diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/exportfs/expfs.c | 1 | ||||
-rw-r--r-- | fs/lockd/mon.c | 3 | ||||
-rw-r--r-- | fs/lockd/svc.c | 52 | ||||
-rw-r--r-- | fs/lockd/svclock.c | 18 | ||||
-rw-r--r-- | fs/locks.c | 7 | ||||
-rw-r--r-- | fs/nfs/callback.c | 23 | ||||
-rw-r--r-- | fs/nfsd/blocklayoutxdr.c | 9 | ||||
-rw-r--r-- | fs/nfsd/cache.h | 8 | ||||
-rw-r--r-- | fs/nfsd/flexfilelayoutxdr.c | 9 | ||||
-rw-r--r-- | fs/nfsd/nfs3proc.c | 4 | ||||
-rw-r--r-- | fs/nfsd/nfs4acl.c | 34 | ||||
-rw-r--r-- | fs/nfsd/nfs4proc.c | 51 | ||||
-rw-r--r-- | fs/nfsd/nfs4state.c | 162 | ||||
-rw-r--r-- | fs/nfsd/nfs4xdr.c | 39 | ||||
-rw-r--r-- | fs/nfsd/nfscache.c | 204 | ||||
-rw-r--r-- | fs/nfsd/nfsctl.c | 1 | ||||
-rw-r--r-- | fs/nfsd/nfsd.h | 7 | ||||
-rw-r--r-- | fs/nfsd/nfsfh.c | 26 | ||||
-rw-r--r-- | fs/nfsd/nfsfh.h | 6 | ||||
-rw-r--r-- | fs/nfsd/nfssvc.c | 111 | ||||
-rw-r--r-- | fs/nfsd/state.h | 3 | ||||
-rw-r--r-- | fs/nfsd/stats.c | 2 | ||||
-rw-r--r-- | fs/nfsd/stats.h | 7 | ||||
-rw-r--r-- | fs/nfsd/trace.h | 27 | ||||
-rw-r--r-- | fs/nfsd/vfs.c | 52 | ||||
-rw-r--r-- | fs/nfsd/xdr4.h | 11 |
26 files changed, 550 insertions, 327 deletions
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index d1dbe47c7975..c20704aa21b3 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -386,6 +386,7 @@ static int export_encode_fh(struct inode *inode, struct fid *fid, * @inode: the object to encode * @fid: where to store the file handle fragment * @max_len: maximum length to store there + * @parent: parent directory inode, if wanted * @flags: properties of the requested file handle * * Returns an enum fid_type or a negative errno. diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1d9488cf0534..87a0f207df0b 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -276,6 +276,9 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, { struct nsm_handle *new; + if (!hostname) + return NULL; + new = kzalloc(sizeof(*new) + hostname_len + 1, GFP_KERNEL); if (unlikely(new == NULL)) return NULL; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 22d3ff3818f5..6579948070a4 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -45,7 +45,6 @@ #define NLMDBG_FACILITY NLMDBG_SVC #define LOCKD_BUFSIZE (1024 + NLMSVC_XDRSIZE) -#define ALLOWED_SIGS (sigmask(SIGKILL)) static struct svc_program nlmsvc_program; @@ -57,6 +56,12 @@ static unsigned int nlmsvc_users; static struct svc_serv *nlmsvc_serv; unsigned long nlmsvc_timeout; +static void nlmsvc_request_retry(struct timer_list *tl) +{ + svc_wake_up(nlmsvc_serv); +} +DEFINE_TIMER(nlmsvc_retry, nlmsvc_request_retry); + unsigned int lockd_net_id; /* @@ -111,26 +116,12 @@ static void set_grace_period(struct net *net) schedule_delayed_work(&ln->grace_period_end, grace_period); } -static void restart_grace(void) -{ - if (nlmsvc_ops) { - struct net *net = &init_net; - struct lockd_net *ln = net_generic(net, lockd_net_id); - - cancel_delayed_work_sync(&ln->grace_period_end); - locks_end_grace(&ln->lockd_manager); - nlmsvc_invalidate_all(); - set_grace_period(net); - } -} - /* * This is the lockd kernel thread */ static int lockd(void *vrqstp) { - int err = 0; struct svc_rqst *rqstp = vrqstp; struct net *net = &init_net; struct lockd_net *ln = net_generic(net, lockd_net_id); @@ -138,9 +129,6 @@ lockd(void *vrqstp) /* try_to_freeze() is called from svc_recv() */ set_freezable(); - /* Allow SIGKILL to tell lockd to drop all of its locks */ - allow_signal(SIGKILL); - dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n"); /* @@ -148,33 +136,12 @@ lockd(void *vrqstp) * NFS mount or NFS daemon has gone away. */ while (!kthread_should_stop()) { - long timeout = MAX_SCHEDULE_TIMEOUT; - RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); - /* update sv_maxconn if it has changed */ rqstp->rq_server->sv_maxconn = nlm_max_connections; - if (signalled()) { - flush_signals(current); - restart_grace(); - continue; - } - - timeout = nlmsvc_retry_blocked(); - - /* - * Find a socket with data available and call its - * recvfrom routine. - */ - err = svc_recv(rqstp, timeout); - if (err == -EAGAIN || err == -EINTR) - continue; - dprintk("lockd: request from %s\n", - svc_print_addr(rqstp, buf, sizeof(buf))); - - svc_process(rqstp); + nlmsvc_retry_blocked(); + svc_recv(rqstp); } - flush_signals(current); if (nlmsvc_ops) nlmsvc_invalidate_all(); nlm_shutdown_hosts(); @@ -407,6 +374,7 @@ static void lockd_put(void) #endif svc_set_num_threads(nlmsvc_serv, NULL, 0); + timer_delete_sync(&nlmsvc_retry); nlmsvc_serv = NULL; dprintk("lockd_down: service destroyed\n"); } @@ -538,7 +506,7 @@ static inline int is_callback(u32 proc) } -static int lockd_authenticate(struct svc_rqst *rqstp) +static enum svc_auth_status lockd_authenticate(struct svc_rqst *rqstp) { rqstp->rq_client = NULL; switch (rqstp->rq_authop->flavour) { diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index c43ccdf28ed9..43aeba9de55c 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -131,12 +131,14 @@ static void nlmsvc_insert_block(struct nlm_block *block, unsigned long when) static inline void nlmsvc_remove_block(struct nlm_block *block) { + spin_lock(&nlm_blocked_lock); if (!list_empty(&block->b_list)) { - spin_lock(&nlm_blocked_lock); list_del_init(&block->b_list); spin_unlock(&nlm_blocked_lock); nlmsvc_release_block(block); + return; } + spin_unlock(&nlm_blocked_lock); } /* @@ -152,6 +154,7 @@ nlmsvc_lookup_block(struct nlm_file *file, struct nlm_lock *lock) file, lock->fl.fl_pid, (long long)lock->fl.fl_start, (long long)lock->fl.fl_end, lock->fl.fl_type); + spin_lock(&nlm_blocked_lock); list_for_each_entry(block, &nlm_blocked, b_list) { fl = &block->b_call->a_args.lock.fl; dprintk("lockd: check f=%p pd=%d %Ld-%Ld ty=%d cookie=%s\n", @@ -161,9 +164,11 @@ nlmsvc_lookup_block(struct nlm_file *file, struct nlm_lock *lock) nlmdbg_cookie2a(&block->b_call->a_args.cookie)); if (block->b_file == file && nlm_compare_locks(fl, &lock->fl)) { kref_get(&block->b_count); + spin_unlock(&nlm_blocked_lock); return block; } } + spin_unlock(&nlm_blocked_lock); return NULL; } @@ -185,16 +190,19 @@ nlmsvc_find_block(struct nlm_cookie *cookie) { struct nlm_block *block; + spin_lock(&nlm_blocked_lock); list_for_each_entry(block, &nlm_blocked, b_list) { if (nlm_cookie_match(&block->b_call->a_args.cookie,cookie)) goto found; } + spin_unlock(&nlm_blocked_lock); return NULL; found: dprintk("nlmsvc_find_block(%s): block=%p\n", nlmdbg_cookie2a(cookie), block); kref_get(&block->b_count); + spin_unlock(&nlm_blocked_lock); return block; } @@ -317,6 +325,7 @@ void nlmsvc_traverse_blocks(struct nlm_host *host, restart: mutex_lock(&file->f_mutex); + spin_lock(&nlm_blocked_lock); list_for_each_entry_safe(block, next, &file->f_blocks, b_flist) { if (!match(block->b_host, host)) continue; @@ -325,11 +334,13 @@ restart: if (list_empty(&block->b_list)) continue; kref_get(&block->b_count); + spin_unlock(&nlm_blocked_lock); mutex_unlock(&file->f_mutex); nlmsvc_unlink_block(block); nlmsvc_release_block(block); goto restart; } + spin_unlock(&nlm_blocked_lock); mutex_unlock(&file->f_mutex); } @@ -1008,7 +1019,7 @@ retry_deferred_block(struct nlm_block *block) * picks up locks that can be granted, or grant notifications that must * be retransmitted. */ -unsigned long +void nlmsvc_retry_blocked(void) { unsigned long timeout = MAX_SCHEDULE_TIMEOUT; @@ -1038,5 +1049,6 @@ nlmsvc_retry_blocked(void) } spin_unlock(&nlm_blocked_lock); - return timeout; + if (timeout < MAX_SCHEDULE_TIMEOUT) + mod_timer(&nlmsvc_retry, jiffies + timeout); } diff --git a/fs/locks.c b/fs/locks.c index a45efc16945d..76ad05f8070a 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1744,13 +1744,6 @@ generic_add_lease(struct file *filp, int arg, struct file_lock **flp, void **pri if (is_deleg && !inode_trylock(inode)) return -EAGAIN; - if (is_deleg && arg == F_WRLCK) { - /* Write delegations are not currently supported: */ - inode_unlock(inode); - WARN_ON_ONCE(1); - return -EINVAL; - } - percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 456af7d230cf..466ebf1d41b2 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -74,23 +74,12 @@ out_err: static int nfs4_callback_svc(void *vrqstp) { - int err; struct svc_rqst *rqstp = vrqstp; set_freezable(); - while (!kthread_freezable_should_stop(NULL)) { - - if (signal_pending(current)) - flush_signals(current); - /* - * Listen for a request on the socket - */ - err = svc_recv(rqstp, MAX_SCHEDULE_TIMEOUT); - if (err == -EAGAIN || err == -EINTR) - continue; - svc_process(rqstp); - } + while (!kthread_freezable_should_stop(NULL)) + svc_recv(rqstp); svc_exit_thread(rqstp); return 0; @@ -112,11 +101,7 @@ nfs41_callback_svc(void *vrqstp) set_freezable(); while (!kthread_freezable_should_stop(NULL)) { - - if (signal_pending(current)) - flush_signals(current); - - prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_IDLE); spin_lock_bh(&serv->sv_cb_lock); if (!list_empty(&serv->sv_cb_list)) { req = list_first_entry(&serv->sv_cb_list, @@ -387,7 +372,7 @@ check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp) * All other checking done after NFS decoding where the nfs_client can be * found in nfs4_callback_compound */ -static int nfs_callback_authenticate(struct svc_rqst *rqstp) +static enum svc_auth_status nfs_callback_authenticate(struct svc_rqst *rqstp) { rqstp->rq_auth_stat = rpc_autherr_badcred; diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 8e9c1a0f8d38..1ed2f691ebb9 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -83,6 +83,15 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, int len = sizeof(__be32), ret, i; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + p = xdr_reserve_space(xdr, len + sizeof(__be32)); if (!p) return nfserr_resource; diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 4c9b87850ab1..929248c6ca84 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -19,7 +19,7 @@ * typical sockaddr_storage. This is for space reasons, since sockaddr_storage * is much larger than a sockaddr_in6. */ -struct svc_cacherep { +struct nfsd_cacherep { struct { /* Keep often-read xid, csum in the same cache line: */ __be32 k_xid; @@ -84,8 +84,10 @@ int nfsd_net_reply_cache_init(struct nfsd_net *nn); void nfsd_net_reply_cache_destroy(struct nfsd_net *nn); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); -int nfsd_cache_lookup(struct svc_rqst *); -void nfsd_cache_update(struct svc_rqst *, int, __be32 *); +int nfsd_cache_lookup(struct svc_rqst *rqstp, + struct nfsd_cacherep **cacherep); +void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, + int cachetype, __be32 *statp); int nfsd_reply_cache_stats_show(struct seq_file *m, void *v); #endif /* NFSCACHE_H */ diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index e81d2a5cf381..bb205328e043 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -85,6 +85,15 @@ nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, int addr_len; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + /* len + padding for two strings */ addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; ver_len = 20; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index fc8d5b7db9f8..268ef57751c4 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -307,7 +307,9 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!IS_POSIXACL(inode)) iap->ia_mode &= ~current_umask(); - fh_fill_pre_attrs(fhp); + status = fh_fill_pre_attrs(fhp); + if (status != nfs_ok) + goto out; host_err = vfs_create(&nop_mnt_idmap, inode, child, iap->ia_mode, true); if (host_err < 0) { status = nfserrno(host_err); diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 518203821790..96e786b5e544 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -441,7 +441,7 @@ struct posix_ace_state_array { * calculated so far: */ struct posix_acl_state { - int empty; + unsigned char valid; struct posix_ace_state owner; struct posix_ace_state group; struct posix_ace_state other; @@ -457,7 +457,6 @@ init_state(struct posix_acl_state *state, int cnt) int alloc; memset(state, 0, sizeof(struct posix_acl_state)); - state->empty = 1; /* * In the worst case, each individual acl could be for a distinct * named user or group, but we don't know which, so we allocate @@ -500,7 +499,7 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags) * and effective cases: when there are no inheritable ACEs, * calls ->set_acl with a NULL ACL structure. */ - if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) + if (!state->valid && (flags & NFS4_ACL_TYPE_DEFAULT)) return NULL; /* @@ -622,11 +621,12 @@ static void process_one_v4_ace(struct posix_acl_state *state, struct nfs4_ace *ace) { u32 mask = ace->access_mask; + short type = ace2type(ace); int i; - state->empty = 0; + state->valid |= type; - switch (ace2type(ace)) { + switch (type) { case ACL_USER_OBJ: if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) { allow_bits(&state->owner, mask); @@ -726,6 +726,30 @@ static int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *acl, if (!(ace->flag & NFS4_ACE_INHERIT_ONLY_ACE)) process_one_v4_ace(&effective_acl_state, ace); } + + /* + * At this point, the default ACL may have zeroed-out entries for owner, + * group and other. That usually results in a non-sensical resulting ACL + * that denies all access except to any ACE that was explicitly added. + * + * The setfacl command solves a similar problem with this logic: + * + * "If a Default ACL entry is created, and the Default ACL contains + * no owner, owning group, or others entry, a copy of the ACL + * owner, owning group, or others entry is added to the Default ACL." + * + * Copy any missing ACEs from the effective set, if any ACEs were + * explicitly set. + */ + if (default_acl_state.valid) { + if (!(default_acl_state.valid & ACL_USER_OBJ)) + default_acl_state.owner = effective_acl_state.owner; + if (!(default_acl_state.valid & ACL_GROUP_OBJ)) + default_acl_state.group = effective_acl_state.group; + if (!(default_acl_state.valid & ACL_OTHER)) + default_acl_state.other = effective_acl_state.other; + } + *pacl = posix_state_to_acl(&effective_acl_state, flags); if (IS_ERR(*pacl)) { ret = PTR_ERR(*pacl); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 5ae670807449..5ca748309c26 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -297,12 +297,12 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, } if (d_really_is_positive(child)) { - status = nfs_ok; - /* NFSv4 protocol requires change attributes even though * no change happened. */ - fh_fill_both_attrs(fhp); + status = fh_fill_both_attrs(fhp); + if (status != nfs_ok) + goto out; switch (open->op_createmode) { case NFS4_CREATE_UNCHECKED: @@ -345,7 +345,9 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (!IS_POSIXACL(inode)) iap->ia_mode &= ~current_umask(); - fh_fill_pre_attrs(fhp); + status = fh_fill_pre_attrs(fhp); + if (status != nfs_ok) + goto out; status = nfsd4_vfs_create(fhp, child, open); if (status != nfs_ok) goto out; @@ -380,6 +382,38 @@ out: return status; } +/** + * set_change_info - set up the change_info4 for a reply + * @cinfo: pointer to nfsd4_change_info to be populated + * @fhp: pointer to svc_fh to use as source + * + * Many operations in NFSv4 require change_info4 in the reply. This function + * populates that from the info that we (should!) have already collected. In + * the event that we didn't get any pre-attrs, just zero out both. + */ +static void +set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) +{ + cinfo->atomic = (u32)(fhp->fh_pre_saved && fhp->fh_post_saved && !fhp->fh_no_atomic_attr); + cinfo->before_change = fhp->fh_pre_change; + cinfo->after_change = fhp->fh_post_change; + + /* + * If fetching the pre-change attributes failed, then we should + * have already failed the whole operation. We could have still + * failed to fetch post-change attributes however. + * + * If we didn't get post-op attrs, just zero-out the after + * field since we don't know what it should be. If the pre_saved + * field isn't set for some reason, throw warning and just copy + * whatever is in the after field. + */ + if (WARN_ON_ONCE(!fhp->fh_pre_saved)) + cinfo->before_change = 0; + if (!fhp->fh_post_saved) + cinfo->after_change = cinfo->before_change + 1; +} + static __be32 do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh) { @@ -424,11 +458,11 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru } else { status = nfsd_lookup(rqstp, current_fh, open->op_fname, open->op_fnamelen, *resfh); - if (!status) + if (status == nfs_ok) /* NFSv4 protocol requires change attributes even though * no change happened. */ - fh_fill_both_attrs(current_fh); + status = fh_fill_both_attrs(current_fh); } if (status) goto out; @@ -1313,12 +1347,11 @@ try_again: /* found a match */ if (ni->nsui_busy) { /* wait - and try again */ - prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, - TASK_INTERRUPTIBLE); + prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, TASK_IDLE); spin_unlock(&nn->nfsd_ssc_lock); /* allow 20secs for mount/unmount for now - revisit */ - if (signal_pending(current) || + if (kthread_should_stop() || (schedule_timeout(20*HZ) == 0)) { finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index daf305daa751..8534693eb6a4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -649,6 +649,18 @@ 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) { @@ -1144,7 +1156,7 @@ 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; long n; @@ -1170,7 +1182,7 @@ 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, @@ -5449,8 +5461,9 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, 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 nfsd_file *nf = NULL; struct file_lock *fl; + u32 dl_type; /* * The fi_had_conflict and nfs_get_existing_delegation checks @@ -5460,15 +5473,35 @@ 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. - */ - return ERR_PTR(-EAGAIN); + /* + * 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 the client can use a write delegation for most READ + * operations as well, so we require a O_RDWR file here. + * + * Offer a write delegation in the case of a BOTH open, and ensure + * we get the O_RDWR descriptor. + */ + 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 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 = NFS4_OPEN_DELEGATE_READ; + } + + if (!nf) + return ERR_PTR(-EAGAIN); + spin_lock(&state_lock); spin_lock(&fp->fi_lock); if (nfs4_delegation_exists(clp, fp)) @@ -5491,11 +5524,11 @@ 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, dl_type); if (!fl) goto out_clnt_odstate; @@ -5568,10 +5601,28 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) } /* - * 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. + * + * 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. * - * Note we don't support write delegations, and won't until the vfs has - * proper support for them. + * 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, @@ -5590,8 +5641,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, 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; break; case NFS4_OPEN_CLAIM_NULL: parent = currentfh; @@ -5606,6 +5655,9 @@ 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; @@ -5616,8 +5668,13 @@ 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) { + open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE; + trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); + } else { + open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; + trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); + } nfs4_put_stid(&dp->dl_stid); return; out_no_deleg: @@ -8341,3 +8398,68 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, { get_stateid(cstate, &u->write.wr_stateid); } + +/** + * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict + * @rqstp: RPC transaction context + * @inode: file to be checked for a conflict + * + * 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. + * + * The current implementation does not support CB_GETATTR yet. However + * this can avoid recalling the delegation could be added in follow up + * work. + * + * Returns 0 if there is no conflict; otherwise an nfs_stat + * code is returned. + */ +__be32 +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode) +{ + __be32 status; + struct file_lock_context *ctx; + struct file_lock *fl; + struct nfs4_delegation *dp; + + ctx = locks_inode_context(inode); + if (!ctx) + return 0; + spin_lock(&ctx->flc_lock); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_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 (fl->fl_type == F_RDLCK) + break; + goto break_lease; + } + if (fl->fl_type == F_WRLCK) { + dp = fl->fl_owner; + if (dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) { + spin_unlock(&ctx->flc_lock); + return 0; + } +break_lease: + spin_unlock(&ctx->flc_lock); + nfsd_stats_wdeleg_getattr_inc(); + status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + return status; + return 0; + } + break; + } + spin_unlock(&ctx->flc_lock); + return 0; +} diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index b30dca7de8cc..2e40c74d2f72 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2984,6 +2984,11 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, if (status) goto out; } + if (bmval0 & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { + status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry)); + if (status) + goto out; + } err = vfs_getattr(&path, &stat, STATX_BASIC_STATS | STATX_BTIME | STATX_CHANGE_COOKIE, @@ -3973,17 +3978,20 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid); if (nfserr) return nfserr; - p = xdr_reserve_space(xdr, 32); + + p = xdr_reserve_space(xdr, XDR_UNIT * 8); if (!p) return nfserr_resource; *p++ = cpu_to_be32(open->op_recall); /* + * Always flush on close + * * TODO: space_limit's in delegations */ *p++ = cpu_to_be32(NFS4_LIMIT_SIZE); - *p++ = cpu_to_be32(~(u32)0); - *p++ = cpu_to_be32(~(u32)0); + *p++ = xdr_zero; + *p++ = xdr_zero; /* * TODO: ACE's in delegations @@ -4678,20 +4686,17 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(gdev->gd_layout_type); - /* If maxcount is 0 then just update notifications */ - if (gdev->gd_maxcount != 0) { - ops = nfsd4_layout_ops[gdev->gd_layout_type]; - nfserr = ops->encode_getdeviceinfo(xdr, gdev); - if (nfserr) { - /* - * We don't bother to burden the layout drivers with - * enforcing gd_maxcount, just tell the client to - * come back with a bigger buffer if it's not enough. - */ - if (xdr->buf->len + 4 > gdev->gd_maxcount) - goto toosmall; - return nfserr; - } + ops = nfsd4_layout_ops[gdev->gd_layout_type]; + nfserr = ops->encode_getdeviceinfo(xdr, gdev); + if (nfserr) { + /* + * We don't bother to burden the layout drivers with + * enforcing gd_maxcount, just tell the client to + * come back with a bigger buffer if it's not enough. + */ + if (xdr->buf->len + 4 > gdev->gd_maxcount) + goto toosmall; + return nfserr; } if (gdev->gd_notify_types) { diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index a8eda1c85829..80621a709510 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -84,11 +84,11 @@ nfsd_hashsize(unsigned int limit) return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE); } -static struct svc_cacherep * -nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, - struct nfsd_net *nn) +static struct nfsd_cacherep * +nfsd_cacherep_alloc(struct svc_rqst *rqstp, __wsum csum, + struct nfsd_net *nn) { - struct svc_cacherep *rp; + struct nfsd_cacherep *rp; rp = kmem_cache_alloc(drc_slab, GFP_KERNEL); if (rp) { @@ -110,36 +110,64 @@ nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, return rp; } -static void -nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, - struct nfsd_net *nn) +static void nfsd_cacherep_free(struct nfsd_cacherep *rp) { - if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) { - nfsd_stats_drc_mem_usage_sub(nn, rp->c_replvec.iov_len); + if (rp->c_type == RC_REPLBUFF) kfree(rp->c_replvec.iov_base); + kmem_cache_free(drc_slab, rp); +} + +static unsigned long +nfsd_cacherep_dispose(struct list_head *dispose) +{ + struct nfsd_cacherep *rp; + unsigned long freed = 0; + + while (!list_empty(dispose)) { + rp = list_first_entry(dispose, struct nfsd_cacherep, c_lru); + list_del(&rp->c_lru); + nfsd_cacherep_free(rp); + freed++; } + return freed; +} + +static void +nfsd_cacherep_unlink_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, + struct nfsd_cacherep *rp) +{ + if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) + nfsd_stats_drc_mem_usage_sub(nn, rp->c_replvec.iov_len); if (rp->c_state != RC_UNUSED) { rb_erase(&rp->c_node, &b->rb_head); list_del(&rp->c_lru); atomic_dec(&nn->num_drc_entries); nfsd_stats_drc_mem_usage_sub(nn, sizeof(*rp)); } - kmem_cache_free(drc_slab, rp); } static void -nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, +nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp, + struct nfsd_net *nn) +{ + nfsd_cacherep_unlink_locked(nn, b, rp); + nfsd_cacherep_free(rp); +} + +static void +nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp, struct nfsd_net *nn) { spin_lock(&b->cache_lock); - nfsd_reply_cache_free_locked(b, rp, nn); + nfsd_cacherep_unlink_locked(nn, b, rp); spin_unlock(&b->cache_lock); + nfsd_cacherep_free(rp); } int nfsd_drc_slab_create(void) { drc_slab = kmem_cache_create("nfsd_drc", - sizeof(struct svc_cacherep), 0, 0, NULL); + sizeof(struct nfsd_cacherep), 0, 0, NULL); return drc_slab ? 0: -ENOMEM; } @@ -208,7 +236,7 @@ out_shrinker: void nfsd_reply_cache_shutdown(struct nfsd_net *nn) { - struct svc_cacherep *rp; + struct nfsd_cacherep *rp; unsigned int i; unregister_shrinker(&nn->nfsd_reply_cache_shrinker); @@ -216,7 +244,7 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) for (i = 0; i < nn->drc_hashsize; i++) { struct list_head *head = &nn->drc_hashtbl[i].lru_head; while (!list_empty(head)) { - rp = list_first_entry(head, struct svc_cacherep, c_lru); + rp = list_first_entry(head, struct nfsd_cacherep, c_lru); nfsd_reply_cache_free_locked(&nn->drc_hashtbl[i], rp, nn); } @@ -233,7 +261,7 @@ void nfsd_reply_cache_shutdown(struct nfsd_net *nn) * not already scheduled. */ static void -lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) +lru_put_end(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp) { rp->c_timestamp = jiffies; list_move_tail(&rp->c_lru, &b->lru_head); @@ -247,12 +275,21 @@ nfsd_cache_bucket_find(__be32 xid, struct nfsd_net *nn) return &nn->drc_hashtbl[hash]; } -static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn, - unsigned int max) +/* + * Remove and return no more than @max expired entries in bucket @b. + * If @max is zero, do not limit the number of removed entries. + */ +static void +nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, + unsigned int max, struct list_head *dispose) { - struct svc_cacherep *rp, *tmp; - long freed = 0; + unsigned long expiry = jiffies - RC_EXPIRE; + struct nfsd_cacherep *rp, *tmp; + unsigned int freed = 0; + + lockdep_assert_held(&b->cache_lock); + /* The bucket LRU is ordered oldest-first. */ list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) { /* * Don't free entries attached to calls that are still @@ -260,60 +297,77 @@ static long prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn, */ if (rp->c_state == RC_INPROG) continue; + if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries && - time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) + time_before(expiry, rp->c_timestamp)) break; - nfsd_reply_cache_free_locked(b, rp, nn); - if (max && freed++ > max) + + nfsd_cacherep_unlink_locked(nn, b, rp); + list_add(&rp->c_lru, dispose); + + if (max && ++freed > max) break; } - return freed; } -static long nfsd_prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) +/** + * nfsd_reply_cache_count - count_objects method for the DRC shrinker + * @shrink: our registered shrinker context + * @sc: garbage collection parameters + * + * Returns the total number of entries in the duplicate reply cache. To + * keep things simple and quick, this is not the number of expired entries + * in the cache (ie, the number that would be removed by a call to + * nfsd_reply_cache_scan). + */ +static unsigned long +nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - return prune_bucket(b, nn, 3); + struct nfsd_net *nn = container_of(shrink, + struct nfsd_net, nfsd_reply_cache_shrinker); + + return atomic_read(&nn->num_drc_entries); } -/* - * Walk the LRU list and prune off entries that are older than RC_EXPIRE. - * Also prune the oldest ones when the total exceeds the max number of entries. +/** + * nfsd_reply_cache_scan - scan_objects method for the DRC shrinker + * @shrink: our registered shrinker context + * @sc: garbage collection parameters + * + * Free expired entries on each bucket's LRU list until we've released + * nr_to_scan freed objects. Nothing will be released if the cache + * has not exceeded it's max_drc_entries limit. + * + * Returns the number of entries released by this call. */ -static long -prune_cache_entries(struct nfsd_net *nn) +static unsigned long +nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { + struct nfsd_net *nn = container_of(shrink, + struct nfsd_net, nfsd_reply_cache_shrinker); + unsigned long freed = 0; + LIST_HEAD(dispose); unsigned int i; - long freed = 0; for (i = 0; i < nn->drc_hashsize; i++) { struct nfsd_drc_bucket *b = &nn->drc_hashtbl[i]; if (list_empty(&b->lru_head)) continue; + spin_lock(&b->cache_lock); - freed += prune_bucket(b, nn, 0); + nfsd_prune_bucket_locked(nn, b, 0, &dispose); spin_unlock(&b->cache_lock); - } - return freed; -} -static unsigned long -nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) -{ - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_reply_cache_shrinker); + freed += nfsd_cacherep_dispose(&dispose); + if (freed > sc->nr_to_scan) + break; + } - return atomic_read(&nn->num_drc_entries); + trace_nfsd_drc_gc(nn, freed); + return freed; } -static unsigned long -nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) -{ - struct nfsd_net *nn = container_of(shrink, - struct nfsd_net, nfsd_reply_cache_shrinker); - - return prune_cache_entries(nn); -} /* * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes */ @@ -348,8 +402,8 @@ nfsd_cache_csum(struct svc_rqst *rqstp) } static int -nfsd_cache_key_cmp(const struct svc_cacherep *key, - const struct svc_cacherep *rp, struct nfsd_net *nn) +nfsd_cache_key_cmp(const struct nfsd_cacherep *key, + const struct nfsd_cacherep *rp, struct nfsd_net *nn) { if (key->c_key.k_xid == rp->c_key.k_xid && key->c_key.k_csum != rp->c_key.k_csum) { @@ -365,11 +419,11 @@ nfsd_cache_key_cmp(const struct svc_cacherep *key, * Must be called with cache_lock held. Returns the found entry or * inserts an empty key on failure. */ -static struct svc_cacherep * -nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key, +static struct nfsd_cacherep * +nfsd_cache_insert(struct nfsd_drc_bucket *b, struct nfsd_cacherep *key, struct nfsd_net *nn) { - struct svc_cacherep *rp, *ret = key; + struct nfsd_cacherep *rp, *ret = key; struct rb_node **p = &b->rb_head.rb_node, *parent = NULL; unsigned int entries = 0; @@ -378,7 +432,7 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key, while (*p != NULL) { ++entries; parent = *p; - rp = rb_entry(parent, struct svc_cacherep, c_node); + rp = rb_entry(parent, struct nfsd_cacherep, c_node); cmp = nfsd_cache_key_cmp(key, rp, nn); if (cmp < 0) @@ -411,6 +465,7 @@ out: /** * nfsd_cache_lookup - Find an entry in the duplicate reply cache * @rqstp: Incoming Call to find + * @cacherep: OUT: DRC entry for this request * * Try to find an entry matching the current call in the cache. When none * is found, we try to grab the oldest expired entry off the LRU list. If @@ -423,16 +478,17 @@ out: * %RC_REPLY: Reply from cache * %RC_DROPIT: Do not process the request further */ -int nfsd_cache_lookup(struct svc_rqst *rqstp) +int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep) { struct nfsd_net *nn; - struct svc_cacherep *rp, *found; + struct nfsd_cacherep *rp, *found; __wsum csum; struct nfsd_drc_bucket *b; int type = rqstp->rq_cachetype; + unsigned long freed; + LIST_HEAD(dispose); int rtn = RC_DOIT; - rqstp->rq_cacherep = NULL; if (type == RC_NOCACHE) { nfsd_stats_rc_nocache_inc(); goto out; @@ -445,7 +501,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) * preallocate an entry. */ nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - rp = nfsd_reply_cache_alloc(rqstp, csum, nn); + rp = nfsd_cacherep_alloc(rqstp, csum, nn); if (!rp) goto out; @@ -454,20 +510,18 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp) found = nfsd_cache_insert(b, rp, nn); if (found != rp) goto found_entry; - - nfsd_stats_rc_misses_inc(); - rqstp->rq_cacherep = rp; + *cacherep = rp; rp->c_state = RC_INPROG; + nfsd_prune_bucket_locked(nn, b, 3, &dispose); + spin_unlock(&b->cache_lock); + freed = nfsd_cacherep_dispose(&dispose); + trace_nfsd_drc_gc(nn, freed); + + nfsd_stats_rc_misses_inc(); atomic_inc(&nn->num_drc_entries); nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp)); - - nfsd_prune_bucket(b, nn); - -out_unlock: - spin_unlock(&b->cache_lock); -out: - return rtn; + goto out; found_entry: /* We found a matching entry which is either in progress or done. */ @@ -505,12 +559,16 @@ found_entry: out_trace: trace_nfsd_drc_found(nn, rqstp, rtn); - goto out_unlock; +out_unlock: + spin_unlock(&b->cache_lock); +out: + return rtn; } /** * nfsd_cache_update - Update an entry in the duplicate reply cache. * @rqstp: svc_rqst with a finished Reply + * @rp: IN: DRC entry for this request * @cachetype: which cache to update * @statp: pointer to Reply's NFS status code, or NULL * @@ -528,10 +586,10 @@ out_trace: * nfsd failed to encode a reply that otherwise would have been cached. * In this case, nfsd_cache_update is called with statp == NULL. */ -void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) +void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, + int cachetype, __be32 *statp) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - struct svc_cacherep *rp = rqstp->rq_cacherep; struct kvec *resv = &rqstp->rq_res.head[0], *cachv; struct nfsd_drc_bucket *b; int len; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3709830f90a6..7ed02fb88a36 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1627,6 +1627,7 @@ static void __exit exit_nfsd(void) } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); +MODULE_DESCRIPTION("In-kernel NFS server"); MODULE_LICENSE("GPL"); module_init(init_nfsd) module_exit(exit_nfsd) diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index d88498f8b275..11c14faa6c67 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -96,7 +96,12 @@ int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_shutdown_threads(struct net *net); -void nfsd_put(struct net *net); +static inline void nfsd_put(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + svc_put(nn->nfsd_serv); +} bool i_am_nfsd(void); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c291389a1d71..355bf0db3235 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -614,7 +614,7 @@ out_negative: * @fhp: file handle to be updated * */ -void fh_fill_pre_attrs(struct svc_fh *fhp) +__be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp) { bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); struct inode *inode; @@ -622,12 +622,12 @@ void fh_fill_pre_attrs(struct svc_fh *fhp) __be32 err; if (fhp->fh_no_wcc || fhp->fh_pre_saved) - return; + return nfs_ok; inode = d_inode(fhp->fh_dentry); err = fh_getattr(fhp, &stat); if (err) - return; + return err; if (v4) fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); @@ -636,6 +636,7 @@ void fh_fill_pre_attrs(struct svc_fh *fhp) fhp->fh_pre_ctime = stat.ctime; fhp->fh_pre_size = stat.size; fhp->fh_pre_saved = true; + return nfs_ok; } /** @@ -643,26 +644,27 @@ void fh_fill_pre_attrs(struct svc_fh *fhp) * @fhp: file handle to be updated * */ -void fh_fill_post_attrs(struct svc_fh *fhp) +__be32 fh_fill_post_attrs(struct svc_fh *fhp) { bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE); struct inode *inode = d_inode(fhp->fh_dentry); __be32 err; if (fhp->fh_no_wcc) - return; + return nfs_ok; if (fhp->fh_post_saved) printk("nfsd: inode locked twice during operation.\n"); err = fh_getattr(fhp, &fhp->fh_post_attr); if (err) - return; + return err; fhp->fh_post_saved = true; if (v4) fhp->fh_post_change = nfsd4_change_attribute(&fhp->fh_post_attr, inode); + return nfs_ok; } /** @@ -672,16 +674,20 @@ void fh_fill_post_attrs(struct svc_fh *fhp) * This is used when the directory wasn't changed, but wcc attributes * are needed anyway. */ -void fh_fill_both_attrs(struct svc_fh *fhp) +__be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp) { - fh_fill_post_attrs(fhp); - if (!fhp->fh_post_saved) - return; + __be32 err; + + err = fh_fill_post_attrs(fhp); + if (err) + return err; + fhp->fh_pre_change = fhp->fh_post_change; fhp->fh_pre_mtime = fhp->fh_post_attr.mtime; fhp->fh_pre_ctime = fhp->fh_post_attr.ctime; fhp->fh_pre_size = fhp->fh_post_attr.size; fhp->fh_pre_saved = true; + return nfs_ok; } /* diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 4e0ecf0ae2cf..40426f899e76 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -294,7 +294,7 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp) } u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode); -extern void fh_fill_pre_attrs(struct svc_fh *fhp); -extern void fh_fill_post_attrs(struct svc_fh *fhp); -extern void fh_fill_both_attrs(struct svc_fh *fhp); +__be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp); +__be32 fh_fill_post_attrs(struct svc_fh *fhp); +__be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp); #endif /* _LINUX_NFSD_NFSFH_H */ diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 2154fa63c5f2..1582af33e204 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -542,9 +542,14 @@ static struct notifier_block nfsd_inet6addr_notifier = { /* Only used under nfsd_mutex, so this atomic may be overkill: */ static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0); -static void nfsd_last_thread(struct svc_serv *serv, struct net *net) +static void nfsd_last_thread(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv = nn->nfsd_serv; + + spin_lock(&nfsd_notifier_lock); + nn->nfsd_serv = NULL; + spin_unlock(&nfsd_notifier_lock); /* check if the notifier still has clients */ if (atomic_dec_return(&nfsd_notifier_refcount) == 0) { @@ -554,6 +559,8 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) #endif } + svc_xprt_destroy_all(serv, net); + /* * write_ports can create the server without actually starting * any threads--if we get shut down before any threads are @@ -644,7 +651,8 @@ void nfsd_shutdown_threads(struct net *net) svc_get(serv); /* Kill outstanding nfsd threads */ svc_set_num_threads(serv, NULL, 0); - nfsd_put(net); + nfsd_last_thread(net); + svc_put(serv); mutex_unlock(&nfsd_mutex); } @@ -674,9 +682,6 @@ int nfsd_create_serv(struct net *net) serv->sv_maxconn = nn->max_connections; error = svc_bind(serv, net); if (error < 0) { - /* NOT nfsd_put() as notifiers (see below) haven't - * been set up yet. - */ svc_put(serv); return error; } @@ -719,29 +724,6 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) return 0; } -/* This is the callback for kref_put() below. - * There is no code here as the first thing to be done is - * call svc_shutdown_net(), but we cannot get the 'net' from - * the kref. So do all the work when kref_put returns true. - */ -static void nfsd_noop(struct kref *ref) -{ -} - -void nfsd_put(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - if (kref_put(&nn->nfsd_serv->sv_refcnt, nfsd_noop)) { - svc_xprt_destroy_all(nn->nfsd_serv, net); - nfsd_last_thread(nn->nfsd_serv, net); - svc_destroy(&nn->nfsd_serv->sv_refcnt); - spin_lock(&nfsd_notifier_lock); - nn->nfsd_serv = NULL; - spin_unlock(&nfsd_notifier_lock); - } -} - int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) { int i = 0; @@ -792,7 +774,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) if (err) break; } - nfsd_put(net); + svc_put(nn->nfsd_serv); return err; } @@ -807,6 +789,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) int error; bool nfsd_up_before; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct svc_serv *serv; mutex_lock(&nfsd_mutex); dprintk("nfsd: creating service\n"); @@ -826,22 +809,25 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) goto out; nfsd_up_before = nn->nfsd_net_up; + serv = nn->nfsd_serv; error = nfsd_startup_net(net, cred); if (error) goto out_put; - error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs); + error = svc_set_num_threads(serv, NULL, nrservs); if (error) goto out_shutdown; - error = nn->nfsd_serv->sv_nrthreads; + error = serv->sv_nrthreads; + if (error == 0) + nfsd_last_thread(net); out_shutdown: if (error < 0 && !nfsd_up_before) nfsd_shutdown_net(net); out_put: /* Threads now hold service active */ if (xchg(&nn->keep_active, 0)) - nfsd_put(net); - nfsd_put(net); + svc_put(serv); + svc_put(serv); out: mutex_unlock(&nfsd_mutex); return error; @@ -953,7 +939,6 @@ nfsd(void *vrqstp) struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list); struct net *net = perm_sock->xpt_net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - int err; /* At this point, the thread shares current->fs * with the init process. We need to create files with the @@ -965,15 +950,6 @@ nfsd(void *vrqstp) current->fs->umask = 0; - /* - * thread is spawned with all signals set to SIG_IGN, re-enable - * the ones that will bring down the thread - */ - allow_signal(SIGKILL); - allow_signal(SIGHUP); - allow_signal(SIGINT); - allow_signal(SIGQUIT); - atomic_inc(&nfsdstats.th_cnt); set_freezable(); @@ -981,54 +957,19 @@ nfsd(void *vrqstp) /* * The main request loop */ - for (;;) { + while (!kthread_should_stop()) { /* Update sv_maxconn if it has changed */ rqstp->rq_server->sv_maxconn = nn->max_connections; - /* - * Find a socket with data available and call its - * recvfrom routine. - */ - while ((err = svc_recv(rqstp, 60*60*HZ)) == -EAGAIN) - ; - if (err == -EINTR) - break; - validate_process_creds(); - svc_process(rqstp); + svc_recv(rqstp); validate_process_creds(); } - /* Clear signals before calling svc_exit_thread() */ - flush_signals(current); - atomic_dec(&nfsdstats.th_cnt); out: - /* Take an extra ref so that the svc_put in svc_exit_thread() - * doesn't call svc_destroy() - */ - svc_get(nn->nfsd_serv); - /* Release the thread */ svc_exit_thread(rqstp); - - /* We need to drop a ref, but may not drop the last reference - * without holding nfsd_mutex, and we cannot wait for nfsd_mutex as that - * could deadlock with nfsd_shutdown_threads() waiting for us. - * So three options are: - * - drop a non-final reference, - * - get the mutex without waiting - * - sleep briefly andd try the above again - */ - while (!svc_put_not_last(nn->nfsd_serv)) { - if (mutex_trylock(&nfsd_mutex)) { - nfsd_put(net); - mutex_unlock(&nfsd_mutex); - break; - } - msleep(20); - } - return 0; } @@ -1046,6 +987,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp) { const struct svc_procedure *proc = rqstp->rq_procinfo; __be32 *statp = rqstp->rq_accept_statp; + struct nfsd_cacherep *rp; /* * Give the xdr decoder a chance to change this if it wants @@ -1056,7 +998,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp) if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; - switch (nfsd_cache_lookup(rqstp)) { + rp = NULL; + switch (nfsd_cache_lookup(rqstp, &rp)) { case RC_DOIT: break; case RC_REPLY: @@ -1072,7 +1015,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp) if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; - nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1); + nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1); out_cached_reply: return 1; @@ -1082,13 +1025,13 @@ out_decode_err: return 1; out_update_drop: - nfsd_cache_update(rqstp, RC_NOCACHE, NULL); + nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); out_dropit: return 0; out_encode_err: trace_nfsd_cant_encode_err(rqstp); - nfsd_cache_update(rqstp, RC_NOCACHE, NULL); + nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); *statp = rpc_system_err; return 1; } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index d49d3060ed4f..cbddcf484dba 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -732,4 +732,7 @@ static inline bool try_to_expire_client(struct nfs4_client *clp) cmpxchg(&clp->cl_state, NFSD4_COURTESY, NFSD4_EXPIRABLE); return clp->cl_state == NFSD4_EXPIRABLE; } + +extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, + struct inode *inode); #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c index 777e24e5da33..63797635e1c3 100644 --- a/fs/nfsd/stats.c +++ b/fs/nfsd/stats.c @@ -65,6 +65,8 @@ static int nfsd_show(struct seq_file *seq, void *v) seq_printf(seq, " %lld", percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_NFS4_OP(i)])); } + seq_printf(seq, "\nwdeleg_getattr %lld", + percpu_counter_sum_positive(&nfsdstats.counter[NFSD_STATS_WDELEG_GETATTR])); seq_putc(seq, '\n'); #endif diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h index 9b43dc3d9991..cf5524e7ca06 100644 --- a/fs/nfsd/stats.h +++ b/fs/nfsd/stats.h @@ -22,6 +22,7 @@ enum { NFSD_STATS_FIRST_NFS4_OP, /* count of individual nfsv4 operations */ NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP, #define NFSD_STATS_NFS4_OP(op) (NFSD_STATS_FIRST_NFS4_OP + (op)) + NFSD_STATS_WDELEG_GETATTR, /* count of getattr conflict with wdeleg */ #endif NFSD_STATS_COUNTERS_NUM }; @@ -93,4 +94,10 @@ static inline void nfsd_stats_drc_mem_usage_sub(struct nfsd_net *nn, s64 amount) percpu_counter_sub(&nn->counter[NFSD_NET_DRC_MEM_USAGE], amount); } +#ifdef CONFIG_NFSD_V4 +static inline void nfsd_stats_wdeleg_getattr_inc(void) +{ + percpu_counter_inc(&nfsdstats.counter[NFSD_STATS_WDELEG_GETATTR]); +} +#endif #endif /* _NFSD_STATS_H */ diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 2af74983f146..803904348871 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -607,6 +607,7 @@ DEFINE_STATEID_EVENT(layout_recall_release); DEFINE_STATEID_EVENT(open); DEFINE_STATEID_EVENT(deleg_read); +DEFINE_STATEID_EVENT(deleg_write); DEFINE_STATEID_EVENT(deleg_return); DEFINE_STATEID_EVENT(deleg_recall); @@ -1240,8 +1241,8 @@ TRACE_EVENT(nfsd_drc_found, TRACE_EVENT(nfsd_drc_mismatch, TP_PROTO( const struct nfsd_net *nn, - const struct svc_cacherep *key, - const struct svc_cacherep *rp + const struct nfsd_cacherep *key, + const struct nfsd_cacherep *rp ), TP_ARGS(nn, key, rp), TP_STRUCT__entry( @@ -1261,6 +1262,28 @@ TRACE_EVENT(nfsd_drc_mismatch, __entry->ingress) ); +TRACE_EVENT_CONDITION(nfsd_drc_gc, + TP_PROTO( + const struct nfsd_net *nn, + unsigned long freed + ), + TP_ARGS(nn, freed), + TP_CONDITION(freed > 0), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(unsigned long, freed) + __field(int, total) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->freed = freed; + __entry->total = atomic_read(&nn->num_drc_entries); + ), + TP_printk("boot_time=%16llx total=%d freed=%lu", + __entry->boot_time, __entry->total, __entry->freed + ) +); + TRACE_EVENT(nfsd_cb_args, TP_PROTO( const struct nfs4_client *clp, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9b7acba382fe..48260cf68fde 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1540,7 +1540,9 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, dput(dchild); if (err) goto out_unlock; - fh_fill_pre_attrs(fhp); + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; err = nfsd_create_locked(rqstp, fhp, attrs, type, rdev, resfhp); fh_fill_post_attrs(fhp); out_unlock: @@ -1635,13 +1637,16 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, inode_unlock(dentry->d_inode); goto out_drop_write; } - fh_fill_pre_attrs(fhp); + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; host_err = vfs_symlink(&nop_mnt_idmap, d_inode(dentry), dnew, path); err = nfserrno(host_err); cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); if (!err) nfsd_create_setattr(rqstp, fhp, resfhp, attrs); fh_fill_post_attrs(fhp); +out_unlock: inode_unlock(dentry->d_inode); if (!err) err = nfserrno(commit_metadata(fhp)); @@ -1703,7 +1708,9 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, err = nfserr_noent; if (d_really_is_negative(dold)) goto out_dput; - fh_fill_pre_attrs(ffhp); + err = fh_fill_pre_attrs(ffhp); + if (err != nfs_ok) + goto out_dput; host_err = vfs_link(dold, &nop_mnt_idmap, dirp, dnew, NULL); fh_fill_post_attrs(ffhp); inode_unlock(dirp); @@ -1789,8 +1796,12 @@ retry: } trap = lock_rename(tdentry, fdentry); - fh_fill_pre_attrs(ffhp); - fh_fill_pre_attrs(tfhp); + err = fh_fill_pre_attrs(ffhp); + if (err != nfs_ok) + goto out_unlock; + err = fh_fill_pre_attrs(tfhp); + if (err != nfs_ok) + goto out_unlock; odentry = lookup_one_len(fname, fdentry, flen); host_err = PTR_ERR(odentry); @@ -1857,6 +1868,7 @@ retry: fh_fill_post_attrs(ffhp); fh_fill_post_attrs(tfhp); } +out_unlock: unlock_rename(tdentry, fdentry); fh_drop_write(ffhp); @@ -1916,12 +1928,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, goto out_unlock; } rinode = d_inode(rdentry); - ihold(rinode); + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; + ihold(rinode); if (!type) type = d_inode(rdentry)->i_mode & S_IFMT; - fh_fill_pre_attrs(fhp); if (type != S_IFDIR) { int retries; @@ -2341,16 +2355,18 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) return nfserrno(ret); inode_lock(fhp->fh_dentry->d_inode); - fh_fill_pre_attrs(fhp); - + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; ret = __vfs_removexattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, NULL); - + err = nfsd_xattr_errno(ret); fh_fill_post_attrs(fhp); +out_unlock: inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); - return nfsd_xattr_errno(ret); + return err; } __be32 @@ -2368,15 +2384,17 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, if (ret) return nfserrno(ret); inode_lock(fhp->fh_dentry->d_inode); - fh_fill_pre_attrs(fhp); - - ret = __vfs_setxattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, buf, - len, flags, NULL); + err = fh_fill_pre_attrs(fhp); + if (err != nfs_ok) + goto out_unlock; + ret = __vfs_setxattr_locked(&nop_mnt_idmap, fhp->fh_dentry, + name, buf, len, flags, NULL); fh_fill_post_attrs(fhp); + err = nfsd_xattr_errno(ret); +out_unlock: inode_unlock(fhp->fh_dentry->d_inode); fh_drop_write(fhp); - - return nfsd_xattr_errno(ret); + return err; } #endif diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 510978e602da..9d918a79dc16 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -774,17 +774,6 @@ void warn_on_nonidempotent_op(struct nfsd4_op *op); #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) -static inline void -set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) -{ - BUG_ON(!fhp->fh_pre_saved); - cinfo->atomic = (u32)(fhp->fh_post_saved && !fhp->fh_no_atomic_attr); - - cinfo->before_change = fhp->fh_pre_change; - cinfo->after_change = fhp->fh_post_change; -} - - bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr); |