;
+
+ BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot)
+ + sizeof(struct nfsd4_session) > PAGE_SIZE);
+
+ status = nfserr_serverfault;
+ /* allocate struct nfsd4_session and slot table pointers in one piece */
+ slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot *);
+ new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL);
+ if (!new)
+ goto out;
+
+ memcpy(new, &tmp, sizeof(*new));
+
+ /* allocate each struct nfsd4_slot and data cache in one piece */
+ cachesize = new->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+ for (i = 0; i < new->se_fchannel.maxreqs; i++) {
+ sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL);
+ if (!sp)
+ goto out_free;
+ new->se_slots[i] = sp;
+ }
+
+ new->se_client = clp;
+ gen_sessionid(new);
+ idx = hash_sessionid(&new->se_sessionid);
+ memcpy(clp->cl_sessionid.data, new->se_sessionid.data,
+ NFS4_MAX_SESSIONID_LEN);
+
+ new->se_flags = cses->flags;
+ kref_init(&new->se_ref);
+ spin_lock(&sessionid_lock);
+ list_add(&new->se_hash, &sessionid_hashtbl[idx]);
+ list_add(&new->se_perclnt, &clp->cl_sessions);
+ spin_unlock(&sessionid_lock);
+
+ status = nfs_ok;
+out:
+ return status;
+out_free:
+ free_session_slots(new);
+ kfree(new);
+ goto out;
+}
+
+/* caller must hold sessionid_lock */
+static struct nfsd4_session *
+find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid)
+{
+ struct nfsd4_session *elem;
+ int idx;
+
+ dump_sessionid(__func__, sessionid);
+ idx = hash_sessionid(sessionid);
+ dprintk("%s: idx is %d\n", __func__, idx);
+ /* Search in the appropriate list */
+ list_for_each_entry(elem, &sessionid_hashtbl[idx], se_hash) {
+ dump_sessionid("list traversal", &elem->se_sessionid);
+ if (!memcmp(elem->se_sessionid.data, sessionid->data,
+ NFS4_MAX_SESSIONID_LEN)) {
+ return elem;
+ }
+ }
+
+ dprintk("%s: session not found\n", __func__);
+ return NULL;
+}
+
+/* caller must hold sessionid_lock */
+static void
+unhash_session(struct nfsd4_session *ses)
+{
+ list_del(&ses->se_hash);
+ list_del(&ses->se_perclnt);
+}
+
+static void
+release_session(struct nfsd4_session *ses)
+{
+ spin_lock(&sessionid_lock);
+ unhash_session(ses);
+ spin_unlock(&sessionid_lock);
+ nfsd4_put_session(ses);
+}
+
+void
+free_session(struct kref *kref)
+{
+ struct nfsd4_session *ses;
+
+ ses = container_of(kref, struct nfsd4_session, se_ref);
+ spin_lock(&nfsd_drc_lock);
+ nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE;
+ spin_unlock(&nfsd_drc_lock);
+ free_session_slots(ses);
+ kfree(ses);
+}
+
static inline void
renew_client(struct nfs4_client *clp)
{
{
if (clid->cl_boot == boot_time)
return 0;
- dprintk("NFSD stale clientid (%08x/%08x)\n",
- clid->cl_boot, clid->cl_id);
+ dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
+ clid->cl_boot, clid->cl_id, boot_time);
return 1;
}
static void
shutdown_callback_client(struct nfs4_client *clp)
{
- struct rpc_clnt *clnt = clp->cl_callback.cb_client;
+ struct rpc_clnt *clnt = clp->cl_cb_conn.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;
+ clp->cl_cb_conn.cb_client = NULL;
rpc_shutdown_client(clnt);
}
+ if (clp->cl_cb_conn.cb_cred) {
+ put_rpccred(clp->cl_cb_conn.cb_cred);
+ clp->cl_cb_conn.cb_cred = NULL;
+ }
}
static inline void
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);
}
list_del(&clp->cl_lru);
while (!list_empty(&clp->cl_openowners)) {
sop = list_entry(clp->cl_openowners.next, struct nfs4_stateowner, so_perclient);
- release_stateowner(sop);
+ release_openowner(sop);
+ }
+ while (!list_empty(&clp->cl_sessions)) {
+ struct nfsd4_session *ses;
+ ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
+ se_perclnt);
+ release_session(ses);
}
put_nfs4_client(clp);
}
return NULL;
memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
atomic_set(&clp->cl_count, 1);
- atomic_set(&clp->cl_callback.cb_set, 0);
+ atomic_set(&clp->cl_cb_conn.cb_set, 0);
INIT_LIST_HEAD(&clp->cl_idhash);
INIT_LIST_HEAD(&clp->cl_strhash);
INIT_LIST_HEAD(&clp->cl_openowners);
INIT_LIST_HEAD(&clp->cl_delegations);
+ INIT_LIST_HEAD(&clp->cl_sessions);
INIT_LIST_HEAD(&clp->cl_lru);
return clp;
}
return NULL;
}
+/*
+ * Return 1 iff clp's clientid establishment method matches the use_exchange_id
+ * parameter. Matching is based on the fact the at least one of the
+ * EXCHGID4_FLAG_USE_{NON_PNFS,PNFS_MDS,PNFS_DS} flags must be set for v4.1
+ *
+ * FIXME: we need to unify the clientid namespaces for nfsv4.x
+ * and correctly deal with client upgrade/downgrade in EXCHANGE_ID
+ * and SET_CLIENTID{,_CONFIRM}
+ */
+static inline int
+match_clientid_establishment(struct nfs4_client *clp, bool use_exchange_id)
+{
+ bool has_exchange_flags = (clp->cl_exchange_flags != 0);
+ return use_exchange_id == has_exchange_flags;
+}
+
static struct nfs4_client *
-find_confirmed_client_by_str(const char *dname, unsigned int hashval)
+find_confirmed_client_by_str(const char *dname, unsigned int hashval,
+ bool use_exchange_id)
{
struct nfs4_client *clp;
list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) {
- if (same_name(clp->cl_recdir, dname))
+ if (same_name(clp->cl_recdir, dname) &&
+ match_clientid_establishment(clp, use_exchange_id))
return clp;
}
return NULL;
}
static struct nfs4_client *
-find_unconfirmed_client_by_str(const char *dname, unsigned int hashval)
+find_unconfirmed_client_by_str(const char *dname, unsigned int hashval,
+ bool use_exchange_id)
{
struct nfs4_client *clp;
list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) {
- if (same_name(clp->cl_recdir, dname))
+ if (same_name(clp->cl_recdir, dname) &&
+ match_clientid_establishment(clp, use_exchange_id))
return clp;
}
return NULL;
}
-/* a helper function for parse_callback */
-static int
-parse_octet(unsigned int *lenp, char **addrp)
+static void
+gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
+{
+ struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
+ unsigned short expected_family;
+
+ /* Currently, we only support tcp and tcp6 for the callback channel */
+ if (se->se_callback_netid_len == 3 &&
+ !memcmp(se->se_callback_netid_val, "tcp", 3))
+ expected_family = AF_INET;
+ else if (se->se_callback_netid_len == 4 &&
+ !memcmp(se->se_callback_netid_val, "tcp6", 4))
+ expected_family = AF_INET6;
+ else
+ goto out_err;
+
+ cb->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val,
+ se->se_callback_addr_len,
+ (struct sockaddr *) &cb->cb_addr,
+ sizeof(cb->cb_addr));
+
+ if (!cb->cb_addrlen || cb->cb_addr.ss_family != expected_family)
+ goto out_err;
+
+ if (cb->cb_addr.ss_family == AF_INET6)
+ ((struct sockaddr_in6 *) &cb->cb_addr)->sin6_scope_id = scopeid;
+
+ cb->cb_minorversion = 0;
+ cb->cb_prog = se->se_callback_prog;
+ cb->cb_ident = se->se_callback_ident;
+ return;
+out_err:
+ cb->cb_addr.ss_family = AF_UNSPEC;
+ cb->cb_addrlen = 0;
+ dprintk(KERN_INFO "NFSD: this client (clientid %08x/%08x) "
+ "will not receive delegations\n",
+ clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);
+
+ return;
+}
+
+/*
+ * Cache a reply. nfsd4_check_drc_limit() has bounded the cache size.
+ */
+void
+nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
- unsigned int len = *lenp;
- char *p = *addrp;
- int n = -1;
- char c;
+ struct nfsd4_slot *slot = resp->cstate.slot;
+ unsigned int base;
- for (;;) {
- if (!len)
- break;
- len--;
- c = *p++;
- if (c == '.')
- break;
- if ((c < '0') || (c > '9')) {
- n = -1;
- break;
+ dprintk("--> %s slot %p\n", __func__, slot);
+
+ slot->sl_opcnt = resp->opcnt;
+ slot->sl_status = resp->cstate.status;
+
+ if (nfsd4_not_cached(resp)) {
+ slot->sl_datalen = 0;
+ return;
+ }
+ slot->sl_datalen = (char *)resp->p - (char *)resp->cstate.datap;
+ base = (char *)resp->cstate.datap -
+ (char *)resp->xbuf->head[0].iov_base;
+ if (read_bytes_from_xdr_buf(resp->xbuf, base, slot->sl_data,
+ slot->sl_datalen))
+ WARN("%s: sessions DRC could not cache compound\n", __func__);
+ return;
+}
+
+/*
+ * Encode the replay sequence operation from the slot values.
+ * If cachethis is FALSE encode the uncached rep error on the next
+ * operation which sets resp->p and increments resp->opcnt for
+ * nfs4svc_encode_compoundres.
+ *
+ */
+static __be32
+nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args,
+ struct nfsd4_compoundres *resp)
+{
+ struct nfsd4_op *op;
+ struct nfsd4_slot *slot = resp->cstate.slot;
+
+ dprintk("--> %s resp->opcnt %d cachethis %u \n", __func__,
+ resp->opcnt, resp->cstate.slot->sl_cachethis);
+
+ /* Encode the replayed sequence operation */
+ op = &args->ops[resp->opcnt - 1];
+ nfsd4_encode_operation(resp, op);
+
+ /* Return nfserr_retry_uncached_rep in next operation. */
+ if (args->opcnt > 1 && slot->sl_cachethis == 0) {
+ op = &args->ops[resp->opcnt++];
+ op->status = nfserr_retry_uncached_rep;
+ nfsd4_encode_operation(resp, op);
+ }
+ return op->status;
+}
+
+/*
+ * The sequence operation is not cached because we can use the slot and
+ * session values.
+ */
+__be32
+nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
+ struct nfsd4_sequence *seq)
+{
+ struct nfsd4_slot *slot = resp->cstate.slot;
+ __be32 status;
+
+ dprintk("--> %s slot %p\n", __func__, slot);
+
+ /* Either returns 0 or nfserr_retry_uncached */
+ status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp);
+ if (status == nfserr_retry_uncached_rep)
+ return status;
+
+ /* The sequence operation has been encoded, cstate->datap set. */
+ memcpy(resp->cstate.datap, slot->sl_data, slot->sl_datalen);
+
+ resp->opcnt = slot->sl_opcnt;
+ resp->p = resp->cstate.datap + XDR_QUADLEN(slot->sl_datalen);
+ status = slot->sl_status;
+
+ return status;
+}
+
+/*
+ * Set the exchange_id flags returned by the server.
+ */
+static void
+nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
+{
+ /* pNFS is not supported */
+ new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
+
+ /* Referrals are supported, Migration is not. */
+ new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;
+
+ /* set the wire flags to return to client. */
+ clid->flags = new->cl_exchange_flags;
+}
+
+__be32
+nfsd4_exchange_id(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd4_exchange_id *exid)
+{
+ struct nfs4_client *unconf, *conf, *new;
+ int status;
+ unsigned int strhashval;
+ char dname[HEXDIR_LEN];
+ char addr_str[INET6_ADDRSTRLEN];
+ nfs4_verifier verf = exid->verifier;
+ struct sockaddr *sa = svc_addr(rqstp);
+
+ rpc_ntop(sa, addr_str, sizeof(addr_str));
+ dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p "
+ "ip_addr=%s flags %x, spa_how %d\n",
+ __func__, rqstp, exid, exid->clname.len, exid->clname.data,
+ addr_str, exid->flags, exid->spa_how);
+
+ if (!check_name(exid->clname) || (exid->flags & ~EXCHGID4_FLAG_MASK_A))
+ return nfserr_inval;
+
+ /* Currently only support SP4_NONE */
+ switch (exid->spa_how) {
+ case SP4_NONE:
+ break;
+ case SP4_SSV:
+ return nfserr_encr_alg_unsupp;
+ default:
+ BUG(); /* checked by xdr code */
+ case SP4_MACH_CRED:
+ return nfserr_serverfault; /* no excuse :-/ */
+ }
+
+ status = nfs4_make_rec_clidname(dname, &exid->clname);
+
+ if (status)
+ goto error;
+
+ strhashval = clientstr_hashval(dname);
+
+ nfs4_lock_state();
+ status = nfs_ok;
+
+ conf = find_confirmed_client_by_str(dname, strhashval, true);
+ if (conf) {
+ if (!same_verf(&verf, &conf->cl_verifier)) {
+ /* 18.35.4 case 8 */
+ if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) {
+ status = nfserr_not_same;
+ goto out;
+ }
+ /* Client reboot: destroy old state */
+ expire_client(conf);
+ goto out_new;
}
- if (n < 0)
- n = 0;
- n = (n * 10) + (c - '0');
- if (n > 255) {
- n = -1;
- break;
+ if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) {
+ /* 18.35.4 case 9 */
+ if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) {
+ status = nfserr_perm;
+ goto out;
+ }
+ expire_client(conf);
+ goto out_new;
}
+ /*
+ * Set bit when the owner id and verifier map to an already
+ * confirmed client id (18.35.3).
+ */
+ exid->flags |= EXCHGID4_FLAG_CONFIRMED_R;
+
+ /*
+ * Falling into 18.35.4 case 2, possible router replay.
+ * Leave confirmed record intact and return same result.
+ */
+ copy_verf(conf, &verf);
+ new = conf;
+ goto out_copy;
+ }
+
+ /* 18.35.4 case 7 */
+ if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) {
+ status = nfserr_noent;
+ goto out;
}
- *lenp = len;
- *addrp = p;
- return n;
+
+ unconf = find_unconfirmed_client_by_str(dname, strhashval, true);
+ if (unconf) {
+ /*
+ * Possible retry or client restart. Per 18.35.4 case 4,
+ * a new unconfirmed record should be generated regardless
+ * of whether any properties have changed.
+ */
+ expire_client(unconf);
+ }
+
+out_new:
+ /* Normal case */
+ new = create_client(exid->clname, dname);
+ if (new == NULL) {
+ status = nfserr_serverfault;
+ goto out;
+ }
+
+ copy_verf(new, &verf);
+ copy_cred(&new->cl_cred, &rqstp->rq_cred);
+ rpc_copy_addr((struct sockaddr *) &new->cl_addr, sa);
+ gen_clid(new);
+ gen_confirm(new);
+ add_to_unconfirmed(new, strhashval);
+out_copy:
+ exid->clientid.cl_boot = new->cl_clientid.cl_boot;
+ exid->clientid.cl_id = new->cl_clientid.cl_id;
+
+ exid->seqid = 1;
+ nfsd4_set_ex_flags(new, exid);
+
+ dprintk("nfsd4_exchange_id seqid %d flags %x\n",
+ new->cl_cs_slot.sl_seqid, new->cl_exchange_flags);
+ status = nfs_ok;
+
+out:
+ nfs4_unlock_state();
+error:
+ dprintk("nfsd4_exchange_id returns %d\n", ntohl(status));
+ return status;
}
-/* parse and set the setclientid ipv4 callback address */
static int
-parse_ipv4(unsigned int addr_len, char *addr_val, unsigned int *cbaddrp, unsigned short *cbportp)
-{
- int temp = 0;
- u32 cbaddr = 0;
- u16 cbport = 0;
- u32 addrlen = addr_len;
- char *addr = addr_val;
- int i, shift;
-
- /* ipaddress */
- shift = 24;
- for(i = 4; i > 0 ; i--) {
- if ((temp = parse_octet(&addrlen, &addr)) < 0) {
- return 0;
- }
- cbaddr |= (temp << shift);
- if (shift > 0)
- shift -= 8;
+check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse)
+{
+ dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid,
+ slot_seqid);
+
+ /* The slot is in use, and no response has been sent. */
+ if (slot_inuse) {
+ if (seqid == slot_seqid)
+ return nfserr_jukebox;
+ else
+ return nfserr_seq_misordered;
}
- *cbaddrp = cbaddr;
+ /* Normal */
+ if (likely(seqid == slot_seqid + 1))
+ return nfs_ok;
+ /* Replay */
+ if (seqid == slot_seqid)
+ return nfserr_replay_cache;
+ /* Wraparound */
+ if (seqid == 1 && (slot_seqid + 1) == 0)
+ return nfs_ok;
+ /* Misordered replay or misordered new request */
+ return nfserr_seq_misordered;
+}
- /* port */
- shift = 8;
- for(i = 2; i > 0 ; i--) {
- if ((temp = parse_octet(&addrlen, &addr)) < 0) {
- return 0;
+/*
+ * Cache the create session result into the create session single DRC
+ * slot cache by saving the xdr structure. sl_seqid has been set.
+ * Do this for solo or embedded create session operations.
+ */
+static void
+nfsd4_cache_create_session(struct nfsd4_create_session *cr_ses,
+ struct nfsd4_clid_slot *slot, int nfserr)
+{
+ slot->sl_status = nfserr;
+ memcpy(&slot->sl_cr_ses, cr_ses, sizeof(*cr_ses));
+}
+
+static __be32
+nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses,
+ struct nfsd4_clid_slot *slot)
+{
+ memcpy(cr_ses, &slot->sl_cr_ses, sizeof(*cr_ses));
+ return slot->sl_status;
+}
+
+__be32
+nfsd4_create_session(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd4_create_session *cr_ses)
+{
+ struct sockaddr *sa = svc_addr(rqstp);
+ struct nfs4_client *conf, *unconf;
+ struct nfsd4_clid_slot *cs_slot = NULL;
+ int status = 0;
+
+ nfs4_lock_state();
+ unconf = find_unconfirmed_client(&cr_ses->clientid);
+ conf = find_confirmed_client(&cr_ses->clientid);
+
+ if (conf) {
+ cs_slot = &conf->cl_cs_slot;
+ status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
+ if (status == nfserr_replay_cache) {
+ dprintk("Got a create_session replay! seqid= %d\n",
+ cs_slot->sl_seqid);
+ /* Return the cached reply status */
+ status = nfsd4_replay_create_session(cr_ses, cs_slot);
+ goto out;
+ } else if (cr_ses->seqid != cs_slot->sl_seqid + 1) {
+ status = nfserr_seq_misordered;
+ dprintk("Sequence misordered!\n");
+ dprintk("Expected seqid= %d but got seqid= %d\n",
+ cs_slot->sl_seqid, cr_ses->seqid);
+ goto out;
}
- cbport |= (temp << shift);
- if (shift > 0)
- shift -= 8;
+ cs_slot->sl_seqid++;
+ } else if (unconf) {
+ if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
+ !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
+ status = nfserr_clid_inuse;
+ goto out;
+ }
+
+ cs_slot = &unconf->cl_cs_slot;
+ status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
+ if (status) {
+ /* an unconfirmed replay returns misordered */
+ status = nfserr_seq_misordered;
+ goto out_cache;
+ }
+
+ cs_slot->sl_seqid++; /* from 0 to 1 */
+ move_to_confirmed(unconf);
+
+ /*
+ * We do not support RDMA or persistent sessions
+ */
+ cr_ses->flags &= ~SESSION4_PERSIST;
+ cr_ses->flags &= ~SESSION4_RDMA;
+
+ conf = unconf;
+ } else {
+ status = nfserr_stale_clientid;
+ goto out;
}
- *cbportp = cbport;
- return 1;
+
+ status = alloc_init_session(rqstp, conf, cr_ses);
+ if (status)
+ goto out;
+
+ memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data,
+ NFS4_MAX_SESSIONID_LEN);
+ cr_ses->seqid = cs_slot->sl_seqid;
+
+out_cache:
+ /* cache solo and embedded create sessions under the state lock */
+ nfsd4_cache_create_session(cr_ses, cs_slot, status);
+out:
+ nfs4_unlock_state();
+ dprintk("%s returns %d\n", __func__, ntohl(status));
+ return status;
+}
+
+__be32
+nfsd4_destroy_session(struct svc_rqst *r,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd4_destroy_session *sessionid)
+{
+ struct nfsd4_session *ses;
+ u32 status = nfserr_badsession;
+
+ /* Notes:
+ * - The confirmed nfs4_client->cl_sessionid holds destroyed sessinid
+ * - Should we return nfserr_back_chan_busy if waiting for
+ * callbacks on to-be-destroyed session?
+ * - Do we need to clear any callback info from previous session?
+ */
+
+ dump_sessionid(__func__, &sessionid->sessionid);
+ spin_lock(&sessionid_lock);
+ ses = find_in_sessionid_hashtbl(&sessionid->sessionid);
+ if (!ses) {
+ spin_unlock(&sessionid_lock);
+ goto out;
+ }
+
+ unhash_session(ses);
+ spin_unlock(&sessionid_lock);
+
+ /* wait for callbacks */
+ shutdown_callback_client(ses->se_client);
+ nfsd4_put_session(ses);
+ status = nfs_ok;
+out:
+ dprintk("%s returns %d\n", __func__, ntohl(status));
+ return status;
}
-static void
-gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se)
+__be32
+nfsd4_sequence(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd4_sequence *seq)
{
- struct nfs4_callback *cb = &clp->cl_callback;
+ struct nfsd4_compoundres *resp = rqstp->rq_resp;
+ struct nfsd4_session *session;
+ struct nfsd4_slot *slot;
+ int status;
- /* Currently, we only support tcp for the callback channel */
- if ((se->se_callback_netid_len != 3) || memcmp((char *)se->se_callback_netid_val, "tcp", 3))
- goto out_err;
+ if (resp->opcnt != 1)
+ return nfserr_sequence_pos;
- if ( !(parse_ipv4(se->se_callback_addr_len, se->se_callback_addr_val,
- &cb->cb_addr, &cb->cb_port)))
- goto out_err;
- cb->cb_prog = se->se_callback_prog;
- cb->cb_ident = se->se_callback_ident;
- return;
-out_err:
- dprintk(KERN_INFO "NFSD: this client (clientid %08x/%08x) "
- "will not receive delegations\n",
- clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);
+ spin_lock(&sessionid_lock);
+ status = nfserr_badsession;
+ session = find_in_sessionid_hashtbl(&seq->sessionid);
+ if (!session)
+ goto out;
- return;
+ status = nfserr_badslot;
+ if (seq->slotid >= session->se_fchannel.maxreqs)
+ goto out;
+
+ slot = session->se_slots[seq->slotid];
+ dprintk("%s: slotid %d\n", __func__, seq->slotid);
+
+ /* We do not negotiate the number of slots yet, so set the
+ * maxslots to the session maxreqs which is used to encode
+ * sr_highest_slotid and the sr_target_slot id to maxslots */
+ seq->maxslots = session->se_fchannel.maxreqs;
+
+ status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_inuse);
+ if (status == nfserr_replay_cache) {
+ cstate->slot = slot;
+ cstate->session = session;
+ /* Return the cached reply status and set cstate->status
+ * for nfsd4_proc_compound processing */
+ status = nfsd4_replay_cache_entry(resp, seq);
+ cstate->status = nfserr_replay_cache;
+ goto out;
+ }
+ if (status)
+ goto out;
+
+ /* Success! bump slot seqid */
+ slot->sl_inuse = true;
+ slot->sl_seqid = seq->seqid;
+ slot->sl_cachethis = seq->cachethis;
+
+ cstate->slot = slot;
+ cstate->session = session;
+
+ /* Hold a session reference until done processing the compound:
+ * nfsd4_put_session called only if the cstate slot is set.
+ */
+ nfsd4_get_session(session);
+out:
+ spin_unlock(&sessionid_lock);
+ /* Renew the clientid on success and on replay */
+ if (cstate->session) {
+ nfs4_lock_state();
+ renew_client(session->se_client);
+ nfs4_unlock_state();
+ }
+ dprintk("%s: return %d\n", __func__, ntohl(status));
+ return status;
}
__be32
nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_setclientid *setclid)
{
- struct sockaddr_in *sin = svc_addr_in(rqstp);
+ struct sockaddr *sa = svc_addr(rqstp);
struct xdr_netobj clname = {
.len = setclid->se_namelen,
.data = setclid->se_name,
unsigned int strhashval;
struct nfs4_client *conf, *unconf, *new;
__be32 status;
+ char *princ;
char dname[HEXDIR_LEN];
if (!check_name(clname))
strhashval = clientstr_hashval(dname);
nfs4_lock_state();
- conf = find_confirmed_client_by_str(dname, strhashval);
+ conf = find_confirmed_client_by_str(dname, strhashval, false);
if (conf) {
/* RFC 3530 14.2.33 CASE 0: */
status = nfserr_clid_inuse;
- if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)
- || conf->cl_addr != sin->sin_addr.s_addr) {
- dprintk("NFSD: setclientid: string in use by client"
- "at %u.%u.%u.%u\n", NIPQUAD(conf->cl_addr));
+ if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) {
+ char addr_str[INET6_ADDRSTRLEN];
+ rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str,
+ sizeof(addr_str));
+ dprintk("NFSD: setclientid: string in use by client "
+ "at %s\n", addr_str);
goto out;
}
}
* 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);
+ unconf = find_unconfirmed_client_by_str(dname, strhashval, false);
status = nfserr_resource;
if (!conf) {
/*
gen_clid(new);
}
copy_verf(new, &clverifier);
- new->cl_addr = sin->sin_addr.s_addr;
+ rpc_copy_addr((struct sockaddr *) &new->cl_addr, sa);
+ 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);
+ gen_callback(new, setclid, rpc_get_scope_id(sa));
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;
struct nfsd4_compound_state *cstate,
struct nfsd4_setclientid_confirm *setclientid_confirm)
{
- struct sockaddr_in *sin = svc_addr_in(rqstp);
+ struct sockaddr *sa = svc_addr(rqstp);
struct nfs4_client *conf, *unconf;
nfs4_verifier confirm = setclientid_confirm->sc_confirm;
clientid_t * clid = &setclientid_confirm->sc_clientid;
unconf = find_unconfirmed_client(clid);
status = nfserr_clid_inuse;
- if (conf && conf->cl_addr != sin->sin_addr.s_addr)
+ if (conf && !rpc_cmp_addr((struct sockaddr *) &conf->cl_addr, sa))
goto out;
- if (unconf && unconf->cl_addr != sin->sin_addr.s_addr)
+ if (unconf && !rpc_cmp_addr((struct sockaddr *) &unconf->cl_addr, sa))
goto out;
/*
else {
/* 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);
+ atomic_set(&conf->cl_cb_conn.cb_set, 0);
expire_client(unconf);
status = nfs_ok;
unsigned int hash =
clientstr_hashval(unconf->cl_recdir);
conf = find_confirmed_client_by_str(unconf->cl_recdir,
- hash);
+ hash, false);
if (conf) {
nfsd4_remove_clid_dir(conf);
expire_client(conf);
fp = kmem_cache_alloc(file_slab, GFP_KERNEL);
if (fp) {
- kref_init(&fp->fi_ref);
+ atomic_set(&fp->fi_ref, 1);
INIT_LIST_HEAD(&fp->fi_hash);
INIT_LIST_HEAD(&fp->fi_stateids);
INIT_LIST_HEAD(&fp->fi_delegations);
+ spin_lock(&recall_lock);
list_add(&fp->fi_hash, &file_hashtbl[hashval]);
+ spin_unlock(&recall_lock);
fp->fi_inode = igrab(ino);
fp->fi_id = current_fileid++;
fp->fi_had_conflict = false;
return sop;
}
-static void
-release_stateid_lockowners(struct nfs4_stateid *open_stp)
-{
- struct nfs4_stateowner *lock_sop;
-
- while (!list_empty(&open_stp->st_lockowners)) {
- lock_sop = list_entry(open_stp->st_lockowners.next,
- struct nfs4_stateowner, so_perstateid);
- /* list_del(&open_stp->st_lockowners); */
- BUG_ON(lock_sop->so_is_open_owner);
- release_stateowner(lock_sop);
- }
-}
-
-static void
-unhash_stateowner(struct nfs4_stateowner *sop)
-{
- struct nfs4_stateid *stp;
-
- list_del(&sop->so_idhash);
- list_del(&sop->so_strhash);
- if (sop->so_is_open_owner)
- list_del(&sop->so_perclient);
- list_del(&sop->so_perstateid);
- while (!list_empty(&sop->so_stateids)) {
- stp = list_entry(sop->so_stateids.next,
- struct nfs4_stateid, st_perstateowner);
- if (sop->so_is_open_owner)
- release_stateid(stp, OPEN_STATE);
- else
- release_stateid(stp, LOCK_STATE);
- }
-}
-
-static void
-release_stateowner(struct nfs4_stateowner *sop)
-{
- unhash_stateowner(sop);
- list_del(&sop->so_close_lru);
- nfs4_put_stateowner(sop);
-}
-
static inline void
init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
struct nfs4_stateowner *sop = open->op_stateowner;
stp->st_stateowner = sop;
get_nfs4_file(fp);
stp->st_file = fp;
- stp->st_stateid.si_boot = boot_time;
+ stp->st_stateid.si_boot = get_seconds();
stp->st_stateid.si_stateownerid = sop->so_id;
stp->st_stateid.si_fileid = fp->fi_id;
stp->st_stateid.si_generation = 0;
stp->st_access_bmap = 0;
stp->st_deny_bmap = 0;
- __set_bit(open->op_share_access, &stp->st_access_bmap);
+ __set_bit(open->op_share_access & ~NFS4_SHARE_WANT_MASK,
+ &stp->st_access_bmap);
__set_bit(open->op_share_deny, &stp->st_deny_bmap);
stp->st_openstp = NULL;
}
static void
-release_stateid(struct nfs4_stateid *stp, int flags)
-{
- struct file *filp = stp->st_vfs_file;
-
- list_del(&stp->st_hash);
- list_del(&stp->st_perfile);
- list_del(&stp->st_perstateowner);
- if (flags & OPEN_STATE) {
- release_stateid_lockowners(stp);
- stp->st_vfs_file = NULL;
- nfsd_close(filp);
- } else if (flags & LOCK_STATE)
- locks_remove_posix(filp, (fl_owner_t) stp->st_stateowner);
- put_nfs4_file(stp->st_file);
- kmem_cache_free(stateid_slab, stp);
-}
-
-static void
move_to_close_lru(struct nfs4_stateowner *sop)
{
dprintk("NFSD: move_to_close_lru nfs4_stateowner %p\n", sop);
unsigned int hashval = file_hashval(ino);
struct nfs4_file *fp;
+ spin_lock(&recall_lock);
list_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) {
if (fp->fi_inode == ino) {
get_nfs4_file(fp);
+ spin_unlock(&recall_lock);
return fp;
}
}
+ spin_unlock(&recall_lock);
return NULL;
}
-static inline int access_valid(u32 x)
+static inline int access_valid(u32 x, u32 minorversion)
{
- if (x < NFS4_SHARE_ACCESS_READ)
+ if ((x & NFS4_SHARE_ACCESS_MASK) < NFS4_SHARE_ACCESS_READ)
return 0;
- if (x > NFS4_SHARE_ACCESS_BOTH)
+ if ((x & NFS4_SHARE_ACCESS_MASK) > NFS4_SHARE_ACCESS_BOTH)
+ return 0;
+ x &= ~NFS4_SHARE_ACCESS_MASK;
+ if (minorversion && x) {
+ if ((x & NFS4_SHARE_WANT_MASK) > NFS4_SHARE_WANT_CANCEL)
+ return 0;
+ if ((x & NFS4_SHARE_WHEN_MASK) > NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED)
+ return 0;
+ x &= ~(NFS4_SHARE_WANT_MASK | NFS4_SHARE_WHEN_MASK);
+ }
+ if (x)
return 0;
return 1;
}
return x <= NFS4_SHARE_DENY_BOTH;
}
+/*
+ * We store the NONE, READ, WRITE, and BOTH bits separately in the
+ * st_{access,deny}_bmap field of the stateid, in order to track not
+ * only what share bits are currently in force, but also what
+ * combinations of share bits previous opens have used. This allows us
+ * to enforce the recommendation of rfc 3530 14.2.19 that the server
+ * return an error if the client attempt to downgrade to a combination
+ * of share bits not explicable by closing some of its previous opens.
+ *
+ * XXX: This enforcement is actually incomplete, since we don't keep
+ * track of access/deny bit combinations; so, e.g., we allow:
+ *
+ * OPEN allow read, deny write
+ * OPEN allow both, deny none
+ * DOWNGRADE allow read, deny none
+ *
+ * which we should reject.
+ */
static void
set_access(unsigned int *access, unsigned long bmap) {
int i;
}
/*
- * Recall a delegation
- */
-static int
-do_recall(void *__dp)
-{
- struct nfs4_delegation *dp = __dp;
-
- dp->dl_file->fi_had_conflict = true;
- nfsd4_cb_recall(dp);
- return 0;
-}
-
-/*
* Spawn a thread to perform a recall on the delegation represented
* by the lease (file_lock)
*
static
void nfsd_break_deleg_cb(struct file_lock *fl)
{
- struct nfs4_delegation *dp= (struct nfs4_delegation *)fl->fl_owner;
- struct task_struct *t;
+ struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
dprintk("NFSD nfsd_break_deleg_cb: dp %p fl %p\n",dp,fl);
if (!dp)
*/
fl->fl_break_time = 0;
- t = kthread_run(do_recall, dp, "%s", "nfs4_cb_recall");
- if (IS_ERR(t)) {
- struct nfs4_client *clp = dp->dl_client;
-
- 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);
- }
+ dp->dl_file->fi_had_conflict = true;
+ nfsd4_cb_recall(dp);
}
/*
__be32
-nfsd4_process_open1(struct nfsd4_open *open)
+nfsd4_process_open1(struct nfsd4_compound_state *cstate,
+ struct nfsd4_open *open)
{
clientid_t *clientid = &open->op_clientid;
struct nfs4_client *clp = NULL;
return nfserr_expired;
goto renew;
}
+ /* When sessions are used, skip open sequenceid processing */
+ if (nfsd4_has_session(cstate))
+ goto renew;
if (!sop->so_confirmed) {
/* Replace unconfirmed owners without checking for replay. */
clp = sop->so_client;
- release_stateowner(sop);
+ release_openowner(sop);
open->op_stateowner = NULL;
goto renew;
}
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) {
}
/* remember the open */
filp->f_mode |= open->op_share_access;
- set_bit(open->op_share_access, &stp->st_access_bmap);
- set_bit(open->op_share_deny, &stp->st_deny_bmap);
+ __set_bit(open->op_share_access, &stp->st_access_bmap);
+ __set_bit(open->op_share_deny, &stp->st_deny_bmap);
return nfs_ok;
}
{
struct nfs4_delegation *dp;
struct nfs4_stateowner *sop = stp->st_stateowner;
- struct nfs4_callback *cb = &sop->so_client->cl_callback;
+ struct nfs4_cb_conn *cb = &sop->so_client->cl_cb_conn;
struct file_lock fl, *flp = &fl;
int status, flag = 0;
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;
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;
/* vfs_setlease checks to see if delegation should be handed out.
* the lock_manager callbacks fl_mylease and fl_change are used
*/
- if ((status = vfs_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;
__be32
nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
+ struct nfsd4_compoundres *resp = rqstp->rq_resp;
struct nfs4_file *fp = NULL;
struct inode *ino = current_fh->fh_dentry->d_inode;
struct nfs4_stateid *stp = NULL;
__be32 status;
status = nfserr_inval;
- if (!access_valid(open->op_share_access)
+ if (!access_valid(open->op_share_access, resp->cstate.minorversion)
|| !deny_valid(open->op_share_deny))
goto out;
/*
/* Stateid was not found, this is a new OPEN */
int flags = 0;
if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
- flags |= MAY_READ;
+ flags |= NFSD_MAY_READ;
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
- flags |= MAY_WRITE;
+ flags |= NFSD_MAY_WRITE;
status = nfs4_new_open(rqstp, &stp, dp, current_fh, flags);
if (status)
goto out;
init_stateid(stp, fp, open);
status = nfsd4_truncate(rqstp, current_fh, open);
if (status) {
- release_stateid(stp, OPEN_STATE);
+ release_open_stateid(stp);
goto out;
}
+ if (nfsd4_has_session(&resp->cstate))
+ update_stateid(&stp->st_stateid);
}
memcpy(&open->op_stateid, &stp->st_stateid, sizeof(stateid_t));
+ if (nfsd4_has_session(&resp->cstate))
+ open->op_stateowner->so_confirmed = 1;
+
/*
* Attempt to hand out a delegation. No error return, because the
* OPEN succeeds even if we fail.
* To finish the open response, we just need to set the rflags.
*/
open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX;
- if (!open->op_stateowner->so_confirmed)
+ if (!open->op_stateowner->so_confirmed &&
+ !nfsd4_has_session(&resp->cstate))
open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM;
return status;
}
-static struct workqueue_struct *laundry_wq;
-static void laundromat_main(struct work_struct *);
-static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main);
-
__be32
nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
clientid_t *clid)
renew_client(clp);
status = nfserr_cb_path_down;
if (!list_empty(&clp->cl_delegations)
- && !atomic_read(&clp->cl_callback.cb_set))
+ && !atomic_read(&clp->cl_cb_conn.cb_set))
goto out;
status = nfs_ok;
out:
return status;
}
+struct lock_manager nfsd4_manager = {
+};
+
static void
-end_grace(void)
+nfsd4_end_grace(void)
{
dprintk("NFSD: end of grace period\n");
nfsd4_recdir_purge_old();
- in_grace = 0;
+ locks_end_grace(&nfsd4_manager);
}
static time_t
nfs4_lock_state();
dprintk("NFSD: laundromat service - starting\n");
- if (in_grace)
- end_grace();
+ if (locks_in_grace())
+ nfsd4_end_grace();
list_for_each_safe(pos, next, &client_lru) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) {
}
dprintk("NFSD: purging unused open stateowner (so_id %d)\n",
sop->so_id);
- release_stateowner(sop);
+ release_openowner(sop);
}
if (clientid_val < NFSD_LAUNDROMAT_MINTIMEOUT)
clientid_val = NFSD_LAUNDROMAT_MINTIMEOUT;
return clientid_val;
}
-void
+static struct workqueue_struct *laundry_wq;
+static void laundromat_main(struct work_struct *);
+static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main);
+
+static void
laundromat_main(struct work_struct *not_used)
{
time_t t;
static int
STALE_STATEID(stateid_t *stateid)
{
- if (stateid->si_boot == boot_time)
- return 0;
- dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n",
- stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid,
- stateid->si_generation);
- return 1;
+ if (time_after((unsigned long)boot_time,
+ (unsigned long)stateid->si_boot)) {
+ dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n",
+ stateid->si_boot, stateid->si_stateownerid,
+ stateid->si_fileid, stateid->si_generation);
+ return 1;
+ }
+ return 0;
+}
+
+static int
+EXPIRED_STATEID(stateid_t *stateid)
+{
+ if (time_before((unsigned long)boot_time,
+ ((unsigned long)stateid->si_boot)) &&
+ time_before((unsigned long)(stateid->si_boot + lease_time), get_seconds())) {
+ dprintk("NFSD: expired stateid (%08x/%08x/%08x/%08x)!\n",
+ stateid->si_boot, stateid->si_stateownerid,
+ stateid->si_fileid, stateid->si_generation);
+ return 1;
+ }
+ return 0;
+}
+
+static __be32
+stateid_error_map(stateid_t *stateid)
+{
+ if (STALE_STATEID(stateid))
+ return nfserr_stale_stateid;
+ if (EXPIRED_STATEID(stateid))
+ return nfserr_expired;
+
+ dprintk("NFSD: bad stateid (%08x/%08x/%08x/%08x)!\n",
+ stateid->si_boot, stateid->si_stateownerid,
+ stateid->si_fileid, stateid->si_generation);
+ return nfserr_bad_stateid;
}
static inline int
static inline __be32
check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags)
{
- /* Trying to call delegreturn with a special stateid? Yuch: */
- if (!(flags & (RD_STATE | WR_STATE)))
- return nfserr_bad_stateid;
- else if (ONE_STATEID(stateid) && (flags & RD_STATE))
+ if (ONE_STATEID(stateid) && (flags & RD_STATE))
return nfs_ok;
- else if (nfs4_in_grace()) {
+ else if (locks_in_grace()) {
/* Answer in remaining cases depends on existance of
* conflicting state; so we must wait out the grace period. */
return nfserr_grace;
* that are not able to provide mandatory locking.
*/
static inline int
-io_during_grace_disallowed(struct inode *inode, int flags)
+grace_disallows_io(struct inode *inode)
+{
+ return locks_in_grace() && mandatory_lock(inode);
+}
+
+static int check_stateid_generation(stateid_t *in, stateid_t *ref, int flags)
+{
+ /*
+ * When sessions are used the stateid generation number is ignored
+ * when it is zero.
+ */
+ if ((flags & HAS_SESSION) && in->si_generation == 0)
+ goto out;
+
+ /* If the client sends us a stateid from the future, it's buggy: */
+ if (in->si_generation > ref->si_generation)
+ return nfserr_bad_stateid;
+ /*
+ * The following, however, can happen. For example, if the
+ * client sends an open and some IO at the same time, the open
+ * may bump si_generation while the IO is still in flight.
+ * Thanks to hard links and renames, the client never knows what
+ * file an open will affect. So it could avoid that situation
+ * only by serializing all opens and IO from the same open
+ * owner. To recover from the old_stateid error, the client
+ * will just have to retry the IO:
+ */
+ if (in->si_generation < ref->si_generation)
+ return nfserr_old_stateid;
+out:
+ return nfs_ok;
+}
+
+static int is_delegation_stateid(stateid_t *stateid)
{
- return nfs4_in_grace() && (flags & (RD_STATE | WR_STATE))
- && mandatory_lock(inode);
+ return stateid->si_fileid == 0;
}
/*
* Checks for stateid operations
*/
__be32
-nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int flags, struct file **filpp)
+nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
+ stateid_t *stateid, int flags, struct file **filpp)
{
struct nfs4_stateid *stp = NULL;
struct nfs4_delegation *dp = NULL;
- stateid_t *stidp;
+ struct svc_fh *current_fh = &cstate->current_fh;
struct inode *ino = current_fh->fh_dentry->d_inode;
__be32 status;
- dprintk("NFSD: preprocess_stateid_op: stateid = (%08x/%08x/%08x/%08x)\n",
- stateid->si_boot, stateid->si_stateownerid,
- stateid->si_fileid, stateid->si_generation);
if (filpp)
*filpp = NULL;
- if (io_during_grace_disallowed(ino, flags))
+ if (grace_disallows_io(ino))
return nfserr_grace;
+ if (nfsd4_has_session(cstate))
+ flags |= HAS_SESSION;
+
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
return check_special_stateids(current_fh, stateid, flags);
- /* STALE STATEID */
status = nfserr_stale_stateid;
if (STALE_STATEID(stateid))
goto out;
- /* BAD STATEID */
status = nfserr_bad_stateid;
- if (!stateid->si_fileid) { /* delegation stateid */
- if(!(dp = find_delegation_stateid(ino, stateid))) {
- dprintk("NFSD: delegation stateid not found\n");
+ if (is_delegation_stateid(stateid)) {
+ dp = find_delegation_stateid(ino, stateid);
+ if (!dp) {
+ status = stateid_error_map(stateid);
goto out;
}
- stidp = &dp->dl_stateid;
+ status = check_stateid_generation(stateid, &dp->dl_stateid,
+ flags);
+ if (status)
+ goto out;
+ status = nfs4_check_delegmode(dp, flags);
+ if (status)
+ goto out;
+ renew_client(dp->dl_client);
+ if (filpp)
+ *filpp = dp->dl_vfs_file;
} else { /* open or lock stateid */
- if (!(stp = find_stateid(stateid, flags))) {
- dprintk("NFSD: open or lock stateid not found\n");
+ stp = find_stateid(stateid, flags);
+ if (!stp) {
+ status = stateid_error_map(stateid);
goto out;
}
- if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp))
+ if (nfs4_check_fh(current_fh, stp))
goto out;
if (!stp->st_stateowner->so_confirmed)
goto out;
- stidp = &stp->st_stateid;
- }
- if (stateid->si_generation > stidp->si_generation)
- goto out;
-
- /* OLD STATEID */
- status = nfserr_old_stateid;
- if (stateid->si_generation < stidp->si_generation)
- goto out;
- if (stp) {
- if ((status = nfs4_check_openmode(stp,flags)))
+ status = check_stateid_generation(stateid, &stp->st_stateid,
+ flags);
+ if (status)
+ goto out;
+ status = nfs4_check_openmode(stp, flags);
+ if (status)
goto out;
renew_client(stp->st_stateowner->so_client);
if (filpp)
*filpp = stp->st_vfs_file;
- } else if (dp) {
- if ((status = nfs4_check_delegmode(dp, flags)))
- goto out;
- renew_client(dp->dl_client);
- if (flags & DELEG_RET)
- unhash_delegation(dp);
- if (filpp)
- *filpp = dp->dl_vfs_file;
}
status = nfs_ok;
out:
* Checks for sequence id mutating operations.
*/
static __be32
-nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *stateid, int flags, struct nfs4_stateowner **sopp, struct nfs4_stateid **stpp, struct nfsd4_lock *lock)
+nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
+ stateid_t *stateid, int flags,
+ struct nfs4_stateowner **sopp,
+ struct nfs4_stateid **stpp, struct nfsd4_lock *lock)
{
struct nfs4_stateid *stp;
struct nfs4_stateowner *sop;
+ struct svc_fh *current_fh = &cstate->current_fh;
+ __be32 status;
dprintk("NFSD: preprocess_seqid_op: seqid=%d "
"stateid = (%08x/%08x/%08x/%08x)\n", seqid,
if (STALE_STATEID(stateid))
return nfserr_stale_stateid;
+
+ if (nfsd4_has_session(cstate))
+ flags |= HAS_SESSION;
+
/*
* We return BAD_STATEID if filehandle doesn't match stateid,
* the confirmed flag is incorrecly set, or the generation
*/
sop = search_close_lru(stateid->si_stateownerid, flags);
if (sop == NULL)
- return nfserr_bad_stateid;
+ return stateid_error_map(stateid);
*sopp = sop;
goto check_replay;
}
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;
+ if (!(flags & HAS_SESSION) &&
+ !same_clid(&clp->cl_clientid, lockclid))
+ return nfserr_bad_stateid;
/* stp is the open stateid */
status = nfs4_check_openmode(stp, lkflg);
if (status)
* For the moment, we ignore the possibility of
* generation number wraparound.
*/
- if (seqid != sop->so_seqid)
+ if (!(flags & HAS_SESSION) && seqid != sop->so_seqid)
goto check_replay;
if (sop->so_confirmed && flags & CONFIRM) {
" confirmed yet!\n");
return nfserr_bad_stateid;
}
- if (stateid->si_generation > stp->st_stateid.si_generation) {
- dprintk("NFSD: preprocess_seqid_op: future stateid?!\n");
- return nfserr_bad_stateid;
- }
-
- if (stateid->si_generation < stp->st_stateid.si_generation) {
- dprintk("NFSD: preprocess_seqid_op: old stateid!\n");
- return nfserr_old_stateid;
- }
+ status = check_stateid_generation(stateid, &stp->st_stateid, flags);
+ if (status)
+ return status;
renew_client(sop->so_client);
return nfs_ok;
nfs4_lock_state();
- if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
+ if ((status = nfs4_preprocess_seqid_op(cstate,
oc->oc_seqid, &oc->oc_req_stateid,
CONFIRM | OPEN_STATE,
&oc->oc_stateowner, &stp, NULL)))
(int)cstate->current_fh.fh_dentry->d_name.len,
cstate->current_fh.fh_dentry->d_name.name);
- if (!access_valid(od->od_share_access)
+ if (!access_valid(od->od_share_access, cstate->minorversion)
|| !deny_valid(od->od_share_deny))
return nfserr_inval;
nfs4_lock_state();
- if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
+ if ((status = nfs4_preprocess_seqid_op(cstate,
od->od_seqid,
&od->od_stateid,
OPEN_STATE,
nfs4_lock_state();
/* check close_lru for replay */
- if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
+ if ((status = nfs4_preprocess_seqid_op(cstate,
close->cl_seqid,
&close->cl_stateid,
OPEN_STATE | CLOSE_STATE,
memcpy(&close->cl_stateid, &stp->st_stateid, sizeof(stateid_t));
/* release_stateid() calls nfsd_close() if needed */
- release_stateid(stp, OPEN_STATE);
+ release_open_stateid(stp);
/* place unused nfs4_stateowners on so_close_lru list to be
* released by the laundromat service after the lease period
nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_delegreturn *dr)
{
+ struct nfs4_delegation *dp;
+ stateid_t *stateid = &dr->dr_stateid;
+ struct inode *inode;
__be32 status;
+ int flags = 0;
if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
- goto out;
+ return status;
+ inode = cstate->current_fh.fh_dentry->d_inode;
+ if (nfsd4_has_session(cstate))
+ flags |= HAS_SESSION;
nfs4_lock_state();
- status = nfs4_preprocess_stateid_op(&cstate->current_fh,
- &dr->dr_stateid, DELEG_RET, NULL);
- nfs4_unlock_state();
+ status = nfserr_bad_stateid;
+ if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
+ goto out;
+ status = nfserr_stale_stateid;
+ if (STALE_STATEID(stateid))
+ goto out;
+ status = nfserr_bad_stateid;
+ if (!is_delegation_stateid(stateid))
+ goto out;
+ dp = find_delegation_stateid(inode, stateid);
+ if (!dp) {
+ status = stateid_error_map(stateid);
+ goto out;
+ }
+ status = check_stateid_generation(stateid, &dp->dl_stateid, flags);
+ if (status)
+ goto out;
+ renew_client(dp->dl_client);
+
+ unhash_delegation(dp);
out:
+ nfs4_unlock_state();
+
return status;
}
#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)
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) &&
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) &&
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)
stp->st_stateowner = sop;
get_nfs4_file(fp);
stp->st_file = fp;
- stp->st_stateid.si_boot = boot_time;
+ stp->st_stateid.si_boot = get_seconds();
stp->st_stateid.si_stateownerid = sop->so_id;
stp->st_stateid.si_fileid = fp->fi_id;
stp->st_stateid.si_generation = 0;
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)));
}
return nfserr_inval;
if ((status = fh_verify(rqstp, &cstate->current_fh,
- S_IFREG, MAY_LOCK))) {
+ S_IFREG, NFSD_MAY_LOCK))) {
dprintk("NFSD: nfsd4_lock: permission denied!\n");
return status;
}
struct nfs4_file *fp;
status = nfserr_stale_clientid;
- if (STALE_CLIENTID(&lock->lk_new_clientid))
+ if (!nfsd4_has_session(cstate) &&
+ STALE_CLIENTID(&lock->lk_new_clientid))
goto out;
/* validate and update open stateid and open seqid */
- status = nfs4_preprocess_seqid_op(&cstate->current_fh,
+ status = nfs4_preprocess_seqid_op(cstate,
lock->lk_new_open_seqid,
&lock->lk_new_open_stateid,
OPEN_STATE,
goto out;
} else {
/* lock (lock owner + lock stateid) already exists */
- status = nfs4_preprocess_seqid_op(&cstate->current_fh,
+ status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
&lock->lk_old_lock_stateid,
LOCK_STATE,
filp = lock_stp->st_vfs_file;
status = nfserr_grace;
- if (nfs4_in_grace() && !lock->lk_reclaim)
+ if (locks_in_grace() && !lock->lk_reclaim)
goto out;
status = nfserr_no_grace;
- if (!nfs4_in_grace() && lock->lk_reclaim)
+ if (!locks_in_grace() && lock->lk_reclaim)
goto out;
locks_init_lock(&file_lock);
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);
/*
* Note: locks.c uses the BKL to protect the inode's lock list.
*/
- /* XXX?: Just to divert the locks_release_private at the start of
- * locks_copy_lock: */
- locks_init_lock(&conflock);
err = vfs_lock_file(filp, cmd, &file_lock, &conflock);
switch (-err) {
case 0: /* success! */
}
out:
if (status && lock->lk_is_new && lock_sop)
- release_stateowner(lock_sop);
+ release_lockowner(lock_sop);
if (lock->lk_replay_owner) {
nfs4_get_stateowner(lock->lk_replay_owner);
cstate->replay_owner = lock->lk_replay_owner;
}
/*
+ * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN,
+ * so we do a temporary open here just to get an open file to pass to
+ * vfs_test_lock. (Arguably perhaps test_lock should be done with an
+ * inode operation.)
+ */
+static int nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock)
+{
+ struct file *file;
+ int err;
+
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
+ if (err)
+ return err;
+ err = vfs_test_lock(file, lock);
+ nfsd_close(file);
+ return err;
+}
+
+/*
* LOCKT operation
*/
__be32
struct nfsd4_lockt *lockt)
{
struct inode *inode;
- struct file file;
struct file_lock file_lock;
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))
nfs4_lock_state();
status = nfserr_stale_clientid;
- if (STALE_CLIENTID(&lockt->lt_clientid))
+ if (!nfsd4_has_session(cstate) && STALE_CLIENTID(&lockt->lt_clientid))
goto out;
if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) {
file_lock.fl_owner = (fl_owner_t)lockt->lt_stateowner;
file_lock.fl_pid = current->tgid;
file_lock.fl_flags = FL_POSIX;
- file_lock.fl_lmops = &nfsd_posix_mng_ops;
file_lock.fl_start = lockt->lt_offset;
- if ((lockt->lt_length == ~(u64)0) || LOFF_OVERFLOW(lockt->lt_offset, lockt->lt_length))
- file_lock.fl_end = ~(u64)0;
- else
- file_lock.fl_end = lockt->lt_offset + lockt->lt_length - 1;
+ file_lock.fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length);
nfs4_transform_lock_offset(&file_lock);
- /* vfs_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 vfs_test_lock a struct file with
- * only the dentry:inode set.
- */
- memset(&file, 0, sizeof (struct file));
- file.f_path.dentry = cstate->current_fh.fh_dentry;
-
status = nfs_ok;
- error = vfs_test_lock(&file, &file_lock);
+ error = nfsd_test_lock(rqstp, &cstate->current_fh, &file_lock);
if (error) {
status = nfserrno(error);
goto out;
nfs4_lock_state();
- if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
+ if ((status = nfs4_preprocess_seqid_op(cstate,
locku->lu_seqid,
&locku->lu_stateid,
LOCK_STATE,
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);
/*
/* unhash_stateowner deletes so_perclient only
* for openowners. */
list_del(&sop->so_perclient);
- release_stateowner(sop);
+ release_lockowner(sop);
}
out:
nfs4_unlock_state();
}
int
-nfs4_has_reclaimed_state(const char *name)
+nfs4_has_reclaimed_state(const char *name, bool use_exchange_id)
{
unsigned int strhashval = clientstr_hashval(name);
struct nfs4_client *clp;
- clp = find_confirmed_client_by_str(name, strhashval);
+ clp = find_confirmed_client_by_str(name, strhashval, use_exchange_id);
return clp ? 1 : 0;
}
INIT_LIST_HEAD(&conf_str_hashtbl[i]);
INIT_LIST_HEAD(&unconf_str_hashtbl[i]);
INIT_LIST_HEAD(&unconf_id_hashtbl[i]);
+ INIT_LIST_HEAD(&reclaim_str_hashtbl[i]);
}
+ for (i = 0; i < SESSION_HASH_SIZE; i++)
+ INIT_LIST_HEAD(&sessionid_hashtbl[i]);
for (i = 0; i < FILE_HASH_SIZE; i++) {
INIT_LIST_HEAD(&file_hashtbl[i]);
}
INIT_LIST_HEAD(&close_lru);
INIT_LIST_HEAD(&client_lru);
INIT_LIST_HEAD(&del_recall_lru);
- for (i = 0; i < CLIENT_HASH_SIZE; i++)
- INIT_LIST_HEAD(&reclaim_str_hashtbl[i]);
reclaim_str_hashtbl_size = 0;
return 0;
}
/* initialization to perform when the nfsd service is started: */
-static void
+static int
__nfs4_state_start(void)
{
unsigned long grace_time;
boot_time = get_seconds();
- grace_time = get_nfs_grace_period();
+ grace_time = get_nfs4_grace_period();
lease_time = user_lease_time;
- in_grace = 1;
+ locks_start_grace(&nfsd4_manager);
printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
grace_time/HZ);
laundry_wq = create_singlethread_workqueue("nfsd4");
+ if (laundry_wq == NULL)
+ return -ENOMEM;
queue_delayed_work(laundry_wq, &laundromat_work, grace_time);
set_max_delegations();
+ return 0;
}
-void
+int
nfs4_state_start(void)
{
+ int ret;
+
if (nfs4_init)
- return;
+ return 0;
nfsd4_load_reboot_recovery_data();
- __nfs4_state_start();
+ ret = __nfs4_state_start();
+ if (ret)
+ return ret;
nfs4_init = 1;
- return;
-}
-
-int
-nfs4_in_grace(void)
-{
- return in_grace;
+ return 0;
}
time_t
{
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();
nfs4_unlock_state();
}
+/*
+ * user_recovery_dirname is protected by the nfsd_mutex since it's only
+ * accessed when nfsd is starting.
+ */
static void
nfs4_set_recdir(char *recdir)
{
- nfs4_lock_state();
strcpy(user_recovery_dirname, recdir);
- nfs4_unlock_state();
}
/*
nfs4_reset_recoverydir(char *recdir)
{
int status;
- struct nameidata nd;
+ struct path path;
- status = path_lookup(recdir, LOOKUP_FOLLOW, &nd);
+ status = kern_path(recdir, LOOKUP_FOLLOW, &path);
if (status)
return status;
status = -ENOTDIR;
- if (S_ISDIR(nd.path.dentry->d_inode->i_mode)) {
+ if (S_ISDIR(path.dentry->d_inode->i_mode)) {
nfs4_set_recdir(recdir);
status = 0;
}
- path_put(&nd.path);
+ path_put(&path);
return status;
}
+char *
+nfs4_recoverydir(void)
+{
+ return user_recovery_dirname;
+}
+
/*
* Called when leasetime is changed.
*
* 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();
}