diff options
Diffstat (limited to 'fs/nfsd/nfs4state.c')
| -rw-r--r-- | fs/nfsd/nfs4state.c | 2542 |
1 files changed, 1834 insertions, 708 deletions
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index daf305daa751..808c24fb5c9a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -59,7 +59,7 @@ #define NFSDDBG_FACILITY NFSDDBG_PROC -#define all_ones {{~0,~0},~0} +#define all_ones {{ ~0, ~0}, ~0} static const stateid_t one_stateid = { .si_generation = ~0, .si_opaque = all_ones, @@ -87,6 +87,7 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); static void nfsd4_file_hash_remove(struct nfs4_file *fi); +static void deleg_reaper(struct nfsd_net *nn); /* Locking: */ @@ -127,6 +128,7 @@ static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops; static struct workqueue_struct *laundry_wq; @@ -147,14 +149,14 @@ void nfsd4_destroy_laundry_wq(void) static bool is_session_dead(struct nfsd4_session *ses) { - return ses->se_flags & NFS4_SESSION_DEAD; + return ses->se_dead; } static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me) { if (atomic_read(&ses->se_ref) > ref_held_by_me) return nfserr_jukebox; - ses->se_flags |= NFS4_SESSION_DEAD; + ses->se_dead = true; return nfs_ok; } @@ -297,7 +299,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, nbl = find_blocked_lock(lo, fh, nn); if (!nbl) { - nbl= kmalloc(sizeof(*nbl), GFP_KERNEL); + nbl = kmalloc(sizeof(*nbl), GFP_KERNEL); if (nbl) { INIT_LIST_HEAD(&nbl->nbl_list); INIT_LIST_HEAD(&nbl->nbl_lru); @@ -318,6 +320,7 @@ free_nbl(struct kref *kref) struct nfsd4_blocked_lock *nbl; nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref); + locks_release_private(&nbl->nbl_lock); kfree(nbl); } @@ -325,7 +328,6 @@ static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { locks_delete_block(&nbl->nbl_lock); - locks_release_private(&nbl->nbl_lock); kref_put(&nbl->nbl_kref, free_nbl); } @@ -398,6 +400,7 @@ static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, + .opcode = OP_CB_NOTIFY_LOCK, }; /* @@ -539,7 +542,7 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner) } static struct nfs4_openowner * -find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open, +find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, struct nfs4_client *clp) { struct nfs4_stateowner *so; @@ -556,18 +559,6 @@ find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open, return NULL; } -static struct nfs4_openowner * -find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, - struct nfs4_client *clp) -{ - struct nfs4_openowner *oo; - - spin_lock(&clp->cl_lock); - oo = find_openstateowner_str_locked(hashval, open, clp); - spin_unlock(&clp->cl_lock); - return oo; -} - static inline u32 opaque_hashval(const void *ptr, int nbytes) { @@ -581,13 +572,6 @@ opaque_hashval(const void *ptr, int nbytes) return x; } -static void nfsd4_free_file_rcu(struct rcu_head *rcu) -{ - struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu); - - kmem_cache_free(file_slab, fp); -} - void put_nfs4_file(struct nfs4_file *fi) { @@ -595,7 +579,7 @@ put_nfs4_file(struct nfs4_file *fi) nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); - call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); + kfree_rcu(fi, fi_rcu); } } @@ -950,15 +934,6 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla spin_lock_init(&stid->sc_lock); INIT_LIST_HEAD(&stid->sc_cp_list); - /* - * It shouldn't be a problem to reuse an opaque stateid value. - * I don't think it is for 4.1. But with 4.0 I worry that, for - * example, a stray write retransmission could be accepted by - * the server when it should have been rejected. Therefore, - * adopt a trick from the sctp code to attempt to maximize the - * amount of time until an id is reused, by ensuring they always - * "increase" (mod INT_MAX): - */ return stid; out_free: kmem_cache_free(slab, stid); @@ -1054,6 +1029,12 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) return openlockstateid(stid); } +/* + * As the sc_free callback of deleg, this may be called by nfs4_put_stid + * in nfsd_break_one_deleg. + * Considering nfsd_break_one_deleg is called with the flc->flc_lock held, + * this function mustn't ever sleep. + */ static void nfs4_free_deleg(struct nfs4_stid *stid) { struct nfs4_delegation *dp = delegstateid(stid); @@ -1075,7 +1056,8 @@ static void nfs4_free_deleg(struct nfs4_stid *stid) * When a delegation is recalled, the filehandle is stored in the "new" * filter. * Every 30 seconds we swap the filters and clear the "new" one, - * unless both are empty of course. + * unless both are empty of course. This results in delegations for a + * given filehandle being blocked for between 30 and 60 seconds. * * Each filter is 256 bits. We hash the filehandle to 32bit and use the * low 3 bytes as hash-table indices. @@ -1104,9 +1086,9 @@ static int delegation_blocked(struct knfsd_fh *fh) if (ktime_get_seconds() - bd->swap_time > 30) { bd->entries -= bd->old_entries; bd->old_entries = bd->entries; + bd->new = 1-bd->new; memset(bd->set[bd->new], 0, sizeof(bd->set[0])); - bd->new = 1-bd->new; bd->swap_time = ktime_get_seconds(); } spin_unlock(&blocked_delegations_lock); @@ -1144,9 +1126,10 @@ static void block_delegations(struct knfsd_fh *fh) static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, - struct nfs4_clnt_odstate *odstate) + struct nfs4_clnt_odstate *odstate, u32 dl_type) { struct nfs4_delegation *dp; + struct nfs4_stid *stid; long n; dprintk("NFSD alloc_init_deleg\n"); @@ -1155,9 +1138,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, goto out_dec; if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; - dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); - if (dp == NULL) + stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg); + if (stid == NULL) goto out_dec; + dp = delegstateid(stid); /* * delegation seqid's are never incremented. The 4.1 special @@ -1170,11 +1154,14 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, INIT_LIST_HEAD(&dp->dl_recall_lru); dp->dl_clnt_odstate = odstate; get_clnt_odstate(odstate); - dp->dl_type = NFS4_OPEN_DELEGATE_READ; + dp->dl_type = dl_type; dp->dl_retries = 1; dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); + nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client, + &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR); + dp->dl_cb_fattr.ncf_file_modified = false; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; @@ -1196,6 +1183,8 @@ nfs4_put_stid(struct nfs4_stid *s) return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + atomic_dec(&s->sc_client->cl_admin_revoked); nfs4_free_cpntf_statelist(clp->net, s); spin_unlock(&clp->cl_lock); s->sc_free(s); @@ -1217,15 +1206,56 @@ nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) static void put_deleg_file(struct nfs4_file *fp) { + struct nfsd_file *rnf = NULL; struct nfsd_file *nf = NULL; spin_lock(&fp->fi_lock); - if (--fp->fi_delegees == 0) + if (--fp->fi_delegees == 0) { swap(nf, fp->fi_deleg_file); + swap(rnf, fp->fi_rdeleg_file); + } spin_unlock(&fp->fi_lock); if (nf) nfsd_file_put(nf); + if (rnf) + nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ); +} + +static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) +{ + struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME }; + struct inode *inode = file_inode(f); + int ret; + + /* don't do anything if FMODE_NOCMTIME isn't set */ + if ((READ_ONCE(f->f_mode) & FMODE_NOCMTIME) == 0) + return; + + spin_lock(&f->f_lock); + f->f_mode &= ~FMODE_NOCMTIME; + spin_unlock(&f->f_lock); + + /* was it never written? */ + if (!dp->dl_written) + return; + + /* did it get a setattr for the timestamps at some point? */ + if (dp->dl_setattr) + return; + + /* Stamp everything to "now" */ + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, f->f_path.dentry, &ia, NULL); + inode_unlock(inode); + if (ret) { + struct inode *inode = file_inode(f); + + pr_notice_ratelimited("Unable to update timestamps on inode %02x:%02x:%lu: %d\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), + inode->i_ino, ret); + } } static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) @@ -1235,7 +1265,8 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) WARN_ON_ONCE(!fp->fi_delegees); - vfs_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); + nfsd4_finalize_deleg_timestamps(dp, nf->nf_file); + kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); put_deleg_file(fp); } @@ -1246,11 +1277,6 @@ static void destroy_unhashed_deleg(struct nfs4_delegation *dp) nfs4_put_stid(&dp->dl_stid); } -void nfs4_unhash_stid(struct nfs4_stid *s) -{ - s->sc_type = 0; -} - /** * nfs4_delegation_exists - Discover if this delegation already exists * @clp: a pointer to the nfs4_client we're granting a delegation to @@ -1298,11 +1324,12 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); + lockdep_assert_held(&clp->cl_lock); if (nfs4_delegation_exists(clp, fp)) return -EAGAIN; refcount_inc(&dp->dl_stid.sc_count); - dp->dl_stid.sc_type = NFS4_DELEG_STID; + dp->dl_stid.sc_type = SC_TYPE_DELEG; list_add(&dp->dl_perfile, &fp->fi_delegations); list_add(&dp->dl_perclnt, &clp->cl_delegations); return 0; @@ -1314,7 +1341,7 @@ static bool delegation_hashed(struct nfs4_delegation *dp) } static bool -unhash_delegation_locked(struct nfs4_delegation *dp) +unhash_delegation_locked(struct nfs4_delegation *dp, unsigned short statusmask) { struct nfs4_file *fp = dp->dl_stid.sc_file; @@ -1323,7 +1350,13 @@ unhash_delegation_locked(struct nfs4_delegation *dp) if (!delegation_hashed(dp)) return false; - dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID; + if (statusmask == SC_STATUS_REVOKED && + dp->dl_stid.sc_client->cl_minorversion == 0) + statusmask = SC_STATUS_CLOSED; + dp->dl_stid.sc_status |= statusmask; + if (statusmask & SC_STATUS_ADMIN_REVOKED) + atomic_inc(&dp->dl_stid.sc_client->cl_admin_revoked); + /* Ensure that deleg break won't try to requeue it */ ++dp->dl_time; spin_lock(&fp->fi_lock); @@ -1339,32 +1372,59 @@ static void destroy_delegation(struct nfs4_delegation *dp) bool unhashed; spin_lock(&state_lock); - unhashed = unhash_delegation_locked(dp); + unhashed = unhash_delegation_locked(dp, SC_STATUS_CLOSED); spin_unlock(&state_lock); if (unhashed) destroy_unhashed_deleg(dp); } +/** + * revoke_delegation - perform nfs4 delegation structure cleanup + * @dp: pointer to the delegation + * + * This function assumes that it's called either from the administrative + * interface (nfsd4_revoke_states()) that's revoking a specific delegation + * stateid or it's called from a laundromat thread (nfsd4_landromat()) that + * determined that this specific state has expired and needs to be revoked + * (both mark state with the appropriate stid sc_status mode). It is also + * assumed that a reference was taken on the @dp state. + * + * If this function finds that the @dp state is SC_STATUS_FREED it means + * that a FREE_STATEID operation for this stateid has been processed and + * we can proceed to removing it from recalled list. However, if @dp state + * isn't marked SC_STATUS_FREED, it means we need place it on the cl_revoked + * list and wait for the FREE_STATEID to arrive from the client. At the same + * time, we need to mark it as SC_STATUS_FREEABLE to indicate to the + * nfsd4_free_stateid() function that this stateid has already been added + * to the cl_revoked list and that nfsd4_free_stateid() is now responsible + * for removing it from the list. Inspection of where the delegation state + * in the revocation process is protected by the clp->cl_lock. + */ static void revoke_delegation(struct nfs4_delegation *dp) { struct nfs4_client *clp = dp->dl_stid.sc_client; WARN_ON(!list_empty(&dp->dl_recall_lru)); + WARN_ON_ONCE(dp->dl_stid.sc_client->cl_minorversion > 0 && + !(dp->dl_stid.sc_status & + (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED))); trace_nfsd_stid_revoke(&dp->dl_stid); - if (clp->cl_minorversion) { - spin_lock(&clp->cl_lock); - dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; - refcount_inc(&dp->dl_stid.sc_count); - list_add(&dp->dl_recall_lru, &clp->cl_revoked); - spin_unlock(&clp->cl_lock); + spin_lock(&clp->cl_lock); + if (dp->dl_stid.sc_status & SC_STATUS_FREED) { + list_del_init(&dp->dl_recall_lru); + goto out; } + list_add(&dp->dl_recall_lru, &clp->cl_revoked); + dp->dl_stid.sc_status |= SC_STATUS_FREEABLE; +out: + spin_unlock(&clp->cl_lock); destroy_unhashed_deleg(dp); } -/* - * SETCLIENTID state +/* + * SETCLIENTID state */ static unsigned int clientid_hashval(u32 id) @@ -1385,11 +1445,16 @@ static void recalculate_deny_mode(struct nfs4_file *fp) { struct nfs4_ol_stateid *stp; + u32 old_deny; spin_lock(&fp->fi_lock); + old_deny = fp->fi_share_deny; fp->fi_share_deny = 0; - list_for_each_entry(stp, &fp->fi_stateids, st_perfile) + list_for_each_entry(stp, &fp->fi_stateids, st_perfile) { fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap); + if (fp->fi_share_deny == old_deny) + break; + } spin_unlock(&fp->fi_lock); } @@ -1477,7 +1542,8 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid) release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); - WARN_ON(!list_empty(&stid->sc_cp_list)); + if (!list_empty(&stid->sc_cp_list)) + nfs4_free_cpntf_statelist(stid->sc_client->net, stid); kmem_cache_free(stateid_slab, stid); } @@ -1517,6 +1583,8 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + atomic_dec(&s->sc_client->cl_admin_revoked); list_add(&stp->st_locks, reaplist); } @@ -1527,7 +1595,7 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) if (!unhash_ol_stateid(stp)) return false; list_del_init(&stp->st_locks); - nfs4_unhash_stid(&stp->st_stid); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; return true; } @@ -1585,7 +1653,7 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, while (!list_empty(&open_stp->st_locks)) { stp = list_entry(open_stp->st_locks.next, struct nfs4_ol_stateid, st_locks); - WARN_ON(!unhash_lock_stateid(stp)); + unhash_lock_stateid(stp); put_ol_stateid_locked(stp, reaplist); } } @@ -1606,12 +1674,21 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp) LIST_HEAD(reaplist); spin_lock(&stp->st_stid.sc_client->cl_lock); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); spin_unlock(&stp->st_stid.sc_client->cl_lock); free_ol_stateid_reaplist(&reaplist); } +static bool nfs4_openowner_unhashed(struct nfs4_openowner *oo) +{ + lockdep_assert_held(&oo->oo_owner.so_client->cl_lock); + + return list_empty(&oo->oo_owner.so_strhash) && + list_empty(&oo->oo_perclient); +} + static void unhash_openowner_locked(struct nfs4_openowner *oo) { struct nfs4_client *clp = oo->oo_owner.so_client; @@ -1643,9 +1720,7 @@ static void release_openowner(struct nfs4_openowner *oo) { struct nfs4_ol_stateid *stp; struct nfs4_client *clp = oo->oo_owner.so_client; - struct list_head reaplist; - - INIT_LIST_HEAD(&reaplist); + LIST_HEAD(reaplist); spin_lock(&clp->cl_lock); unhash_openowner_locked(oo); @@ -1661,6 +1736,137 @@ static void release_openowner(struct nfs4_openowner *oo) nfs4_put_stateowner(&oo->oo_owner); } +static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, + struct super_block *sb, + unsigned int sc_types) +{ + unsigned long id, tmp; + struct nfs4_stid *stid; + + spin_lock(&clp->cl_lock); + idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) + if ((stid->sc_type & sc_types) && + stid->sc_status == 0 && + stid->sc_file->fi_inode->i_sb == sb) { + refcount_inc(&stid->sc_count); + break; + } + spin_unlock(&clp->cl_lock); + return stid; +} + +/** + * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem + * @net: used to identify instance of nfsd (there is one per net namespace) + * @sb: super_block used to identify target filesystem + * + * All nfs4 states (open, lock, delegation, layout) held by the server instance + * and associated with a file on the given filesystem will be revoked resulting + * in any files being closed and so all references from nfsd to the filesystem + * being released. Thus nfsd will no longer prevent the filesystem from being + * unmounted. + * + * The clients which own the states will subsequently being notified that the + * states have been "admin-revoked". + */ +void nfsd4_revoke_states(struct net *net, struct super_block *sb) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unsigned int idhashval; + unsigned int sc_types; + + sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; + + spin_lock(&nn->client_lock); + for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { + struct list_head *head = &nn->conf_id_hashtbl[idhashval]; + struct nfs4_client *clp; + retry: + list_for_each_entry(clp, head, cl_idhash) { + struct nfs4_stid *stid = find_one_sb_stid(clp, sb, + sc_types); + if (stid) { + struct nfs4_ol_stateid *stp; + struct nfs4_delegation *dp; + struct nfs4_layout_stateid *ls; + + spin_unlock(&nn->client_lock); + switch (stid->sc_type) { + case SC_TYPE_OPEN: + stp = openlockstateid(stid); + mutex_lock_nested(&stp->st_mutex, + OPEN_STATEID_MUTEX); + + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + spin_unlock(&clp->cl_lock); + release_all_access(stp); + } else + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + break; + case SC_TYPE_LOCK: + stp = openlockstateid(stid); + mutex_lock_nested(&stp->st_mutex, + LOCK_STATEID_MUTEX); + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + struct nfs4_lockowner *lo = + lockowner(stp->st_stateowner); + struct nfsd_file *nf; + + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + spin_unlock(&clp->cl_lock); + nf = find_any_file(stp->st_stid.sc_file); + if (nf) { + get_file(nf->nf_file); + filp_close(nf->nf_file, + (fl_owner_t)lo); + nfsd_file_put(nf); + } + release_all_access(stp); + } else + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + break; + case SC_TYPE_DELEG: + refcount_inc(&stid->sc_count); + dp = delegstateid(stid); + spin_lock(&state_lock); + if (!unhash_delegation_locked( + dp, SC_STATUS_ADMIN_REVOKED)) + dp = NULL; + spin_unlock(&state_lock); + if (dp) + revoke_delegation(dp); + break; + case SC_TYPE_LAYOUT: + ls = layoutstateid(stid); + nfsd4_close_layout(ls); + break; + } + nfs4_put_stid(stid); + spin_lock(&nn->client_lock); + if (clp->cl_minorversion == 0) + /* Allow cleanup after a lease period. + * store_release ensures cleanup will + * see any newly revoked states if it + * sees the time updated. + */ + nn->nfs40_last_revoke = + ktime_get_boottime_seconds(); + goto retry; + } + } + } + spin_unlock(&nn->client_lock); +} + static inline int hash_sessionid(struct nfs4_sessionid *sessionid) { @@ -1732,113 +1938,145 @@ gen_sessionid(struct nfsd4_session *ses) */ #define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44) +static struct shrinker *nfsd_slot_shrinker; +static DEFINE_SPINLOCK(nfsd_session_list_lock); +static LIST_HEAD(nfsd_session_list); +/* The sum of "target_slots-1" on every session. The shrinker can push this + * down, though it can take a little while for the memory to actually + * be freed. The "-1" is because we can never free slot 0 while the + * session is active. + */ +static atomic_t nfsd_total_target_slots = ATOMIC_INIT(0); + static void -free_session_slots(struct nfsd4_session *ses) +free_session_slots(struct nfsd4_session *ses, int from) { int i; - for (i = 0; i < ses->se_fchannel.maxreqs; i++) { - free_svc_cred(&ses->se_slots[i]->sl_cred); - kfree(ses->se_slots[i]); + if (from >= ses->se_fchannel.maxreqs) + return; + + for (i = from; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + + /* + * Save the seqid in case we reactivate this slot. + * This will never require a memory allocation so GFP + * flag is irrelevant + */ + xa_store(&ses->se_slots, i, xa_mk_value(slot->sl_seqid), 0); + free_svc_cred(&slot->sl_cred); + kfree(slot); + } + ses->se_fchannel.maxreqs = from; + if (ses->se_target_maxslots > from) { + int new_target = from ?: 1; + atomic_sub(ses->se_target_maxslots - new_target, &nfsd_total_target_slots); + ses->se_target_maxslots = new_target; } } -/* - * We don't actually need to cache the rpc and session headers, so we - * can allocate a little less for each slot: +/** + * reduce_session_slots - reduce the target max-slots of a session if possible + * @ses: The session to affect + * @dec: how much to decrease the target by + * + * This interface can be used by a shrinker to reduce the target max-slots + * for a session so that some slots can eventually be freed. + * It uses spin_trylock() as it may be called in a context where another + * spinlock is held that has a dependency on client_lock. As shrinkers are + * best-effort, skiping a session is client_lock is already held has no + * great coast + * + * Return value: + * The number of slots that the target was reduced by. */ -static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca) +static int +reduce_session_slots(struct nfsd4_session *ses, int dec) { - u32 size; + struct nfsd_net *nn = net_generic(ses->se_client->net, + nfsd_net_id); + int ret = 0; - if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ) - size = 0; - else - size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; - return size + sizeof(struct nfsd4_slot); + if (ses->se_target_maxslots <= 1) + return ret; + if (!spin_trylock(&nn->client_lock)) + return ret; + ret = min(dec, ses->se_target_maxslots-1); + ses->se_target_maxslots -= ret; + atomic_sub(ret, &nfsd_total_target_slots); + ses->se_slot_gen += 1; + if (ses->se_slot_gen == 0) { + int i; + ses->se_slot_gen = 1; + for (i = 0; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + slot->sl_generation = 0; + } + } + spin_unlock(&nn->client_lock); + return ret; } -/* - * XXX: If we run out of reserved DRC memory we could (up to a point) - * re-negotiate active sessions and reduce their slot usage to make - * room for new connections. For now we just fail the create session. - */ -static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn) +static struct nfsd4_slot *nfsd4_alloc_slot(struct nfsd4_channel_attrs *fattrs, + int index, gfp_t gfp) { - u32 slotsize = slot_bytes(ca); - u32 num = ca->maxreqs; - unsigned long avail, total_avail; - unsigned int scale_factor; + struct nfsd4_slot *slot; + size_t size; - spin_lock(&nfsd_drc_lock); - if (nfsd_drc_max_mem > nfsd_drc_mem_used) - total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used; - else - /* We have handed out more space than we chose in - * set_max_drc() to allow. That isn't really a - * problem as long as that doesn't make us think we - * have lots more due to integer overflow. - */ - total_avail = 0; - avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail); /* - * Never use more than a fraction of the remaining memory, - * unless it's the only way to give this client a slot. - * The chosen fraction is either 1/8 or 1/number of threads, - * whichever is smaller. This ensures there are adequate - * slots to support multiple clients per thread. - * Give the client one slot even if that would require - * over-allocation--it is better than failure. + * The RPC and NFS session headers are never saved in + * the slot reply cache buffer. */ - scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads); - - avail = clamp_t(unsigned long, avail, slotsize, - total_avail/scale_factor); - num = min_t(int, num, avail / slotsize); - num = max_t(int, num, 1); - nfsd_drc_mem_used += num * slotsize; - spin_unlock(&nfsd_drc_lock); + size = fattrs->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ ? + 0 : fattrs->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; - return num; -} - -static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca) -{ - int slotsize = slot_bytes(ca); - - spin_lock(&nfsd_drc_lock); - nfsd_drc_mem_used -= slotsize * ca->maxreqs; - spin_unlock(&nfsd_drc_lock); + slot = kzalloc(struct_size(slot, sl_data, size), gfp); + if (!slot) + return NULL; + slot->sl_index = index; + return slot; } static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, struct nfsd4_channel_attrs *battrs) { int numslots = fattrs->maxreqs; - int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; + struct nfsd4_slot *slot; int i; - BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) - > PAGE_SIZE); - - new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); + new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; - /* allocate each struct nfsd4_slot and data cache in one piece */ - for (i = 0; i < numslots; i++) { - new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL); - if (!new->se_slots[i]) - goto out_free; - } + xa_init(&new->se_slots); - memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); - memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs)); + slot = nfsd4_alloc_slot(fattrs, 0, GFP_KERNEL); + if (!slot || xa_is_err(xa_store(&new->se_slots, 0, slot, GFP_KERNEL))) + goto out_free; + for (i = 1; i < numslots; i++) { + const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + slot = nfsd4_alloc_slot(fattrs, i, gfp); + if (!slot) + break; + if (xa_is_err(xa_store(&new->se_slots, i, slot, gfp))) { + kfree(slot); + break; + } + } + fattrs->maxreqs = i; + memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); + new->se_target_maxslots = i; + atomic_add(i - 1, &nfsd_total_target_slots); + new->se_cb_slot_avail = ~0U; + new->se_cb_highest_slot = min(battrs->maxreqs - 1, + NFSD_BC_SLOT_TABLE_SIZE - 1); + spin_lock_init(&new->se_lock); return new; out_free: - while (i--) - kfree(new->se_slots[i]); + kfree(slot); + xa_destroy(&new->se_slots); kfree(new); return NULL; } @@ -1944,17 +2182,47 @@ static void nfsd4_del_conns(struct nfsd4_session *s) static void __free_session(struct nfsd4_session *ses) { - free_session_slots(ses); + free_session_slots(ses, 0); + xa_destroy(&ses->se_slots); kfree(ses); } static void free_session(struct nfsd4_session *ses) { nfsd4_del_conns(ses); - nfsd4_put_drc_mem(&ses->se_fchannel); __free_session(ses); } +static unsigned long +nfsd_slot_count(struct shrinker *s, struct shrink_control *sc) +{ + unsigned long cnt = atomic_read(&nfsd_total_target_slots); + + return cnt ? cnt : SHRINK_EMPTY; +} + +static unsigned long +nfsd_slot_scan(struct shrinker *s, struct shrink_control *sc) +{ + struct nfsd4_session *ses; + unsigned long scanned = 0; + unsigned long freed = 0; + + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &nfsd_session_list, se_all_sessions) { + freed += reduce_session_slots(ses, 1); + scanned += 1; + if (scanned >= sc->nr_to_scan) { + /* Move starting point for next scan */ + list_move(&nfsd_session_list, &ses->se_all_sessions); + break; + } + } + spin_unlock(&nfsd_session_list_lock); + sc->nr_scanned = scanned; + return freed; +} + static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) { int idx; @@ -1965,17 +2233,24 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru INIT_LIST_HEAD(&new->se_conns); - new->se_cb_seq_nr = 1; - new->se_flags = cses->flags; + atomic_set(&new->se_ref, 0); + new->se_dead = false; new->se_cb_prog = cses->callback_prog; new->se_cb_sec = cses->cb_sec; - atomic_set(&new->se_ref, 0); + + for (idx = 0; idx < NFSD_BC_SLOT_TABLE_SIZE; ++idx) + new->se_cb_seq_nr[idx] = 1; + idx = hash_sessionid(&new->se_sessionid); list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]); spin_lock(&clp->cl_lock); list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_add_tail(&new->se_all_sessions, &nfsd_session_list); + spin_unlock(&nfsd_session_list_lock); + { struct sockaddr *sa = svc_addr(rqstp); /* @@ -2045,6 +2320,9 @@ unhash_session(struct nfsd4_session *ses) spin_lock(&ses->se_client->cl_lock); list_del(&ses->se_perclnt); spin_unlock(&ses->se_client->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_del(&ses->se_all_sessions); + spin_unlock(&nfsd_session_list_lock); } /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */ @@ -2062,21 +2340,16 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) return 1; } -/* - * XXX Should we use a slab cache ? - * This type of memory management is somewhat inefficient, but we use it - * anyway since SETCLIENTID is not a common operation. - */ static struct nfs4_client *alloc_client(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client *clp; int i; - if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) { + if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients && + atomic_read(&nn->nfsd_courtesy_clients) > 0) mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); - return NULL; - } + clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; @@ -2088,6 +2361,10 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name, GFP_KERNEL); if (!clp->cl_ownerstr_hashtbl) goto err_no_hashtbl; + clp->cl_callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0); + if (!clp->cl_callback_wq) + goto err_no_callback_wq; + for (i = 0; i < OWNER_HASH_SIZE; i++) INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]); INIT_LIST_HEAD(&clp->cl_sessions); @@ -2110,6 +2387,8 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name, spin_lock_init(&clp->cl_lock); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; +err_no_callback_wq: + kfree(clp->cl_ownerstr_hashtbl); err_no_hashtbl: kfree(clp->cl_name.data); err_no_name: @@ -2123,6 +2402,7 @@ static void __free_client(struct kref *k) struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs); free_svc_cred(&clp->cl_cred); + destroy_workqueue(clp->cl_callback_wq); kfree(clp->cl_ownerstr_hashtbl); kfree(clp->cl_name.data); kfree(clp->cl_nii_domain.data); @@ -2178,8 +2458,12 @@ unhash_client_locked(struct nfs4_client *clp) } list_del_init(&clp->cl_lru); spin_lock(&clp->cl_lock); - list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) { list_del_init(&ses->se_hash); + list_del_init(&ses->se_all_sessions); + } + spin_unlock(&nfsd_session_list_lock); spin_unlock(&clp->cl_lock); } @@ -2195,7 +2479,11 @@ unhash_client(struct nfs4_client *clp) static __be32 mark_client_expired_locked(struct nfs4_client *clp) { - if (atomic_read(&clp->cl_rpc_users)) + int users = atomic_read(&clp->cl_rpc_users); + + trace_nfsd_mark_client_expired(clp, users); + + if (users) return nfserr_jukebox; unhash_client_locked(clp); return nfs_ok; @@ -2208,13 +2496,12 @@ __destroy_client(struct nfs4_client *clp) int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; - struct list_head reaplist; + LIST_HEAD(reaplist); - INIT_LIST_HEAD(&reaplist); spin_lock(&state_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); - WARN_ON(!unhash_delegation_locked(dp)); + unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -2446,14 +2733,16 @@ find_stateid_locked(struct nfs4_client *cl, stateid_t *t) } static struct nfs4_stid * -find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask) +find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, + unsigned short typemask, unsigned short ok_states) { struct nfs4_stid *s; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, t); if (s != NULL) { - if (typemask & s->sc_type) + if ((s->sc_status & ~ok_states) == 0 && + (typemask & s->sc_type)) refcount_inc(&s->sc_count); else s = NULL; @@ -2473,9 +2762,9 @@ static struct nfs4_client *get_nfsdfs_clp(struct inode *inode) static void seq_quote_mem(struct seq_file *m, char *data, int len) { - seq_printf(m, "\""); + seq_puts(m, "\""); seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\"); - seq_printf(m, "\""); + seq_puts(m, "\""); } static const char *cb_state2str(int state) @@ -2496,6 +2785,7 @@ static const char *cb_state2str(int state) static int client_info_show(struct seq_file *m, void *v) { struct inode *inode = file_inode(m->file); + struct nfsd4_session *ses; struct nfs4_client *clp; u64 clid; @@ -2516,20 +2806,32 @@ static int client_info_show(struct seq_file *m, void *v) seq_puts(m, "status: unconfirmed\n"); seq_printf(m, "seconds from last renew: %lld\n", ktime_get_boottime_seconds() - clp->cl_time); - seq_printf(m, "name: "); + seq_puts(m, "name: "); seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len); seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); if (clp->cl_nii_domain.data) { - seq_printf(m, "Implementation domain: "); + seq_puts(m, "Implementation domain: "); seq_quote_mem(m, clp->cl_nii_domain.data, clp->cl_nii_domain.len); - seq_printf(m, "\nImplementation name: "); + seq_puts(m, "\nImplementation name: "); seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len); seq_printf(m, "\nImplementation time: [%lld, %ld]\n", clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec); } seq_printf(m, "callback state: %s\n", cb_state2str(clp->cl_cb_state)); - seq_printf(m, "callback address: %pISpc\n", &clp->cl_cb_conn.cb_addr); + seq_printf(m, "callback address: \"%pISpc\"\n", &clp->cl_cb_conn.cb_addr); + seq_printf(m, "admin-revoked states: %d\n", + atomic_read(&clp->cl_admin_revoked)); + spin_lock(&clp->cl_lock); + seq_printf(m, "session slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_fchannel.maxreqs); + seq_printf(m, "\nsession target slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_target_maxslots); + spin_unlock(&clp->cl_lock); + seq_puts(m, "\n"); + drop_client(clp); return 0; @@ -2588,7 +2890,7 @@ static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo) { - seq_printf(s, "owner: "); + seq_puts(s, "owner: "); seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len); } @@ -2606,20 +2908,13 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) struct nfs4_stateowner *oo; unsigned int access, deny; - if (st->sc_type != NFS4_OPEN_STID && st->sc_type != NFS4_LOCK_STID) - return 0; /* XXX: or SEQ_SKIP? */ ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; - spin_lock(&nf->fi_lock); - file = find_any_file_locked(nf); - if (!file) - goto out; - - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: open, "); + seq_puts(s, ": { type: open, "); access = bmap_to_share_mode(ols->st_access_bmap); deny = bmap_to_share_mode(ols->st_deny_bmap); @@ -2631,14 +2926,22 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) deny & NFS4_SHARE_ACCESS_READ ? "r" : "-", deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); - nfs4_show_superblock(s, file); - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, ", "); + if (nf) { + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); + if (file) { + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + seq_puts(s, ", "); + } + spin_unlock(&nf->fi_lock); + } else + seq_puts(s, "closed, "); nfs4_show_owner(s, oo); - seq_printf(s, " }\n"); -out: - spin_unlock(&nf->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); return 0; } @@ -2652,34 +2955,50 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; - spin_lock(&nf->fi_lock); - file = find_any_file_locked(nf); - if (!file) - goto out; - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: lock, "); + seq_puts(s, ": { type: lock, "); - /* - * Note: a lock stateid isn't really the same thing as a lock, - * it's the locking state held by one owner on a file, and there - * may be multiple (or no) lock ranges associated with it. - * (Same for the matter is true of open stateids.) - */ + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); + if (file) { + /* + * Note: a lock stateid isn't really the same thing as a lock, + * it's the locking state held by one owner on a file, and there + * may be multiple (or no) lock ranges associated with it. + * (Same for the matter is true of open stateids.) + */ - nfs4_show_superblock(s, file); - /* XXX: open stateid? */ - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, ", "); + nfs4_show_superblock(s, file); + /* XXX: open stateid? */ + seq_puts(s, ", "); + nfs4_show_fname(s, file); + seq_puts(s, ", "); + } nfs4_show_owner(s, oo); - seq_printf(s, " }\n"); -out: + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); spin_unlock(&nf->fi_lock); return 0; } +static char *nfs4_show_deleg_type(u32 dl_type) +{ + switch (dl_type) { + case OPEN_DELEGATE_READ: + return "r"; + case OPEN_DELEGATE_WRITE: + return "w"; + case OPEN_DELEGATE_READ_ATTRS_DELEG: + return "ra"; + case OPEN_DELEGATE_WRITE_ATTRS_DELEG: + return "wa"; + } + return "?"; +} + static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_delegation *ds; @@ -2688,27 +3007,27 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) ds = delegstateid(st); nf = st->sc_file; - spin_lock(&nf->fi_lock); - file = nf->fi_deleg_file; - if (!file) - goto out; - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: deleg, "); + seq_puts(s, ": { type: deleg, "); - /* Kinda dead code as long as we only support read delegs: */ - seq_printf(s, "access: %s, ", - ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w"); + seq_printf(s, "access: %s", nfs4_show_deleg_type(ds->dl_type)); /* XXX: lease time, whether it's being recalled. */ - nfs4_show_superblock(s, file); - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, " }\n"); -out: + spin_lock(&nf->fi_lock); + file = nf->fi_deleg_file; + if (file) { + seq_puts(s, ", "); + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + } spin_unlock(&nf->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); return 0; } @@ -2718,18 +3037,25 @@ static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st) struct nfsd_file *file; ls = container_of(st, struct nfs4_layout_stateid, ls_stid); - file = ls->ls_file; - seq_printf(s, "- "); + seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); - seq_printf(s, ": { type: layout, "); + seq_puts(s, ": { type: layout"); /* XXX: What else would be useful? */ - nfs4_show_superblock(s, file); - seq_printf(s, ", "); - nfs4_show_fname(s, file); - seq_printf(s, " }\n"); + spin_lock(&ls->ls_stid.sc_file->fi_lock); + file = ls->ls_file; + if (file) { + seq_puts(s, ", "); + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + } + spin_unlock(&ls->ls_stid.sc_file->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); return 0; } @@ -2739,13 +3065,13 @@ static int states_show(struct seq_file *s, void *v) struct nfs4_stid *st = v; switch (st->sc_type) { - case NFS4_OPEN_STID: + case SC_TYPE_OPEN: return nfs4_show_open(s, st); - case NFS4_LOCK_STID: + case SC_TYPE_LOCK: return nfs4_show_lock(s, st); - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: return nfs4_show_deleg(s, st); - case NFS4_LAYOUT_STID: + case SC_TYPE_LAYOUT: return nfs4_show_layout(s, st); default: return 0; /* XXX: or SEQ_SKIP? */ @@ -2785,7 +3111,7 @@ static int client_opens_release(struct inode *inode, struct file *file) /* XXX: alternatively, we could get/drop in seq start/stop */ drop_client(clp); - return 0; + return seq_release(inode, file); } static const struct file_operations client_states_fops = { @@ -2874,19 +3200,70 @@ static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - spin_lock(&nn->client_lock); - clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); - put_client_renew_locked(clp); - spin_unlock(&nn->client_lock); + drop_client(clp); +} + +static int +nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + trace_nfsd_cb_getattr_done(&dp->dl_stid.sc_stateid, task); + ncf->ncf_cb_status = task->tk_status; + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_getattr_release(struct nfsd4_callback *cb) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + nfs4_put_stid(&dp->dl_stid); } static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { .done = nfsd4_cb_recall_any_done, .release = nfsd4_cb_recall_any_release, + .opcode = OP_CB_RECALL_ANY, }; +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = { + .done = nfsd4_cb_getattr_done, + .release = nfsd4_cb_getattr_release, + .opcode = OP_CB_GETATTR, +}; + +static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf) +{ + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &ncf->ncf_getattr.cb_flags)) + return; + + /* set to proper status when nfsd4_cb_getattr_done runs */ + ncf->ncf_cb_status = NFS4ERR_IO; + + /* ensure that wake_bit is done when RUNNING is cleared */ + set_bit(NFSD4_CALLBACK_WAKE, &ncf->ncf_getattr.cb_flags); + + refcount_inc(&dp->dl_stid.sc_count); + nfsd4_run_cb(&ncf->ncf_getattr); +} + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2910,7 +3287,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name, kref_init(&clp->cl_nfsdfs.cl_ref); nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL); clp->cl_time = ktime_get_boottime_seconds(); - clear_bit(0, &clp->cl_cb_slot_busy); copy_verf(clp, verf); memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); clp->cl_cb_session = NULL; @@ -3111,7 +3487,20 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; - dprintk("--> %s slot %p\n", __func__, slot); + /* + * RFC 5661 Section 2.10.6.1.2: + * + * Any time SEQUENCE ... returns an error ... [t]he replier MUST NOT + * modify the reply cache entry for the slot whenever an error is + * returned from SEQUENCE ... + * + * Because nfsd4_store_cache_entry is called only by + * nfsd4_sequence_done(), nfsd4_store_cache_entry() is called only + * when a SEQUENCE operation was part of the COMPOUND. + * nfs41_check_op_ordering() ensures SEQUENCE is the first op. + */ + if (resp->opcnt == 1 && resp->cstate.status != nfs_ok) + return; slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; @@ -3119,7 +3508,7 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) free_svc_cred(&slot->sl_cred); copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred); - if (!nfsd4_cache_this(resp)) { + if (!(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS)) { slot->sl_flags &= ~NFSD4_SLOT_CACHED; return; } @@ -3134,41 +3523,6 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) } /* - * 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; - - /* Encode the replayed sequence operation */ - op = &args->ops[resp->opcnt - 1]; - nfsd4_encode_operation(resp, op); - - if (slot->sl_flags & NFSD4_SLOT_CACHED) - return op->status; - if (args->opcnt == 1) { - /* - * The original operation wasn't a solo sequence--we - * always cache those--so this retry must not match the - * original: - */ - op->status = nfserr_seq_false_retry; - } else { - 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. */ @@ -3176,17 +3530,30 @@ static __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq) { + struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; struct nfsd4_slot *slot = resp->cstate.slot; struct xdr_stream *xdr = resp->xdr; __be32 *p; - __be32 status; dprintk("--> %s slot %p\n", __func__, slot); - status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp); - if (status) - return status; + /* Always encode the SEQUENCE response. */ + nfsd4_encode_operation(resp, &args->ops[0]); + if (args->opcnt == 1) + /* A solo SEQUENCE - nothing was cached */ + return args->ops[0].status; + + if (!(slot->sl_flags & NFSD4_SLOT_CACHED)) { + /* We weren't asked to cache this. */ + struct nfsd4_op *op; + op = &args->ops[resp->opcnt++]; + op->status = nfserr_retry_uncached_rep; + nfsd4_encode_operation(resp, op); + return op->status; + } + + /* return reply from cache */ p = xdr_reserve_space(xdr, slot->sl_datalen); if (!p) { WARN_ON_ONCE(1); @@ -3237,7 +3604,7 @@ static bool client_has_state(struct nfs4_client *clp) #endif || !list_empty(&clp->cl_delegations) || !list_empty(&clp->cl_sessions) - || !list_empty(&clp->async_copies); + || nfsd4_has_active_async_copies(clp); } static __be32 copy_impl_id(struct nfs4_client *clp, @@ -3275,6 +3642,12 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __func__, rqstp, exid, exid->clname.len, exid->clname.data, addr_str, exid->flags, exid->spa_how); + exid->server_impl_name = kasprintf(GFP_KERNEL, "%s %s %s %s", + utsname()->sysname, utsname()->release, + utsname()->version, utsname()->machine); + if (!exid->server_impl_name) + return nfserr_jukebox; + if (exid->flags & ~EXCHGID4_FLAG_MASK_A) return nfserr_inval; @@ -3400,6 +3773,9 @@ out_new: new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0]; new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1]; + /* Contrived initial CREATE_SESSION response */ + new->cl_cs_slot.sl_status = nfserr_seq_misordered; + add_to_unconfirmed(new); swap(new, conf); out_copy: @@ -3409,6 +3785,23 @@ out_copy: exid->seqid = conf->cl_cs_slot.sl_seqid + 1; nfsd4_set_ex_flags(conf, exid); + exid->nii_domain.len = sizeof("kernel.org") - 1; + exid->nii_domain.data = "kernel.org"; + + /* + * Note that RFC 8881 places no length limit on + * nii_name, but this implementation permits no + * more than NFS4_OPAQUE_LIMIT bytes. + */ + exid->nii_name.len = strlen(exid->server_impl_name); + if (exid->nii_name.len > NFS4_OPAQUE_LIMIT) + exid->nii_name.len = NFS4_OPAQUE_LIMIT; + exid->nii_name.data = exid->server_impl_name; + + /* just send zeros - the date is in nii_name */ + exid->nii_time.tv_sec = 0; + exid->nii_time.tv_nsec = 0; + dprintk("nfsd4_exchange_id seqid %d flags %x\n", conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags); status = nfs_ok; @@ -3425,14 +3818,18 @@ out_nolock: return status; } -static __be32 -check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) +void +nfsd4_exchange_id_release(union nfsd4_op_u *u) { - dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid, - slot_seqid); + struct nfsd4_exchange_id *exid = &u->exchange_id; + kfree(exid->server_impl_name); +} + +static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, u8 flags) +{ /* The slot is in use, and no response has been sent. */ - if (slot_inuse) { + if (flags & NFSD4_SLOT_INUSE) { if (seqid == slot_seqid) return nfserr_jukebox; else @@ -3441,6 +3838,8 @@ check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) /* Note unsigned 32-bit arithmetic handles wraparound: */ if (likely(seqid == slot_seqid + 1)) return nfs_ok; + if ((flags & NFSD4_SLOT_REUSED) && seqid == 1) + return nfs_ok; if (seqid == slot_seqid) return nfserr_replay_cache; return nfserr_seq_misordered; @@ -3499,17 +3898,6 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); - /* - * Note decreasing slot size below client's request may make it - * difficult for client to function correctly, whereas - * decreasing the number of slots will (just?) affect - * performance. When short on memory we therefore prefer to - * decrease number of slots instead of their size. Clients that - * request larger slots than they need will get poor results: - * Note that we always allow at least one slot, because our - * accounting is soft and provides no guarantees either way. - */ - ca->maxreqs = nfsd4_get_drc_mem(ca, nn); return nfs_ok; } @@ -3570,10 +3958,10 @@ nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; + struct nfsd4_clid_slot *cs_slot; struct nfs4_client *old = NULL; struct nfsd4_session *new; struct nfsd4_conn *conn; - struct nfsd4_clid_slot *cs_slot = NULL; __be32 status = 0; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -3587,76 +3975,89 @@ nfsd4_create_session(struct svc_rqst *rqstp, return status; status = check_backchannel_attrs(&cr_ses->back_channel); if (status) - goto out_release_drc_mem; + goto out_err; status = nfserr_jukebox; new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel); if (!new) - goto out_release_drc_mem; + goto out_err; conn = alloc_conn_from_crses(rqstp, cr_ses); if (!conn) goto out_free_session; spin_lock(&nn->client_lock); + + /* RFC 8881 Section 18.36.4 Phase 1: Client record look-up. */ unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn); conf = find_confirmed_client(&cr_ses->clientid, true, nn); - WARN_ON_ONCE(conf && unconf); + if (!conf && !unconf) { + status = nfserr_stale_clientid; + goto out_free_conn; + } + + /* RFC 8881 Section 18.36.4 Phase 2: Sequence ID processing. */ + if (conf) { + cs_slot = &conf->cl_cs_slot; + trace_nfsd_slot_seqid_conf(conf, cr_ses); + } else { + cs_slot = &unconf->cl_cs_slot; + trace_nfsd_slot_seqid_unconf(unconf, cr_ses); + } + status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); + switch (status) { + case nfs_ok: + cs_slot->sl_seqid++; + cr_ses->seqid = cs_slot->sl_seqid; + break; + case nfserr_replay_cache: + status = nfsd4_replay_create_session(cr_ses, cs_slot); + fallthrough; + case nfserr_jukebox: + /* The server MUST NOT cache NFS4ERR_DELAY */ + goto out_free_conn; + default: + goto out_cache_error; + } + /* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */ if (conf) { status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(conf, rqstp)) - goto out_free_conn; - cs_slot = &conf->cl_cs_slot; - status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); - if (status) { - if (status == nfserr_replay_cache) - status = nfsd4_replay_create_session(cr_ses, cs_slot); - goto out_free_conn; - } - } else if (unconf) { + goto out_cache_error; + } else { status = nfserr_clid_inuse; if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) { trace_nfsd_clid_cred_mismatch(unconf, rqstp); - goto out_free_conn; + goto out_cache_error; } status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(unconf, rqstp)) - goto out_free_conn; - 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_free_conn; - } + goto out_cache_error; old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = mark_client_expired_locked(old); - if (status) { - old = NULL; - goto out_free_conn; - } + if (status) + goto out_expired_error; trace_nfsd_clid_replaced(&old->cl_clientid); } move_to_confirmed(unconf); conf = unconf; - } else { - status = nfserr_stale_clientid; - goto out_free_conn; } + + /* RFC 8881 Section 18.36.4 Phase 4: Session creation. */ status = nfs_ok; /* Persistent sessions are not supported */ cr_ses->flags &= ~SESSION4_PERSIST; /* Upshifting from TCP to RDMA is not supported */ cr_ses->flags &= ~SESSION4_RDMA; + /* Report the correct number of backchannel slots */ + cr_ses->back_channel.maxreqs = new->se_cb_highest_slot + 1; init_session(rqstp, new, conf, cr_ses); nfsd4_get_session_locked(new); memcpy(cr_ses->sessionid.data, new->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); - cs_slot->sl_seqid++; - cr_ses->seqid = cs_slot->sl_seqid; /* cache solo and embedded create sessions under the client_lock */ nfsd4_cache_create_session(cr_ses, cs_slot, status); @@ -3669,15 +4070,25 @@ nfsd4_create_session(struct svc_rqst *rqstp, if (old) expire_client(old); return status; + +out_expired_error: + /* + * Revert the slot seq_nr change so the server will process + * the client's resend instead of returning a cached response. + */ + if (status == nfserr_jukebox) { + cs_slot->sl_seqid--; + cr_ses->seqid = cs_slot->sl_seqid; + goto out_free_conn; + } +out_cache_error: + nfsd4_cache_create_session(cr_ses, cs_slot, status); out_free_conn: spin_unlock(&nn->client_lock); free_conn(conn); - if (old) - expire_client(old); out_free_session: __free_session(new); -out_release_drc_mem: - nfsd4_put_drc_mem(&cr_ses->fore_channel); +out_err: return status; } @@ -3930,6 +4341,36 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, return true; } +/* + * Note that the response is constructed here both for the case + * of a new SEQUENCE request and for a replayed SEQUENCE request. + * We do not cache SEQUENCE responses as SEQUENCE is idempotent. + */ +static void nfsd4_construct_sequence_response(struct nfsd4_session *session, + struct nfsd4_sequence *seq) +{ + struct nfs4_client *clp = session->se_client; + + seq->maxslots_response = max(session->se_target_maxslots, + seq->maxslots); + seq->target_maxslots = session->se_target_maxslots; + + switch (clp->cl_cb_state) { + case NFSD4_CB_DOWN: + seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; + break; + case NFSD4_CB_FAULT: + seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; + break; + default: + seq->status_flags = 0; + } + if (!list_empty(&clp->cl_revoked)) + seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + if (atomic_read(&clp->cl_admin_revoked)) + seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -3975,16 +4416,14 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (seq->slotid >= session->se_fchannel.maxreqs) goto out_put_session; - slot = session->se_slots[seq->slotid]; + slot = xa_load(&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; + trace_nfsd_slot_seqid_sequence(clp, seq, slot); + + nfsd4_construct_sequence_response(session, seq); - status = check_slot_seqid(seq->seqid, slot->sl_seqid, - slot->sl_flags & NFSD4_SLOT_INUSE); + status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) @@ -4009,6 +4448,12 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out_put_session; + if (session->se_target_maxslots < session->se_fchannel.maxreqs && + slot->sl_generation == session->se_slot_gen && + seq->maxslots <= session->se_target_maxslots) + /* Client acknowledged our reduce maxreqs */ + free_session_slots(session, session->se_target_maxslots); + buflen = (seq->cachethis) ? session->se_fchannel.maxresp_cached : session->se_fchannel.maxresp_sz; @@ -4016,12 +4461,14 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfserr_rep_too_big; if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack)) goto out_put_session; - svc_reserve(rqstp, buflen); + svc_reserve_auth(rqstp, buflen); status = nfs_ok; - /* Success! bump slot seqid */ + /* Success! accept new slot seqid */ slot->sl_seqid = seq->seqid; + slot->sl_flags &= ~NFSD4_SLOT_REUSED; slot->sl_flags |= NFSD4_SLOT_INUSE; + slot->sl_generation = session->se_slot_gen; if (seq->cachethis) slot->sl_flags |= NFSD4_SLOT_CACHETHIS; else @@ -4031,19 +4478,49 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->session = session; cstate->clp = clp; -out: - switch (clp->cl_cb_state) { - case NFSD4_CB_DOWN: - seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; - break; - case NFSD4_CB_FAULT: - seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; - break; - default: - seq->status_flags = 0; + /* + * If the client ever uses the highest available slot, + * gently try to allocate another 20%. This allows + * fairly quick growth without grossly over-shooting what + * the client might use. + */ + if (seq->slotid == session->se_fchannel.maxreqs - 1 && + session->se_target_maxslots >= session->se_fchannel.maxreqs && + session->se_fchannel.maxreqs < NFSD_MAX_SLOTS_PER_SESSION) { + int s = session->se_fchannel.maxreqs; + int cnt = DIV_ROUND_UP(s, 5); + void *prev_slot; + + do { + /* + * GFP_NOWAIT both allows allocation under a + * spinlock, and only succeeds if there is + * plenty of memory. + */ + slot = nfsd4_alloc_slot(&session->se_fchannel, s, + GFP_NOWAIT); + prev_slot = xa_load(&session->se_slots, s); + if (xa_is_value(prev_slot) && slot) { + slot->sl_seqid = xa_to_value(prev_slot); + slot->sl_flags |= NFSD4_SLOT_REUSED; + } + if (slot && + !xa_is_err(xa_store(&session->se_slots, s, slot, + GFP_NOWAIT))) { + s += 1; + session->se_fchannel.maxreqs = s; + atomic_add(s - session->se_target_maxslots, + &nfsd_total_target_slots); + session->se_target_maxslots = s; + } else { + kfree(slot); + slot = NULL; + } + } while (slot && --cnt > 0); } - if (!list_empty(&clp->cl_revoked)) - seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + +out: + trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) free_conn(conn); @@ -4258,10 +4735,16 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } status = nfs_ok; if (conf) { - old = unconf; - unhash_client_locked(old); - nfsd4_change_callback(conf, &unconf->cl_cb_conn); - } else { + if (get_client_locked(conf) == nfs_ok) { + old = unconf; + unhash_client_locked(old); + nfsd4_change_callback(conf, &unconf->cl_cb_conn); + } else { + conf = NULL; + } + } + + if (!conf) { old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = nfserr_clid_inuse; @@ -4278,10 +4761,14 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } trace_nfsd_clid_replaced(&old->cl_clientid); } + status = get_client_locked(unconf); + if (status != nfs_ok) { + old = NULL; + goto out; + } move_to_confirmed(unconf); conf = unconf; } - get_client_locked(conf); spin_unlock(&nn->client_lock); if (conf == unconf) fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); @@ -4311,6 +4798,7 @@ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) INIT_LIST_HEAD(&fp->fi_clnt_odstate); fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle); fp->fi_deleg_file = NULL; + fp->fi_rdeleg_file = NULL; fp->fi_had_conflict = false; fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); @@ -4338,32 +4826,25 @@ nfsd4_free_slabs(void) int nfsd4_init_slabs(void) { - client_slab = kmem_cache_create("nfsd4_clients", - sizeof(struct nfs4_client), 0, 0, NULL); + client_slab = KMEM_CACHE(nfs4_client, 0); if (client_slab == NULL) goto out; - openowner_slab = kmem_cache_create("nfsd4_openowners", - sizeof(struct nfs4_openowner), 0, 0, NULL); + openowner_slab = KMEM_CACHE(nfs4_openowner, 0); if (openowner_slab == NULL) goto out_free_client_slab; - lockowner_slab = kmem_cache_create("nfsd4_lockowners", - sizeof(struct nfs4_lockowner), 0, 0, NULL); + lockowner_slab = KMEM_CACHE(nfs4_lockowner, 0); if (lockowner_slab == NULL) goto out_free_openowner_slab; - file_slab = kmem_cache_create("nfsd4_files", - sizeof(struct nfs4_file), 0, 0, NULL); + file_slab = KMEM_CACHE(nfs4_file, 0); if (file_slab == NULL) goto out_free_lockowner_slab; - stateid_slab = kmem_cache_create("nfsd4_stateids", - sizeof(struct nfs4_ol_stateid), 0, 0, NULL); + stateid_slab = KMEM_CACHE(nfs4_ol_stateid, 0); if (stateid_slab == NULL) goto out_free_file_slab; - deleg_slab = kmem_cache_create("nfsd4_delegations", - sizeof(struct nfs4_delegation), 0, 0, NULL); + deleg_slab = KMEM_CACHE(nfs4_delegation, 0); if (deleg_slab == NULL) goto out_free_stateid_slab; - odstate_slab = kmem_cache_create("nfsd4_odstate", - sizeof(struct nfs4_clnt_odstate), 0, 0, NULL); + odstate_slab = KMEM_CACHE(nfs4_clnt_odstate, 0); if (odstate_slab == NULL) goto out_free_deleg_slab; return 0; @@ -4387,9 +4868,8 @@ out: static unsigned long nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { - int count; - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_client_shrinker); + struct nfsd_net *nn = shrink->private_data; + long count; count = atomic_read(&nn->nfsd_courtesy_clients); if (!count) @@ -4429,21 +4909,32 @@ nfsd4_init_leases_net(struct nfsd_net *nn) atomic_set(&nn->nfsd_courtesy_clients, 0); } +enum rp_lock { + RP_UNLOCKED, + RP_LOCKED, + RP_UNHASHED, +}; + static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; - mutex_init(&rp->rp_mutex); + rp->rp_locked = RP_UNLOCKED; } -static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, - struct nfs4_stateowner *so) +static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, + struct nfs4_stateowner *so) { if (!nfsd4_has_session(cstate)) { - mutex_lock(&so->so_replay.rp_mutex); + wait_var_event(&so->so_replay.rp_locked, + cmpxchg(&so->so_replay.rp_locked, + RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); + if (so->so_replay.rp_locked == RP_UNHASHED) + return -EAGAIN; cstate->replay_owner = nfs4_get_stateowner(so); } + return 0; } void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) @@ -4452,7 +4943,7 @@ void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) if (so != NULL) { cstate->replay_owner = NULL; - mutex_unlock(&so->so_replay.rp_mutex); + store_release_wake_up(&so->so_replay.rp_locked, RP_UNLOCKED); nfs4_put_stateowner(so); } } @@ -4518,7 +5009,8 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) continue; if (local->st_stateowner != &oo->oo_owner) continue; - if (local->st_stid.sc_type == NFS4_OPEN_STID) { + if (local->st_stid.sc_type == SC_TYPE_OPEN && + !local->st_stid.sc_status) { ret = local; refcount_inc(&ret->st_stid.sc_count); break; @@ -4527,22 +5019,75 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) return ret; } -static __be32 -nfsd4_verify_open_stid(struct nfs4_stid *s) +static void nfsd4_drop_revoked_stid(struct nfs4_stid *s) + __releases(&s->sc_client->cl_lock) { - __be32 ret = nfs_ok; + struct nfs4_client *cl = s->sc_client; + LIST_HEAD(reaplist); + struct nfs4_ol_stateid *stp; + struct nfs4_delegation *dp; + bool unhashed; switch (s->sc_type) { - default: + case SC_TYPE_OPEN: + stp = openlockstateid(s); + if (unhash_open_stateid(stp, &reaplist)) + put_ol_stateid_locked(stp, &reaplist); + spin_unlock(&cl->cl_lock); + free_ol_stateid_reaplist(&reaplist); break; - case 0: - case NFS4_CLOSED_STID: - case NFS4_CLOSED_DELEG_STID: - ret = nfserr_bad_stateid; + case SC_TYPE_LOCK: + stp = openlockstateid(s); + unhashed = unhash_lock_stateid(stp); + spin_unlock(&cl->cl_lock); + if (unhashed) + nfs4_put_stid(s); break; - case NFS4_REVOKED_DELEG_STID: - ret = nfserr_deleg_revoked; + case SC_TYPE_DELEG: + dp = delegstateid(s); + list_del_init(&dp->dl_recall_lru); + spin_unlock(&cl->cl_lock); + nfs4_put_stid(s); + break; + default: + spin_unlock(&cl->cl_lock); } +} + +static void nfsd40_drop_revoked_stid(struct nfs4_client *cl, + stateid_t *stid) +{ + /* NFSv4.0 has no way for the client to tell the server + * that it can forget an admin-revoked stateid. + * So we keep it around until the first time that the + * client uses it, and drop it the first time + * nfserr_admin_revoked is returned. + * For v4.1 and later we wait until explicitly told + * to free the stateid. + */ + if (cl->cl_minorversion == 0) { + struct nfs4_stid *st; + + spin_lock(&cl->cl_lock); + st = find_stateid_locked(cl, stid); + if (st) + nfsd4_drop_revoked_stid(st); + else + spin_unlock(&cl->cl_lock); + } +} + +static __be32 +nfsd4_verify_open_stid(struct nfs4_stid *s) +{ + __be32 ret = nfs_ok; + + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + ret = nfserr_admin_revoked; + else if (s->sc_status & SC_STATUS_REVOKED) + ret = nfserr_deleg_revoked; + else if (s->sc_status & SC_STATUS_CLOSED) + ret = nfserr_bad_stateid; return ret; } @@ -4554,6 +5099,10 @@ nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp) mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); ret = nfsd4_verify_open_stid(&stp->st_stid); + if (ret == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(stp->st_stid.sc_client, + &stp->st_stid.sc_stateid); + if (ret != nfs_ok) mutex_unlock(&stp->st_mutex); return ret; @@ -4575,34 +5124,46 @@ nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) } static struct nfs4_openowner * -alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, - struct nfsd4_compound_state *cstate) +find_or_alloc_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, + struct nfsd4_compound_state *cstate) { struct nfs4_client *clp = cstate->clp; - struct nfs4_openowner *oo, *ret; + struct nfs4_openowner *oo, *new = NULL; - oo = alloc_stateowner(openowner_slab, &open->op_owner, clp); - if (!oo) - return NULL; - oo->oo_owner.so_ops = &openowner_ops; - oo->oo_owner.so_is_open_owner = 1; - oo->oo_owner.so_seqid = open->op_seqid; - oo->oo_flags = 0; - if (nfsd4_has_session(cstate)) - oo->oo_flags |= NFS4_OO_CONFIRMED; - oo->oo_time = 0; - oo->oo_last_closed_stid = NULL; - INIT_LIST_HEAD(&oo->oo_close_lru); +retry: spin_lock(&clp->cl_lock); - ret = find_openstateowner_str_locked(strhashval, open, clp); - if (ret == NULL) { - hash_openowner(oo, clp, strhashval); - ret = oo; - } else - nfs4_free_stateowner(&oo->oo_owner); - + oo = find_openstateowner_str(strhashval, open, clp); + if (!oo && new) { + hash_openowner(new, clp, strhashval); + spin_unlock(&clp->cl_lock); + return new; + } spin_unlock(&clp->cl_lock); - return ret; + + if (oo && !(oo->oo_flags & NFS4_OO_CONFIRMED)) { + /* Replace unconfirmed owners without checking for replay. */ + release_openowner(oo); + oo = NULL; + } + if (oo) { + if (new) + nfs4_free_stateowner(&new->oo_owner); + return oo; + } + + new = alloc_stateowner(openowner_slab, &open->op_owner, clp); + if (!new) + return NULL; + new->oo_owner.so_ops = &openowner_ops; + new->oo_owner.so_is_open_owner = 1; + new->oo_owner.so_seqid = open->op_seqid; + new->oo_flags = 0; + if (nfsd4_has_session(cstate)) + new->oo_flags |= NFS4_OO_CONFIRMED; + new->oo_time = 0; + new->oo_last_closed_stid = NULL; + INIT_LIST_HEAD(&new->oo_close_lru); + goto retry; } static struct nfs4_ol_stateid * @@ -4622,13 +5183,19 @@ retry: spin_lock(&oo->oo_owner.so_client->cl_lock); spin_lock(&fp->fi_lock); + if (nfs4_openowner_unhashed(oo)) { + mutex_unlock(&stp->st_mutex); + stp = NULL; + goto out_unlock; + } + retstp = nfsd4_find_existing_open(fp, open); if (retstp) goto out_unlock; open->op_stp = NULL; refcount_inc(&stp->st_stid.sc_count); - stp->st_stid.sc_type = NFS4_OPEN_STID; + stp->st_stid.sc_type = SC_TYPE_OPEN; INIT_LIST_HEAD(&stp->st_locks); stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner); get_nfs4_file(fp); @@ -4678,7 +5245,10 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) * Wait for the refcount to drop to 2. Since it has been unhashed, * there should be no danger of the refcount going back up again at * this point. + * Some threads with a reference might be waiting for rp_locked, + * so tell them to stop waiting. */ + store_release_wake_up(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2); release_all_access(s); @@ -4855,9 +5425,9 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task); - if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID || - dp->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) - return 1; + if (dp->dl_stid.sc_status) + /* CLOSED or REVOKED */ + return 1; switch (task->tk_status) { case 0: @@ -4892,10 +5462,16 @@ static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = { .prepare = nfsd4_cb_recall_prepare, .done = nfsd4_cb_recall_done, .release = nfsd4_cb_recall_release, + .opcode = OP_CB_RECALL, }; static void nfsd_break_one_deleg(struct nfs4_delegation *dp) { + bool queued; + + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags)) + return; + /* * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease @@ -4904,14 +5480,17 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); - WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall)); + queued = nfsd4_run_cb(&dp->dl_recall); + WARN_ON_ONCE(!queued); + if (!queued) + refcount_dec(&dp->dl_stid.sc_count); } /* Called from break_lease() with flc_lock held. */ static bool -nfsd_break_deleg_cb(struct file_lock *fl) +nfsd_break_deleg_cb(struct file_lease *fl) { - struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; + struct nfs4_delegation *dp = (struct nfs4_delegation *) fl->c.flc_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; struct nfs4_client *clp = dp->dl_stid.sc_client; struct nfsd_net *nn; @@ -4932,10 +5511,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); return false; } @@ -4947,27 +5524,24 @@ nfsd_break_deleg_cb(struct file_lock *fl) * %true: Lease conflict was resolved * %false: Lease conflict was not resolved. */ -static bool nfsd_breaker_owns_lease(struct file_lock *fl) +static bool nfsd_breaker_owns_lease(struct file_lease *fl) { - struct nfs4_delegation *dl = fl->fl_owner; + struct nfs4_delegation *dl = fl->c.flc_owner; struct svc_rqst *rqst; struct nfs4_client *clp; - if (!i_am_nfsd()) - return false; - rqst = kthread_data(current); - /* Note rq_prog == NFS_ACL_PROGRAM is also possible: */ - if (rqst->rq_prog != NFS_PROGRAM || rqst->rq_vers < 4) + rqst = nfsd_current_rqst(); + if (!nfsd_v4client(rqst)) return false; clp = *(rqst->rq_lease_breaker); return dl->dl_stid.sc_client == clp; } static int -nfsd_change_deleg_cb(struct file_lock *onlist, int arg, +nfsd_change_deleg_cb(struct file_lease *onlist, int arg, struct list_head *dispose) { - struct nfs4_delegation *dp = (struct nfs4_delegation *)onlist->fl_owner; + struct nfs4_delegation *dp = (struct nfs4_delegation *) onlist->c.flc_owner; struct nfs4_client *clp = dp->dl_stid.sc_client; if (arg & F_UNLCK) { @@ -4978,7 +5552,7 @@ nfsd_change_deleg_cb(struct file_lock *onlist, int arg, return -EAGAIN; } -static const struct lock_manager_operations nfsd_lease_mng_ops = { +static const struct lease_manager_operations nfsd_lease_mng_ops = { .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, @@ -5053,27 +5627,19 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, clp = cstate->clp; strhashval = ownerstr_hashval(&open->op_owner); - oo = find_openstateowner_str(strhashval, open, clp); +retry: + oo = find_or_alloc_open_stateowner(strhashval, open, cstate); open->op_openowner = oo; - if (!oo) { - goto new_owner; - } - if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { - /* Replace unconfirmed owners without checking for replay. */ - release_openowner(oo); - open->op_openowner = NULL; - goto new_owner; + if (!oo) + return nfserr_jukebox; + if (nfsd4_cstate_assign_replay(cstate, &oo->oo_owner) == -EAGAIN) { + nfs4_put_stateowner(&oo->oo_owner); + goto retry; } status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid); if (status) return status; - goto alloc_stateid; -new_owner: - oo = alloc_init_open_stateowner(strhashval, open, cstate); - if (oo == NULL) - return nfserr_jukebox; - open->op_openowner = oo; -alloc_stateid: + open->op_stp = nfs4_alloc_open_stateid(clp); if (!open->op_stp) return nfserr_jukebox; @@ -5091,7 +5657,7 @@ alloc_stateid: static inline __be32 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags) { - if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ)) + if (!(flags & RD_STATE) && deleg_is_read(dp->dl_type)) return nfserr_openmode; else return nfs_ok; @@ -5102,12 +5668,12 @@ static int share_access_to_flags(u32 share_access) return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE; } -static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, stateid_t *s) +static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, + stateid_t *s) { struct nfs4_stid *ret; - ret = find_stateid_by_type(cl, s, - NFS4_DELEG_STID|NFS4_REVOKED_DELEG_STID); + ret = find_stateid_by_type(cl, s, SC_TYPE_DELEG, SC_STATUS_REVOKED); if (!ret) return NULL; return delegstateid(ret); @@ -5130,10 +5696,15 @@ nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open, deleg = find_deleg_stateid(cl, &open->op_delegate_stateid); if (deleg == NULL) goto out; - if (deleg->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) { + if (deleg->dl_stid.sc_status & SC_STATUS_ADMIN_REVOKED) { + nfs4_put_stid(&deleg->dl_stid); + status = nfserr_admin_revoked; + goto out; + } + if (deleg->dl_stid.sc_status & SC_STATUS_REVOKED) { nfs4_put_stid(&deleg->dl_stid); - if (cl->cl_minorversion) - status = nfserr_deleg_revoked; + nfsd40_drop_revoked_stid(cl, &open->op_delegate_stateid); + status = nfserr_deleg_revoked; goto out; } flags = share_access_to_flags(open->op_share_access); @@ -5178,7 +5749,7 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; - return nfsd_setattr(rqstp, fh, &attrs, 0, (time64_t)0); + return nfsd_setattr(rqstp, fh, &attrs, NULL); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, @@ -5318,21 +5889,19 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } -static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, - int flag) +static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp) { - struct file_lock *fl; + struct file_lease *fl; - fl = locks_alloc_lock(); + fl = locks_alloc_lease(); if (!fl) return NULL; fl->fl_lmops = &nfsd_lease_mng_ops; - fl->fl_flags = FL_DELEG; - 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_pid = current->tgid; - fl->fl_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; + fl->c.flc_flags = FL_DELEG; + fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK; + fl->c.flc_owner = (fl_owner_t)dp; + fl->c.flc_pid = current->tgid; + fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; return fl; } @@ -5440,17 +6009,31 @@ nfsd4_verify_setuid_write(struct nfsd4_open *open, struct nfsd_file *nf) return 0; } +#ifdef CONFIG_NFSD_V4_DELEG_TIMESTAMPS +static bool nfsd4_want_deleg_timestamps(const struct nfsd4_open *open) +{ + return open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS; +} +#else /* CONFIG_NFSD_V4_DELEG_TIMESTAMPS */ +static bool nfsd4_want_deleg_timestamps(const struct nfsd4_open *open) +{ + return false; +} +#endif /* CONFIG NFSD_V4_DELEG_TIMESTAMPS */ + static struct nfs4_delegation * nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent) { - int status = 0; + bool deleg_ts = nfsd4_want_deleg_timestamps(open); struct nfs4_client *clp = stp->st_stid.sc_client; struct nfs4_file *fp = stp->st_stid.sc_file; struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; - struct nfsd_file *nf; - struct file_lock *fl; + struct nfsd_file *nf = NULL; + struct file_lease *fl; + int status = 0; + u32 dl_type; /* * The fi_had_conflict and nfs_get_existing_delegation checks @@ -5460,15 +6043,49 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); - nf = find_readable_file(fp); - if (!nf) { - /* - * We probably could attempt another open and get a read - * delegation, but for now, don't bother until the - * client actually sends us one. - */ + /* + * Try for a write delegation first. RFC8881 section 10.4 says: + * + * "An OPEN_DELEGATE_WRITE delegation allows the client to handle, + * on its own, all opens." + * + * Furthermore, section 9.1.2 says: + * + * "In the case of READ, the server may perform the corresponding + * check on the access mode, or it may choose to allow READ for + * OPEN4_SHARE_ACCESS_WRITE, to accommodate clients whose WRITE + * implementation may unavoidably do reads (e.g., due to buffer + * cache constraints)." + * + * We choose to offer a write delegation for OPEN with the + * OPEN4_SHARE_ACCESS_WRITE access mode to accommodate such clients. + */ + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { + nf = find_writeable_file(fp); + dl_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; + } + + /* + * If the file is being opened O_RDONLY or we couldn't get a O_RDWR + * file for some reason, then try for a read delegation instead. + */ + if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) { + nf = find_readable_file(fp); + dl_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; + } + + if (!nf) return ERR_PTR(-EAGAIN); + + /* + * File delegations and associated locks cannot be recovered if the + * export is from an NFS proxy server. + */ + if (exportfs_cannot_lock(nf->nf_file->f_path.mnt->mnt_sb->s_export_op)) { + nfsd_file_put(nf); + return ERR_PTR(-EOPNOTSUPP); } + spin_lock(&state_lock); spin_lock(&fp->fi_lock); if (nfs4_delegation_exists(clp, fp)) @@ -5491,17 +6108,18 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, return ERR_PTR(status); status = -ENOMEM; - dp = alloc_init_deleg(clp, fp, odstate); + dp = alloc_init_deleg(clp, fp, odstate, dl_type); if (!dp) goto out_delegees; - fl = nfs4_alloc_init_lease(dp, NFS4_OPEN_DELEGATE_READ); + fl = nfs4_alloc_init_lease(dp); if (!fl) goto out_clnt_odstate; - status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL); + status = kernel_setlease(fp->fi_deleg_file->nf_file, + fl->c.flc_type, &fl, NULL); if (fl) - locks_free_lock(fl); + locks_free_lease(fl); if (status) goto out_clnt_odstate; @@ -5517,19 +6135,22 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, /* * Now that the deleg is set, check again to ensure that nothing - * raced in and changed the mode while we weren't lookng. + * raced in and changed the mode while we weren't looking. */ status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file); if (status) goto out_unlock; + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); + spin_lock(&clp->cl_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); + spin_unlock(&clp->cl_lock); spin_unlock(&state_lock); if (status) @@ -5537,7 +6158,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, return dp; out_unlock: - vfs_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); + kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); out_clnt_odstate: put_clnt_odstate(dp->dl_clnt_odstate); nfs4_put_stid(&dp->dl_stid); @@ -5548,50 +6169,120 @@ out_delegees: static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; if (status == -EAGAIN) open->op_why_no_deleg = WND4_CONTENTION; else { open->op_why_no_deleg = WND4_RESOURCE; switch (open->op_deleg_want) { - case NFS4_SHARE_WANT_READ_DELEG: - case NFS4_SHARE_WANT_WRITE_DELEG: - case NFS4_SHARE_WANT_ANY_DELEG: + case OPEN4_SHARE_ACCESS_WANT_READ_DELEG: + case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG: + case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG: break; - case NFS4_SHARE_WANT_CANCEL: + case OPEN4_SHARE_ACCESS_WANT_CANCEL: open->op_why_no_deleg = WND4_CANCELLED; break; - case NFS4_SHARE_WANT_NO_DELEG: + case OPEN4_SHARE_ACCESS_WANT_NO_DELEG: WARN_ON_ONCE(1); } } } +static bool +nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh, + struct kstat *stat) +{ + struct nfsd_file *nf = find_writeable_file(dp->dl_stid.sc_file); + struct path path; + int rc; + + if (!nf) + return false; + + path.mnt = currentfh->fh_export->ex_path.mnt; + path.dentry = file_dentry(nf->nf_file); + + rc = vfs_getattr(&path, stat, + STATX_MODE | STATX_SIZE | STATX_ATIME | + STATX_MTIME | STATX_CTIME | STATX_CHANGE_COOKIE, + AT_STATX_SYNC_AS_STAT); + + nfsd_file_put(nf); + return rc == 0; +} + +/* + * Add NFS4_SHARE_ACCESS_READ to the write delegation granted on OPEN + * with NFS4_SHARE_ACCESS_WRITE by allocating separate nfsd_file and + * struct file to be used for read with delegation stateid. + * + */ +static bool +nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open, + struct svc_fh *fh, struct nfs4_ol_stateid *stp) +{ + struct nfs4_file *fp; + struct nfsd_file *nf = NULL; + + if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == + NFS4_SHARE_ACCESS_WRITE) { + if (nfsd_file_acquire_opened(rqstp, fh, NFSD_MAY_READ, NULL, &nf)) + return (false); + fp = stp->st_stid.sc_file; + spin_lock(&fp->fi_lock); + __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); + fp = stp->st_stid.sc_file; + fp->fi_fds[O_RDONLY] = nf; + fp->fi_rdeleg_file = nf; + spin_unlock(&fp->fi_lock); + } + return true; +} + /* - * Attempt to hand out a delegation. + * The Linux NFS server does not offer write delegations to NFSv4.0 + * clients in order to avoid conflicts between write delegations and + * GETATTRs requesting CHANGE or SIZE attributes. * - * Note we don't support write delegations, and won't until the vfs has - * proper support for them. + * With NFSv4.1 and later minorversions, the SEQUENCE operation that + * begins each COMPOUND contains a client ID. Delegation recall can + * be avoided when the server recognizes the client sending a + * GETATTR also holds write delegation it conflicts with. + * + * However, the NFSv4.0 protocol does not enable a server to + * determine that a GETATTR originated from the client holding the + * conflicting delegation versus coming from some other client. Per + * RFC 7530 Section 16.7.5, the server must recall or send a + * CB_GETATTR even when the GETATTR originates from the client that + * holds the conflicting delegation. + * + * An NFSv4.0 client can trigger a pathological situation if it + * always sends a DELEGRETURN preceded by a conflicting GETATTR in + * the same COMPOUND. COMPOUND execution will always stop at the + * GETATTR and the DELEGRETURN will never get executed. The server + * eventually revokes the delegation, which can result in loss of + * open or lock state. */ static void -nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, - struct svc_fh *currentfh) +nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open, + struct nfs4_ol_stateid *stp, struct svc_fh *currentfh, + struct svc_fh *fh) { - struct nfs4_delegation *dp; struct nfs4_openowner *oo = openowner(stp->st_stateowner); + bool deleg_ts = nfsd4_want_deleg_timestamps(open); struct nfs4_client *clp = stp->st_stid.sc_client; struct svc_fh *parent = NULL; - int cb_up; + struct nfs4_delegation *dp; + struct kstat stat; int status = 0; + int cb_up; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); - open->op_recall = 0; + open->op_recall = false; switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_PREVIOUS: if (!cb_up) - open->op_recall = 1; - if (open->op_delegate_type != NFS4_OPEN_DELEGATE_READ) - goto out_no_deleg; + open->op_recall = true; break; case NFS4_OPEN_CLAIM_NULL: parent = currentfh; @@ -5606,6 +6297,9 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, goto out_no_deleg; if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED)) goto out_no_deleg; + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE && + !clp->cl_minorversion) + goto out_no_deleg; break; default: goto out_no_deleg; @@ -5616,17 +6310,36 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); - trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); - open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { + struct file *f = dp->dl_stid.sc_file->fi_deleg_file->nf_file; + + if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) || + !nfs4_delegation_stat(dp, currentfh, &stat)) { + nfs4_put_stid(&dp->dl_stid); + destroy_delegation(dp); + goto out_no_deleg; + } + open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : + OPEN_DELEGATE_WRITE; + dp->dl_cb_fattr.ncf_cur_fsize = stat.size; + dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); + dp->dl_atime = stat.atime; + dp->dl_ctime = stat.ctime; + dp->dl_mtime = stat.mtime; + spin_lock(&f->f_lock); + f->f_mode |= FMODE_NOCMTIME; + spin_unlock(&f->f_lock); + trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); + } else { + open->op_delegate_type = deleg_ts && nfs4_delegation_stat(dp, currentfh, &stat) ? + OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; + dp->dl_atime = stat.atime; + trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); + } nfs4_put_stid(&dp->dl_stid); return; out_no_deleg: - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE; - if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && - open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) { - dprintk("NFSD: WARNING: refusing delegation reclaim\n"); - open->op_recall = 1; - } + open->op_delegate_type = OPEN_DELEGATE_NONE; /* 4.1 client asking for a delegation? */ if (open->op_deleg_want) @@ -5637,21 +6350,32 @@ out_no_deleg: static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, struct nfs4_delegation *dp) { - if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; - } else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + if (deleg_is_write(dp->dl_type)) { + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_READ_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; + } else if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + } } /* Otherwise the client must be confused wanting a delegation * it already has, therefore we don't return - * NFS4_OPEN_DELEGATE_NONE_EXT and reason. + * OPEN_DELEGATE_NONE_EXT and reason. */ } +/* Are we returning only a delegation stateid? */ +static bool open_xor_delegation(struct nfsd4_open *open) +{ + if (!(open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION)) + return false; + /* Did we actually get a delegation? */ + if (!deleg_is_read(open->op_delegate_type) && !deleg_is_write(open->op_delegate_type)) + return false; + return true; +} + /** * nfsd4_process_open2 - finish open processing * @rqstp: the RPC transaction being executed @@ -5687,6 +6411,20 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; + if (dp && nfsd4_is_deleg_cur(open) && + (dp->dl_stid.sc_file != fp)) { + /* + * RFC8881 section 8.2.4 mandates the server to return + * NFS4ERR_BAD_STATEID if the selected table entry does + * not match the current filehandle. However returning + * NFS4ERR_BAD_STATEID in the OPEN can cause the client + * to repeatedly retry the operation with the same + * stateid, since the stateid itself is valid. To avoid + * this situation NFSD returns NFS4ERR_INVAL instead. + */ + status = nfserr_inval; + goto out; + } stp = nfsd4_find_and_lock_existing_open(fp, open); } else { open->op_file = NULL; @@ -5697,6 +6435,11 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf if (!stp) { stp = init_open_stateid(fp, open); + if (!stp) { + status = nfserr_jukebox; + goto out; + } + if (!open->op_stp) new_stp = true; } @@ -5717,7 +6460,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf } else { status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true); if (status) { - stp->st_stid.sc_type = NFS4_CLOSED_STID; release_open_stateid(stp); mutex_unlock(&stp->st_mutex); goto out; @@ -5733,8 +6475,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf mutex_unlock(&stp->st_mutex); if (nfsd4_has_session(&resp->cstate)) { - if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_NO_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_WANTED; goto nodeleg; } @@ -5744,13 +6486,25 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. */ - nfs4_open_delegation(open, stp, &resp->cstate.current_fh); + nfs4_open_delegation(rqstp, open, stp, + &resp->cstate.current_fh, current_fh); + + /* + * If there is an existing open stateid, it must be updated and + * returned. Only respect WANT_OPEN_XOR_DELEGATION when a new + * open stateid would have to be created. + */ + if (new_stp && open_xor_delegation(open)) { + memcpy(&open->op_stateid, &zero_stateid, sizeof(open->op_stateid)); + open->op_rflags |= OPEN4_RESULT_NO_OPEN_STATEID; + release_open_stateid(stp); + } nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ - if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp && + if (open->op_delegate_type == OPEN_DELEGATE_NONE && dp && open->op_deleg_want) nfsd4_deleg_xgrade_none_ext(open, dp); @@ -5761,7 +6515,7 @@ out: /* * To finish the open response, we just need to set the rflags. */ - open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX; + open->op_rflags |= NFS4_OPEN_RESULT_LOCKTYPE_POSIX; if (nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK; else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED)) @@ -5778,12 +6532,8 @@ out: void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { - if (open->op_openowner) { - struct nfs4_stateowner *so = &open->op_openowner->oo_owner; - - nfsd4_cstate_assign_replay(cstate, so); - nfs4_put_stateowner(so); - } + if (open->op_openowner) + nfs4_put_stateowner(&open->op_openowner->oo_owner); if (open->op_file) kmem_cache_free(file_slab, open->op_file); if (open->op_stp) @@ -5893,7 +6643,6 @@ void nfsd4_ssc_init_umount_work(struct nfsd_net *nn) INIT_LIST_HEAD(&nn->nfsd_ssc_mount_list); init_waitqueue_head(&nn->nfsd_ssc_waitq); } -EXPORT_SYMBOL_GPL(nfsd4_ssc_init_umount_work); /* * This is called when nfsd is being shutdown, after all inter_ssc @@ -6071,6 +6820,43 @@ nfs4_process_client_reaplist(struct list_head *reaplist) } } +static void nfs40_clean_admin_revoked(struct nfsd_net *nn, + struct laundry_time *lt) +{ + struct nfs4_client *clp; + + spin_lock(&nn->client_lock); + if (nn->nfs40_last_revoke == 0 || + nn->nfs40_last_revoke > lt->cutoff) { + spin_unlock(&nn->client_lock); + return; + } + nn->nfs40_last_revoke = 0; + +retry: + list_for_each_entry(clp, &nn->client_lru, cl_lru) { + unsigned long id, tmp; + struct nfs4_stid *stid; + + if (atomic_read(&clp->cl_admin_revoked) == 0) + continue; + + spin_lock(&clp->cl_lock); + idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) + if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { + refcount_inc(&stid->sc_count); + spin_unlock(&nn->client_lock); + /* this function drops ->cl_lock */ + nfsd4_drop_revoked_stid(stid); + nfs4_put_stid(stid); + spin_lock(&nn->client_lock); + goto retry; + } + spin_unlock(&clp->cl_lock); + } + spin_unlock(&nn->client_lock); +} + static time64_t nfs4_laundromat(struct nfsd_net *nn) { @@ -6101,15 +6887,19 @@ nfs4_laundromat(struct nfsd_net *nn) _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); + nfsd4_async_copy_reaper(nn); nfs4_get_client_reaplist(nn, &reaplist, <); nfs4_process_client_reaplist(&reaplist); + nfs40_clean_admin_revoked(nn, <); + spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(<, dp->dl_time)) break; - WARN_ON(!unhash_delegation_locked(dp)); + refcount_inc(&dp->dl_stid.sc_count); + unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -6168,6 +6958,8 @@ nfs4_laundromat(struct nfsd_net *nn) /* service the server-to-server copy delayed unmount list */ nfsd4_ssc_expire_umount(nn); #endif + if (atomic_long_read(&num_delegations) >= max_delegations) + deleg_reaper(nn); out: return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); } @@ -6200,38 +6992,34 @@ deleg_reaper(struct nfsd_net *nn) { struct list_head *pos, *next; struct nfs4_client *clp; - struct list_head cblist; - INIT_LIST_HEAD(&cblist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); - if (clp->cl_state != NFSD4_ACTIVE || - list_empty(&clp->cl_delegations) || - atomic_read(&clp->cl_delegs_in_recall) || - test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || - (ktime_get_boottime_seconds() - - clp->cl_ra_time < 5)) { + + if (clp->cl_state != NFSD4_ACTIVE) + continue; + if (list_empty(&clp->cl_delegations)) + continue; + if (atomic_read(&clp->cl_delegs_in_recall)) + continue; + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &clp->cl_ra->ra_cb.cb_flags)) + continue; + if (ktime_get_boottime_seconds() - clp->cl_ra_time < 5) + continue; + if (clp->cl_cb_state != NFSD4_CB_UP) continue; - } - list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ - atomic_inc(&clp->cl_rpc_users); - set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + kref_get(&clp->cl_nfsdfs.cl_ref); clp->cl_ra_time = ktime_get_boottime_seconds(); - } - spin_unlock(&nn->client_lock); - - while (!list_empty(&cblist)) { - clp = list_first_entry(&cblist, struct nfs4_client, - cl_ra_cblist); - list_del_init(&clp->cl_ra_cblist); clp->cl_ra->ra_keep = 0; - clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG); + clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG) | + BIT(RCA4_TYPE_MASK_WDATA_DLG); trace_nfsd_cb_recall_any(clp->cl_ra); nfsd4_run_cb(&clp->cl_ra->ra_cb); } + spin_unlock(&nn->client_lock); } static void @@ -6322,6 +7110,9 @@ static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_sti if (ret == nfs_ok) ret = check_stateid_generation(in, &s->sc_stateid, has_session); spin_unlock(&s->sc_lock); + if (ret == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(s->sc_client, + &s->sc_stateid); return ret; } @@ -6348,32 +7139,33 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) status = nfsd4_stid_check_stateid_generation(stateid, s, 1); if (status) goto out_unlock; + status = nfsd4_verify_open_stid(s); + if (status) + goto out_unlock; + switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: status = nfs_ok; break; - case NFS4_REVOKED_DELEG_STID: - status = nfserr_deleg_revoked; - break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: status = nfsd4_check_openowner_confirmed(openlockstateid(s)); break; default: printk("unknown stateid type %x\n", s->sc_type); - fallthrough; - case NFS4_CLOSED_STID: - case NFS4_CLOSED_DELEG_STID: status = nfserr_bad_stateid; } out_unlock: spin_unlock(&cl->cl_lock); + if (status == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(cl, stateid); return status; } __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, - stateid_t *stateid, unsigned char typemask, + stateid_t *stateid, + unsigned short typemask, unsigned short statusmask, struct nfs4_stid **s, struct nfsd_net *nn) { __be32 status; @@ -6384,10 +7176,15 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, * only return revoked delegations if explicitly asked. * otherwise we report revoked or bad_stateid status. */ - if (typemask & NFS4_REVOKED_DELEG_STID) + if (statusmask & SC_STATUS_REVOKED) return_revoked = true; - else if (typemask & NFS4_DELEG_STID) - typemask |= NFS4_REVOKED_DELEG_STID; + if (typemask & SC_TYPE_DELEG) + /* Always allow REVOKED for DELEG so we can + * return the appropriate error. + */ + statusmask |= SC_STATUS_REVOKED; + + statusmask |= SC_STATUS_ADMIN_REVOKED | SC_STATUS_FREEABLE; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) @@ -6400,14 +7197,17 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, } if (status) return status; - stid = find_stateid_by_type(cstate->clp, stateid, typemask); + stid = find_stateid_by_type(cstate->clp, stateid, typemask, statusmask); if (!stid) return nfserr_bad_stateid; - if ((stid->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) { + if ((stid->sc_status & SC_STATUS_REVOKED) && !return_revoked) { nfs4_put_stid(stid); - if (cstate->minorversion) - return nfserr_deleg_revoked; - return nfserr_bad_stateid; + return nfserr_deleg_revoked; + } + if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { + nfsd40_drop_revoked_stid(cstate->clp, stateid); + nfs4_put_stid(stid); + return nfserr_admin_revoked; } *s = stid; return nfs_ok; @@ -6418,17 +7218,13 @@ nfs4_find_file(struct nfs4_stid *s, int flags) { struct nfsd_file *ret = NULL; - if (!s) + if (!s || s->sc_status) return NULL; switch (s->sc_type) { - case NFS4_DELEG_STID: - spin_lock(&s->sc_file->fi_lock); - ret = nfsd_file_get(s->sc_file->fi_deleg_file); - spin_unlock(&s->sc_file->fi_lock); - break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_DELEG: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: if (flags & RD_STATE) ret = find_readable_file(s->sc_file); else @@ -6459,7 +7255,8 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, nf = nfs4_find_file(s, flags); if (nf) { - status = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, + status = nfsd_permission(&rqstp->rq_cred, + fhp->fh_export, fhp->fh_dentry, acc | NFSD_MAY_OWNER_OVERRIDE); if (status) { nfsd_file_put(nf); @@ -6517,7 +7314,7 @@ unlock: spin_unlock(&nn->s2s_cp_lock); if (!state) return nfserr_bad_stateid; - if (!clp && state) + if (!clp) *cps = state; return 0; } @@ -6541,7 +7338,8 @@ static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st, goto out; *stid = find_stateid_by_type(found, &cps->cp_p_stateid, - NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID); + SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, + 0); if (*stid) status = nfs_ok; else @@ -6589,17 +7387,13 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, *nfp = NULL; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { - if (cstid) - status = nfserr_bad_stateid; - else - status = check_special_stateids(net, fhp, stateid, - flags); + status = check_special_stateids(net, fhp, stateid, flags); goto done; } status = nfsd4_lookup_stateid(cstate, stateid, - NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, - &s, nn); + SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, + 0, &s, nn); if (status == nfserr_bad_stateid) status = find_cpntf_state(nn, stateid, &s); if (status) @@ -6610,16 +7404,13 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, goto out; switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: status = nfs4_check_delegmode(delegstateid(s), flags); break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: status = nfs4_check_olstateid(openlockstateid(s), flags); break; - default: - status = nfserr_bad_stateid; - break; } if (status) goto out; @@ -6698,34 +7489,42 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); - if (!s) + if (!s || s->sc_status & SC_STATUS_CLOSED) goto out_unlock; + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) { + nfsd4_drop_revoked_stid(s); + ret = nfs_ok; + goto out; + } spin_lock(&s->sc_lock); switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: + if (s->sc_status & SC_STATUS_REVOKED) { + s->sc_status |= SC_STATUS_CLOSED; + spin_unlock(&s->sc_lock); + dp = delegstateid(s); + if (s->sc_status & SC_STATUS_FREEABLE) + list_del_init(&dp->dl_recall_lru); + s->sc_status |= SC_STATUS_FREED; + spin_unlock(&cl->cl_lock); + nfs4_put_stid(s); + ret = nfs_ok; + goto out; + } ret = nfserr_locks_held; break; - case NFS4_OPEN_STID: + case SC_TYPE_OPEN: ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) break; ret = nfserr_locks_held; break; - case NFS4_LOCK_STID: + case SC_TYPE_LOCK: spin_unlock(&s->sc_lock); refcount_inc(&s->sc_count); spin_unlock(&cl->cl_lock); ret = nfsd4_free_lock_stateid(stateid, s); goto out; - case NFS4_REVOKED_DELEG_STID: - spin_unlock(&s->sc_lock); - dp = delegstateid(s); - list_del_init(&dp->dl_recall_lru); - spin_unlock(&cl->cl_lock); - nfs4_put_stid(s); - ret = nfs_ok; - goto out; - /* Default falls through and returns nfserr_bad_stateid */ } spin_unlock(&s->sc_lock); out_unlock: @@ -6767,6 +7566,7 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ * @seqid: seqid (provided by client) * @stateid: stateid (provided by client) * @typemask: mask of allowable types for this operation + * @statusmask: mask of allowed states: 0 or STID_CLOSED * @stpp: return pointer for the stateid found * @nn: net namespace for request * @@ -6776,7 +7576,8 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ */ static __be32 nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, - stateid_t *stateid, char typemask, + stateid_t *stateid, + unsigned short typemask, unsigned short statusmask, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { @@ -6787,11 +7588,16 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, trace_nfsd_preprocess(seqid, stateid); *stpp = NULL; - status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn); +retry: + status = nfsd4_lookup_stateid(cstate, stateid, + typemask, statusmask, &s, nn); if (status) return status; stp = openlockstateid(s); - nfsd4_cstate_assign_replay(cstate, stp->st_stateowner); + if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) { + nfs4_put_stateowner(stp->st_stateowner); + goto retry; + } status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp); if (!status) @@ -6809,7 +7615,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs struct nfs4_ol_stateid *stp; status = nfs4_preprocess_seqid_op(cstate, seqid, stateid, - NFS4_OPEN_STID, &stp, nn); + SC_TYPE_OPEN, 0, &stp, nn); if (status) return status; oo = openowner(stp->st_stateowner); @@ -6840,8 +7646,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; status = nfs4_preprocess_seqid_op(cstate, - oc->oc_seqid, &oc->oc_req_stateid, - NFS4_OPEN_STID, &stp, nn); + oc->oc_seqid, &oc->oc_req_stateid, + SC_TYPE_OPEN, 0, &stp, nn); if (status) goto out; oo = openowner(stp->st_stateowner); @@ -6933,7 +7739,7 @@ out: return status; } -static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) +static bool nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) { struct nfs4_client *clp = s->st_stid.sc_client; bool unhashed; @@ -6950,11 +7756,11 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) list_for_each_entry(stp, &reaplist, st_locks) nfs4_free_cpntf_statelist(clp->net, &stp->st_stid); free_ol_stateid_reaplist(&reaplist); + return false; } else { spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); - if (unhashed) - move_to_close_lru(s, clp->net); + return unhashed; } } @@ -6970,19 +7776,22 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); + bool need_move_to_close_list; - dprintk("NFSD: nfsd4_close on file %pd\n", + dprintk("NFSD: nfsd4_close on file %pd\n", cstate->current_fh.fh_dentry); status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, - &close->cl_stateid, - NFS4_OPEN_STID|NFS4_CLOSED_STID, - &stp, nn); + &close->cl_stateid, + SC_TYPE_OPEN, SC_STATUS_CLOSED, + &stp, nn); nfsd4_bump_seqid(cstate, status); if (status) - goto out; + goto out; - stp->st_stid.sc_type = NFS4_CLOSED_STID; + spin_lock(&stp->st_stid.sc_client->cl_lock); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; + spin_unlock(&stp->st_stid.sc_client->cl_lock); /* * Technically we don't _really_ have to increment or copy it, since @@ -6992,8 +7801,10 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, */ nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); - nfsd4_close_open_stateid(stp); + need_move_to_close_list = nfsd4_close_open_stateid(stp); mutex_unlock(&stp->st_mutex); + if (need_move_to_close_list) + move_to_close_lru(stp, net); /* v4.1+ suggests that we send a special stateid in here, since the * clients should just ignore this anyway. Since this is not useful @@ -7021,10 +7832,11 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) + status = fh_verify(rqstp, &cstate->current_fh, 0, 0); + if (status) return status; - status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID, &s, nn); + status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED, &s, nn); if (status) goto out; dp = delegstateid(s); @@ -7033,8 +7845,9 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto put_stateid; trace_nfsd_deleg_return(stateid); - wake_up_var(d_inode(cstate->current_fh.fh_dentry)); destroy_delegation(dp); + smp_mb__after_atomic(); + wake_up_var(d_inode(cstate->current_fh.fh_dentry)); put_stateid: nfs4_put_stid(&dp->dl_stid); out: @@ -7091,7 +7904,7 @@ nfsd4_lm_put_owner(fl_owner_t owner) static bool nfsd4_lm_lock_expirable(struct file_lock *cfl) { - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)cfl->fl_owner; + struct nfs4_lockowner *lo = (struct nfs4_lockowner *) cfl->c.flc_owner; struct nfs4_client *clp = lo->lo_owner.so_client; struct nfsd_net *nn; @@ -7113,7 +7926,7 @@ nfsd4_lm_expire_lock(void) static void nfsd4_lm_notify(struct file_lock *fl) { - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)fl->fl_owner; + struct nfs4_lockowner *lo = (struct nfs4_lockowner *) fl->c.flc_owner; struct net *net = lo->lo_owner.so_client->net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfsd4_blocked_lock *nbl = container_of(fl, @@ -7131,7 +7944,7 @@ nfsd4_lm_notify(struct file_lock *fl) if (queue) { trace_nfsd_cb_notify_lock(lo, nbl); - nfsd4_run_cb(&nbl->nbl_cb); + nfsd4_try_run_cb(&nbl->nbl_cb); } } @@ -7150,7 +7963,7 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) struct nfs4_lockowner *lo; if (fl->fl_lmops == &nfsd_posix_mng_ops) { - lo = (struct nfs4_lockowner *) fl->fl_owner; + lo = (struct nfs4_lockowner *) fl->c.flc_owner; xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner, GFP_KERNEL); if (!deny->ld_owner.data) @@ -7169,7 +7982,7 @@ nevermind: 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) + if (fl->c.flc_type != F_RDLCK) deny->ld_type = NFS4_WRITE_LT; } @@ -7291,7 +8104,7 @@ retry: if (retstp) goto out_found; refcount_inc(&stp->st_stid.sc_count); - stp->st_stid.sc_type = NFS4_LOCK_STID; + stp->st_stid.sc_type = SC_TYPE_LOCK; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; @@ -7434,8 +8247,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int lkflg; int err; bool new = false; - unsigned char fl_type; - unsigned int fl_flags = FL_POSIX; + unsigned char type; + unsigned int flags = FL_POSIX; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -7446,10 +8259,12 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, 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"); + status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); + if (status != nfs_ok) return status; + if (exportfs_cannot_lock(cstate->current_fh.fh_dentry->d_sb->s_export_op)) { + status = nfserr_notsupp; + goto out; } if (lock->lk_is_new) { @@ -7476,9 +8291,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &lock_stp, &new); } else { status = nfs4_preprocess_seqid_op(cstate, - lock->lk_old_lock_seqid, - &lock->lk_old_lock_stateid, - NFS4_LOCK_STID, &lock_stp, nn); + lock->lk_old_lock_seqid, + &lock->lk_old_lock_stateid, + SC_TYPE_LOCK, 0, &lock_stp, + nn); } if (status) goto out; @@ -7497,13 +8313,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; if (lock->lk_reclaim) - fl_flags |= FL_RECLAIM; + flags |= FL_RECLAIM; fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate)) - fl_flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: spin_lock(&fp->fi_lock); @@ -7511,11 +8325,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ); spin_unlock(&fp->fi_lock); - fl_type = F_RDLCK; + type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate)) - fl_flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: spin_lock(&fp->fi_lock); @@ -7523,7 +8335,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE); spin_unlock(&fp->fi_lock); - fl_type = F_WRLCK; + type = F_WRLCK; break; default: status = nfserr_inval; @@ -7535,15 +8347,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - /* - * Most filesystems with their own ->lock operations will block - * the nfsd thread waiting to acquire the lock. That leads to - * deadlocks (we don't want every nfsd thread tied up waiting - * for file locks), so don't attempt blocking lock notifications - * on those filesystems: - */ - if (nf->nf_file->f_op->lock) - fl_flags &= ~FL_SLEEP; + if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) && + nfsd4_has_session(cstate) && + locks_can_async_lock(nf->nf_file->f_op)) + flags |= FL_SLEEP; nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { @@ -7553,11 +8360,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } file_lock = &nbl->nbl_lock; - file_lock->fl_type = fl_type; - file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); - file_lock->fl_pid = current->tgid; - file_lock->fl_file = nf->nf_file; - file_lock->fl_flags = fl_flags; + file_lock->c.flc_type = type; + file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_file = nf->nf_file; + file_lock->c.flc_flags = flags; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = lock->lk_offset; file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length); @@ -7570,7 +8377,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - if (fl_flags & FL_SLEEP) { + if (flags & FL_SLEEP) { nbl->nbl_time = ktime_get_boottime_seconds(); spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); @@ -7607,7 +8414,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, out: if (nbl) { /* dequeue it if we queued it before */ - if (fl_flags & FL_SLEEP) { + if (flags & FL_SLEEP) { spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list) && !list_empty(&nbl->nbl_lru)) { @@ -7648,6 +8455,14 @@ out: return status; } +void nfsd4_lock_release(union nfsd4_op_u *u) +{ + struct nfsd4_lock *lock = &u->lock; + struct nfsd4_lock_denied *deny = &lock->lk_denied; + + kfree(deny->ld_owner.data); +} + /* * 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 @@ -7667,9 +8482,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (err) goto out; - lock->fl_file = nf->nf_file; + lock->c.flc_file = nf->nf_file; err = nfserrno(vfs_test_lock(nf->nf_file, lock)); - lock->fl_file = NULL; + lock->c.flc_file = NULL; out: inode_unlock(inode); nfsd_file_put(nf); @@ -7714,11 +8529,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, switch (lockt->lt_type) { case NFS4_READ_LT: case NFS4_READW_LT: - file_lock->fl_type = F_RDLCK; + file_lock->c.flc_type = F_RDLCK; break; case NFS4_WRITE_LT: case NFS4_WRITEW_LT: - file_lock->fl_type = F_WRLCK; + file_lock->c.flc_type = F_WRLCK; break; default: dprintk("NFSD: nfs4_lockt: bad lock type!\n"); @@ -7728,9 +8543,9 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, lo = find_lockowner_str(cstate->clp, &lockt->lt_owner); if (lo) - file_lock->fl_owner = (fl_owner_t)lo; - file_lock->fl_pid = current->tgid; - file_lock->fl_flags = FL_POSIX; + file_lock->c.flc_owner = (fl_owner_t)lo; + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_flags = FL_POSIX; file_lock->fl_start = lockt->lt_offset; file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length); @@ -7741,7 +8556,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (file_lock->fl_type != F_UNLCK) { + if (file_lock->c.flc_type != F_UNLCK) { status = nfserr_denied; nfs4_set_lock_denied(file_lock, &lockt->lt_denied); } @@ -7753,6 +8568,14 @@ out: return status; } +void nfsd4_lockt_release(union nfsd4_op_u *u) +{ + struct nfsd4_lockt *lockt = &u->lockt; + struct nfsd4_lock_denied *deny = &lockt->lt_denied; + + kfree(deny->ld_owner.data); +} + __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -7773,8 +8596,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, - &locku->lu_stateid, NFS4_LOCK_STID, - &stp, nn); + &locku->lu_stateid, SC_TYPE_LOCK, 0, + &stp, nn); if (status) goto out; nf = find_any_file(stp->st_stid.sc_file); @@ -7782,6 +8605,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_lock_range; goto put_stateid; } + if (exportfs_cannot_lock(nf->nf_file->f_path.mnt->mnt_sb->s_export_op)) { + status = nfserr_notsupp; + goto put_file; + } + file_lock = locks_alloc_lock(); if (!file_lock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); @@ -7789,11 +8617,11 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto put_file; } - file_lock->fl_type = F_UNLCK; - file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); - file_lock->fl_pid = current->tgid; - file_lock->fl_file = nf->nf_file; - file_lock->fl_flags = FL_POSIX; + file_lock->c.flc_type = F_UNLCK; + file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_file = nf->nf_file; + file_lock->c.flc_flags = FL_POSIX; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = locku->lu_offset; @@ -7833,14 +8661,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct nfsd_file *nf = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } inode = file_inode(nf->nf_file); @@ -7848,15 +8678,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); - list_for_each_entry(fl, &flctx->flc_posix, fl_list) { - if (fl->fl_owner == (fl_owner_t)lowner) { + for_each_file_lock(fl, &flctx->flc_posix) { + if (fl->c.flc_owner == (fl_owner_t)lowner) { status = true; break; } } spin_unlock(&flctx->flc_lock); } - nfsd_file_put(nf); +out: + spin_unlock(&fp->fi_lock); return status; } @@ -7866,10 +8697,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * - * The lockowner's so_count is bumped when a lock record is added - * or when copying a conflicting lock. The latter case is brief, - * but can lead to fleeting false positives when looking for - * locks-in-use. + * Check if there are any locks still held and if not, free the lockowner + * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found @@ -7905,17 +8734,20 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, spin_unlock(&clp->cl_lock); return nfs_ok; } - if (atomic_read(&lo->lo_owner.so_count) != 2) { - spin_unlock(&clp->cl_lock); - nfs4_put_stateowner(&lo->lo_owner); - return nfserr_locks_held; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); + return nfserr_locks_held; + } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { stp = list_first_entry(&lo->lo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); - WARN_ON(!unhash_lock_stateid(stp)); + unhash_lock_stateid(stp); put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); @@ -7943,9 +8775,6 @@ nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) /* * failure => all reset bets are off, nfserr_no_grace... - * - * The caller is responsible for freeing name.data if NULL is returned (it - * will be freed in nfs4_remove_reclaim_record in the normal case). */ struct nfs4_client_reclaim * nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, @@ -7954,6 +8783,22 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, unsigned int strhashval; struct nfs4_client_reclaim *crp; + name.data = kmemdup(name.data, name.len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return NULL; + } + if (princhash.len) { + princhash.data = kmemdup(princhash.data, princhash.len, GFP_KERNEL); + if (!princhash.data) { + dprintk("%s: failed to allocate memory for princhash.data!\n", + __func__); + kfree(name.data); + return NULL; + } + } else + princhash.data = NULL; crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); @@ -7965,6 +8810,9 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, crp->cr_princhash.len = princhash.len; crp->cr_clp = NULL; nn->reclaim_str_hashtbl_size++; + } else { + kfree(name.data); + kfree(princhash.data); } return crp; } @@ -8084,6 +8932,7 @@ static int nfs4_state_create_net(struct net *net) spin_lock_init(&nn->client_lock); spin_lock_init(&nn->s2s_cp_lock); idr_init(&nn->s2s_cp_stateids); + atomic_set(&nn->pending_async_copies, 0); spin_lock_init(&nn->blocked_locks_lock); INIT_LIST_HEAD(&nn->blocked_locks_lru); @@ -8092,12 +8941,16 @@ static int nfs4_state_create_net(struct net *net) INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); - nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; - nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - - if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + nn->nfsd_client_shrinker = shrinker_alloc(0, "nfsd-client"); + if (!nn->nfsd_client_shrinker) goto err_shrinker; + + nn->nfsd_client_shrinker->scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker->count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker->private_data = nn; + + shrinker_register(nn->nfsd_client_shrinker); + return 0; err_shrinker: @@ -8168,7 +9021,6 @@ skip_grace: } /* initialization to perform when the nfsd service is started: */ - int nfs4_state_start(void) { @@ -8178,11 +9030,14 @@ nfs4_state_start(void) if (ret) return ret; - ret = nfsd4_create_callback_queue(); - if (ret) { + nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot"); + if (!nfsd_slot_shrinker) { rhltable_destroy(&nfs4_file_rhltable); - return ret; + return -ENOMEM; } + nfsd_slot_shrinker->count_objects = nfsd_slot_count; + nfsd_slot_shrinker->scan_objects = nfsd_slot_scan; + shrinker_register(nfsd_slot_shrinker); set_max_delegations(); return 0; @@ -8195,8 +9050,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - unregister_shrinker(&nn->nfsd_client_shrinker); - cancel_work(&nn->nfsd_shrinker_work); + shrinker_free(nn->nfsd_client_shrinker); + cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -8204,7 +9059,7 @@ nfs4_state_shutdown_net(struct net *net) spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); - WARN_ON(!unhash_delegation_locked(dp)); + unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -8224,8 +9079,8 @@ nfs4_state_shutdown_net(struct net *net) void nfs4_state_shutdown(void) { - nfsd4_destroy_callback_queue(); rhltable_destroy(&nfs4_file_rhltable); + shrinker_free(nfsd_slot_shrinker); } static void @@ -8341,3 +9196,274 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, { get_stateid(cstate, &u->write.wr_stateid); } + +/** + * nfsd4_vet_deleg_time - vet and set the timespec for a delegated timestamp update + * @req: timestamp from the client + * @orig: original timestamp in the inode + * @now: current time + * + * Given a timestamp from the client response, check it against the + * current timestamp in the inode and the current time. Returns true + * if the inode's timestamp needs to be updated, and false otherwise. + * @req may also be changed if the timestamp needs to be clamped. + */ +bool nfsd4_vet_deleg_time(struct timespec64 *req, const struct timespec64 *orig, + const struct timespec64 *now) +{ + + /* + * "When the time presented is before the original time, then the + * update is ignored." Also no need to update if there is no change. + */ + if (timespec64_compare(req, orig) <= 0) + return false; + + /* + * "When the time presented is in the future, the server can either + * clamp the new time to the current time, or it may + * return NFS4ERR_DELAY to the client, allowing it to retry." + */ + if (timespec64_compare(req, now) > 0) + *req = *now; + + return true; +} + +static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp) +{ + struct inode *inode = d_inode(dentry); + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + struct iattr attrs = { }; + int ret; + + if (deleg_attrs_deleg(dp->dl_type)) { + struct timespec64 now = current_time(inode); + + attrs.ia_atime = ncf->ncf_cb_atime; + attrs.ia_mtime = ncf->ncf_cb_mtime; + + if (nfsd4_vet_deleg_time(&attrs.ia_atime, &dp->dl_atime, &now)) + attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; + + if (nfsd4_vet_deleg_time(&attrs.ia_mtime, &dp->dl_mtime, &now)) { + attrs.ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; + attrs.ia_ctime = attrs.ia_mtime; + if (nfsd4_vet_deleg_time(&attrs.ia_ctime, &dp->dl_ctime, &now)) + attrs.ia_valid |= ATTR_CTIME | ATTR_CTIME_SET; + } + } else { + attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME; + } + + if (!attrs.ia_valid) + return 0; + + attrs.ia_valid |= ATTR_DELEG; + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); + inode_unlock(inode); + return ret; +} + +/** + * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict + * @rqstp: RPC transaction context + * @dentry: dentry of inode to be checked for a conflict + * @pdp: returned WRITE delegation, if one was found + * + * This function is called when there is a conflict between a write + * delegation and a change/size GETATTR from another client. The server + * must either use the CB_GETATTR to get the current values of the + * attributes from the client that holds the delegation or recall the + * delegation before replying to the GETATTR. See RFC 8881 section + * 18.7.4. + * + * Returns 0 if there is no conflict; otherwise an nfs_stat + * code is returned. If @pdp is set to a non-NULL value, then the + * caller must put the reference. + */ +__be32 +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, + struct nfs4_delegation **pdp) +{ + __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct file_lock_context *ctx; + struct nfs4_delegation *dp = NULL; + struct file_lease *fl; + struct nfs4_cb_fattr *ncf; + struct inode *inode = d_inode(dentry); + + ctx = locks_inode_context(inode); + if (!ctx) + return nfs_ok; + +#define NON_NFSD_LEASE ((void *)1) + + spin_lock(&ctx->flc_lock); + for_each_file_lock(fl, &ctx->flc_lease) { + if (fl->c.flc_flags == FL_LAYOUT) + continue; + if (fl->c.flc_type == F_WRLCK) { + if (fl->fl_lmops == &nfsd_lease_mng_ops) + dp = fl->c.flc_owner; + else + dp = NON_NFSD_LEASE; + } + break; + } + if (dp == NULL || dp == NON_NFSD_LEASE || + dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) { + spin_unlock(&ctx->flc_lock); + if (dp == NON_NFSD_LEASE) { + status = nfserrno(nfsd_open_break_lease(inode, + NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + return status; + } + return 0; + } + + nfsd_stats_wdeleg_getattr_inc(nn); + refcount_inc(&dp->dl_stid.sc_count); + ncf = &dp->dl_cb_fattr; + nfs4_cb_getattr(&dp->dl_cb_fattr); + spin_unlock(&ctx->flc_lock); + + wait_on_bit_timeout(&ncf->ncf_getattr.cb_flags, NFSD4_CALLBACK_RUNNING, + TASK_UNINTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT); + if (ncf->ncf_cb_status) { + /* Recall delegation only if client didn't respond */ + status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + goto out_status; + } + if (!ncf->ncf_file_modified && + (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || + ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) + ncf->ncf_file_modified = true; + if (ncf->ncf_file_modified) { + int err; + + /* + * Per section 10.4.3 of RFC 8881, the server would + * not update the file's metadata with the client's + * modified size + */ + err = cb_getattr_update_times(dentry, dp); + if (err) { + status = nfserrno(err); + goto out_status; + } + ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; + *pdp = dp; + return nfs_ok; + } + status = nfs_ok; +out_status: + nfs4_put_stid(&dp->dl_stid); + return status; +} + +/** + * nfsd_get_dir_deleg - attempt to get a directory delegation + * @cstate: compound state + * @gdd: GET_DIR_DELEGATION arg/resp structure + * @nf: nfsd_file opened on the directory + * + * Given a GET_DIR_DELEGATION request @gdd, attempt to acquire a delegation + * on the directory to which @nf refers. Note that this does not set up any + * sort of async notifications for the delegation. + */ +struct nfs4_delegation * +nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate, + struct nfsd4_get_dir_delegation *gdd, + struct nfsd_file *nf) +{ + struct nfs4_client *clp = cstate->clp; + struct nfs4_delegation *dp; + struct file_lease *fl; + struct nfs4_file *fp, *rfp; + int status = 0; + + fp = nfsd4_alloc_file(); + if (!fp) + return ERR_PTR(-ENOMEM); + + nfsd4_file_init(&cstate->current_fh, fp); + + rfp = nfsd4_file_hash_insert(fp, &cstate->current_fh); + if (unlikely(!rfp)) { + put_nfs4_file(fp); + return ERR_PTR(-ENOMEM); + } + + if (rfp != fp) { + put_nfs4_file(fp); + fp = rfp; + } + + /* if this client already has one, return that it's unavailable */ + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + /* existing delegation? */ + if (nfs4_delegation_exists(clp, fp)) { + status = -EAGAIN; + } else if (!fp->fi_deleg_file) { + fp->fi_deleg_file = nfsd_file_get(nf); + fp->fi_delegees = 1; + } else { + ++fp->fi_delegees; + } + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) { + put_nfs4_file(fp); + return ERR_PTR(status); + } + + /* Try to set up the lease */ + status = -ENOMEM; + dp = alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ); + if (!dp) + goto out_delegees; + + fl = nfs4_alloc_init_lease(dp); + if (!fl) + goto out_put_stid; + + status = kernel_setlease(nf->nf_file, + fl->c.flc_type, &fl, NULL); + if (fl) + locks_free_lease(fl); + if (status) + goto out_put_stid; + + /* + * Now, try to hash it. This can fail if we race another nfsd task + * trying to set a delegation on the same file. If that happens, + * then just say UNAVAIL. + */ + spin_lock(&state_lock); + spin_lock(&clp->cl_lock); + spin_lock(&fp->fi_lock); + status = hash_delegation_locked(dp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&clp->cl_lock); + spin_unlock(&state_lock); + + if (!status) + return dp; + + /* Something failed. Drop the lease and clean up the stid */ + kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); +out_put_stid: + nfs4_put_stid(&dp->dl_stid); +out_delegees: + put_deleg_file(fp); + return ERR_PTR(status); +} |