diff options
Diffstat (limited to 'fs/nfsd/nfs4state.c')
| -rw-r--r-- | fs/nfsd/nfs4state.c | 1447 |
1 files changed, 1005 insertions, 442 deletions
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a20c2c9d7d45..808c24fb5c9a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -149,14 +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; } @@ -400,6 +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, }; /* @@ -571,13 +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) { @@ -585,7 +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); } } @@ -639,18 +633,6 @@ find_readable_file(struct nfs4_file *f) return ret; } -static struct nfsd_file * -find_rw_file(struct nfs4_file *f) -{ - struct nfsd_file *ret; - - spin_lock(&f->fi_lock); - ret = nfsd_file_get(f->fi_fds[O_RDWR]); - spin_unlock(&f->fi_lock); - - return ret; -} - struct nfsd_file * find_any_file(struct nfs4_file *f) { @@ -952,15 +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); @@ -1056,6 +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); @@ -1077,7 +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. @@ -1106,9 +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); @@ -1182,7 +1162,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, 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; - dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; @@ -1227,15 +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) @@ -1245,6 +1265,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) WARN_ON_ONCE(!fp->fi_delegees); + nfsd4_finalize_deleg_timestamps(dp, nf->nf_file); kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); put_deleg_file(fp); } @@ -1357,21 +1378,48 @@ static void destroy_delegation(struct nfs4_delegation *dp) 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 (dp->dl_stid.sc_status & - (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED)) { - spin_lock(&clp->cl_lock); - 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); } @@ -1494,7 +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); } @@ -1632,6 +1681,14 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp) 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; @@ -1663,9 +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); @@ -1780,6 +1835,7 @@ void nfsd4_revoke_states(struct net *net, struct super_block *sb) 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( @@ -1882,113 +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); - - return num; -} + size = fattrs->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ ? + 0 : fattrs->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; -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; } @@ -2094,17 +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; @@ -2115,17 +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); /* @@ -2195,6 +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 */ @@ -2212,21 +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; @@ -2335,8 +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); } @@ -2369,9 +2496,8 @@ __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); @@ -2659,6 +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; @@ -2692,9 +2819,19 @@ static int client_info_show(struct seq_file *m, void *v) 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; @@ -2789,15 +2926,18 @@ 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" : "-"); - 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); + 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); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); @@ -2844,6 +2984,21 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) 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; @@ -2857,8 +3012,7 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: deleg, "); - 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. */ @@ -3047,7 +3201,6 @@ nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); drop_client(clp); } @@ -3056,7 +3209,10 @@ 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: @@ -3076,18 +3232,18 @@ nfsd4_cb_getattr_release(struct nfsd4_callback *cb) container_of(ncf, struct nfs4_delegation, dl_cb_fattr); nfs4_put_stid(&dp->dl_stid); - clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags); - wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY); } 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) @@ -3095,11 +3251,15 @@ 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(CB_GETATTR_BUSY, &ncf->ncf_cb_flags)) + 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); } @@ -3127,7 +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; @@ -3328,7 +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; @@ -3336,7 +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; } @@ -3351,41 +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. */ @@ -3393,17 +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); @@ -3454,7 +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, @@ -3492,6 +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; @@ -3629,6 +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; @@ -3645,10 +3818,18 @@ out_nolock: return status; } -static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse) +void +nfsd4_exchange_id_release(union nfsd4_op_u *u) +{ + 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 @@ -3657,6 +3838,8 @@ static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool 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; @@ -3715,17 +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; } @@ -3803,11 +3975,11 @@ 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; @@ -3878,6 +4050,8 @@ nfsd4_create_session(struct svc_rqst *rqstp, 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); @@ -3898,7 +4072,6 @@ nfsd4_create_session(struct svc_rqst *rqstp, return status; out_expired_error: - old = NULL; /* * Revert the slot seq_nr change so the server will process * the client's resend instead of returning a cached response. @@ -3913,12 +4086,9 @@ out_cache_error: 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; } @@ -4171,6 +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) @@ -4216,17 +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); - status = check_slot_seqid(seq->seqid, slot->sl_seqid, - slot->sl_flags & NFSD4_SLOT_INUSE); + + nfsd4_construct_sequence_response(session, seq); + + 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)) @@ -4251,6 +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; @@ -4258,12 +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 @@ -4273,21 +4478,48 @@ 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; - if (atomic_read(&clp->cl_admin_revoked)) - seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; + +out: trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) @@ -4503,10 +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; @@ -4523,10 +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); @@ -4556,6 +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)); @@ -4625,8 +4868,8 @@ out: static unsigned long nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { - int count; struct nfsd_net *nn = shrink->private_data; + long count; count = atomic_read(&nn->nfsd_courtesy_clients); if (!count) @@ -4677,7 +4920,7 @@ static void init_nfs4_replay(struct nfs4_replay *rp) rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; - atomic_set(&rp->rp_locked, RP_UNLOCKED); + rp->rp_locked = RP_UNLOCKED; } static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, @@ -4685,9 +4928,9 @@ static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, { if (!nfsd4_has_session(cstate)) { wait_var_event(&so->so_replay.rp_locked, - atomic_cmpxchg(&so->so_replay.rp_locked, - RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); - if (atomic_read(&so->so_replay.rp_locked) == RP_UNHASHED) + 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); } @@ -4700,8 +4943,7 @@ void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) if (so != NULL) { cstate->replay_owner = NULL; - atomic_set(&so->so_replay.rp_locked, RP_UNLOCKED); - wake_up_var(&so->so_replay.rp_locked); + store_release_wake_up(&so->so_replay.rp_locked, RP_UNLOCKED); nfs4_put_stateowner(so); } } @@ -4941,6 +5183,12 @@ 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; @@ -5000,8 +5248,7 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) * Some threads with a reference might be waiting for rp_locked, * so tell them to stop waiting. */ - atomic_set(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); - wake_up_var(&oo->oo_owner.so_replay.rp_locked); + 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); @@ -5215,10 +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 @@ -5227,7 +5480,10 @@ 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. */ @@ -5274,11 +5530,8 @@ static bool nfsd_breaker_owns_lease(struct file_lease *fl) 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; @@ -5404,7 +5657,7 @@ retry: 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; @@ -5636,8 +5889,7 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } -static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, - int flag) +static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp) { struct file_lease *fl; @@ -5646,7 +5898,7 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, return NULL; fl->fl_lmops = &nfsd_lease_mng_ops; fl->c.flc_flags = FL_DELEG; - fl->c.flc_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; + 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; @@ -5757,17 +6009,30 @@ 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 = NULL; struct file_lease *fl; + int status = 0; u32 dl_type; /* @@ -5784,15 +6049,20 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, * "An OPEN_DELEGATE_WRITE delegation allows the client to handle, * on its own, all opens." * - * Furthermore the client can use a write delegation for most READ - * operations as well, so we require a O_RDWR file here. + * 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)." * - * Offer a write delegation in the case of a BOTH open, and ensure - * we get the O_RDWR descriptor. + * 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_BOTH) == NFS4_SHARE_ACCESS_BOTH) { - nf = find_rw_file(fp); - dl_type = NFS4_OPEN_DELEGATE_WRITE; + 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; } /* @@ -5801,12 +6071,21 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, */ if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) { nf = find_readable_file(fp); - dl_type = NFS4_OPEN_DELEGATE_READ; + 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)) @@ -5833,7 +6112,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (!dp) goto out_delegees; - fl = nfs4_alloc_init_lease(dp, dl_type); + fl = nfs4_alloc_init_lease(dp); if (!fl) goto out_clnt_odstate; @@ -5856,7 +6135,7 @@ 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) @@ -5890,25 +6169,76 @@ 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; +} + /* * The Linux NFS server does not offer write delegations to NFSv4.0 * clients in order to avoid conflicts between write delegations and @@ -5934,17 +6264,18 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) * 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; - int status = 0; + struct nfs4_delegation *dp; struct kstat stat; - struct path path; + int status = 0; + int cb_up; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); open->op_recall = false; @@ -5980,33 +6311,35 @@ 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)); if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE; - trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); - path.mnt = currentfh->fh_export->ex_path.mnt; - path.dentry = currentfh->fh_dentry; - if (vfs_getattr(&path, &stat, - (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE), - AT_STATX_SYNC_AS_STAT)) { + 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, d_inode(currentfh->fh_dentry)); + 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 = NFS4_OPEN_DELEGATE_READ; + 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 = true; - } + open->op_delegate_type = OPEN_DELEGATE_NONE; /* 4.1 client asking for a delegation? */ if (open->op_deleg_want) @@ -6017,21 +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 @@ -6067,6 +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; @@ -6077,6 +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; } @@ -6112,8 +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; } @@ -6123,13 +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); @@ -6140,7 +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)) @@ -6268,7 +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 @@ -6513,6 +6887,7 @@ 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); @@ -6523,6 +6898,7 @@ nfs4_laundromat(struct nfsd_net *nn) dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(<, dp->dl_time)) break; + refcount_inc(&dp->dl_stid.sc_count); unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } @@ -6616,40 +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 */ kref_get(&clp->cl_nfsdfs.cl_ref); - set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); 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 @@ -6810,11 +7180,11 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, return_revoked = true; if (typemask & SC_TYPE_DELEG) /* Always allow REVOKED for DELEG so we can - * retturn the appropriate error. + * return the appropriate error. */ statusmask |= SC_STATUS_REVOKED; - statusmask |= SC_STATUS_ADMIN_REVOKED; + statusmask |= SC_STATUS_ADMIN_REVOKED | SC_STATUS_FREEABLE; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) @@ -6853,10 +7223,6 @@ nfs4_find_file(struct nfs4_stid *s, int flags) switch (s->sc_type) { case SC_TYPE_DELEG: - 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 SC_TYPE_OPEN: case SC_TYPE_LOCK: if (flags & RD_STATE) @@ -6889,7 +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); @@ -7020,11 +7387,7 @@ 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; } @@ -7137,9 +7500,12 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, switch (s->sc_type) { 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); - list_del_init(&dp->dl_recall_lru); + 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; @@ -7466,10 +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, SC_TYPE_DELEG, 0, &s, nn); + status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED, &s, nn); if (status) goto out; dp = delegstateid(s); @@ -7478,8 +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: @@ -7576,7 +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); } } @@ -7875,7 +8243,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; - struct super_block *sb; __be32 status = 0; int lkflg; int err; @@ -7892,12 +8259,13 @@ 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; } - sb = cstate->current_fh.fh_dentry->d_sb; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) @@ -7950,9 +8318,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate) || - exportfs_lock_op_is_async(sb->s_export_op)) - flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: spin_lock(&fp->fi_lock); @@ -7963,9 +8328,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate) || - exportfs_lock_op_is_async(sb->s_export_op)) - flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: spin_lock(&fp->fi_lock); @@ -7985,15 +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 (!exportfs_lock_op_is_async(sb->s_export_op)) - 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) { @@ -8248,6 +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__); @@ -8335,7 +8697,7 @@ out: * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * - * Check if theree are any locks still held and if not - free the lockowner + * Check if there are any locks still held and if not, free the lockowner * and any lock state that is owned. * * Return values: @@ -8413,9 +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, @@ -8424,6 +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); @@ -8435,6 +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; } @@ -8554,6 +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); @@ -8642,7 +9021,6 @@ skip_grace: } /* initialization to perform when the nfsd service is started: */ - int nfs4_state_start(void) { @@ -8652,6 +9030,15 @@ nfs4_state_start(void) if (ret) return ret; + nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot"); + if (!nfsd_slot_shrinker) { + rhltable_destroy(&nfs4_file_rhltable); + 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; } @@ -8664,7 +9051,7 @@ nfs4_state_shutdown_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); shrinker_free(nn->nfsd_client_shrinker); - cancel_work(&nn->nfsd_shrinker_work); + cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -8693,6 +9080,7 @@ void nfs4_state_shutdown(void) { rhltable_destroy(&nfs4_file_rhltable); + shrinker_free(nfsd_slot_shrinker); } static void @@ -8810,11 +9198,79 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, } /** + * 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 - * @inode: file to be checked for a conflict - * @modified: return true if file was modified - * @size: new size of file if modified is true + * @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 @@ -8824,83 +9280,190 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, * 18.7.4. * * Returns 0 if there is no conflict; otherwise an nfs_stat - * code is returned. + * 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 inode *inode, - bool *modified, u64 *size) +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_delegation *dp; - struct iattr attrs; struct nfs4_cb_fattr *ncf; + struct inode *inode = d_inode(dentry); - *modified = false; ctx = locks_inode_context(inode); if (!ctx) - return 0; + return nfs_ok; + +#define NON_NFSD_LEASE ((void *)1) + spin_lock(&ctx->flc_lock); for_each_file_lock(fl, &ctx->flc_lease) { - unsigned char type = fl->c.flc_type; - if (fl->c.flc_flags == FL_LAYOUT) continue; - if (fl->fl_lmops != &nfsd_lease_mng_ops) { - /* - * non-nfs lease, if it's a lease with F_RDLCK then - * we are done; there isn't any write delegation - * on this inode - */ - if (type == F_RDLCK) - break; - goto break_lease; - } - if (type == F_WRLCK) { - dp = fl->c.flc_owner; - if (dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) { - spin_unlock(&ctx->flc_lock); - return 0; - } -break_lease: - nfsd_stats_wdeleg_getattr_inc(nn); - dp = fl->c.flc_owner; - ncf = &dp->dl_cb_fattr; - nfs4_cb_getattr(&dp->dl_cb_fattr); - spin_unlock(&ctx->flc_lock); - wait_on_bit_timeout(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, - TASK_INTERRUPTIBLE, 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)) - return 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) { - /* - * Per section 10.4.3 of RFC 8881, the server would - * not update the file's metadata with the client's - * modified size - */ - attrs.ia_mtime = attrs.ia_ctime = current_time(inode); - attrs.ia_valid = ATTR_MTIME | ATTR_CTIME; - setattr_copy(&nop_mnt_idmap, inode, &attrs); - mark_inode_dirty(inode); - ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; - *size = ncf->ncf_cur_fsize; - *modified = true; - } - return 0; + 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); - return 0; + + 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); } |