1 files changed, 217 insertions, 41 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 88c347957da5..6791fc239dbd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1222,6 +1222,42 @@ static void put_deleg_file(struct nfs4_file *fp)
 		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)
 {
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
@@ -1229,6 +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);
 }
@@ -1505,7 +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);
 }
 
@@ -3449,7 +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;
@@ -3865,6 +3916,7 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
 	ca->headerpadsz = 0;
 	ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc);
 	ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc);
+	ca->maxops = min_t(u32, ca->maxops, NFSD_MAX_OPS_PER_COMPOUND);
 	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);
@@ -4311,6 +4363,36 @@ 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)
@@ -4360,6 +4442,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	dprintk("%s: slotid %d\n", __func__, seq->slotid);
 
 	trace_nfsd_slot_seqid_sequence(clp, seq, slot);
+
+	nfsd4_construct_sequence_response(session, seq);
+
 	status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags);
 	if (status == nfserr_replay_cache) {
 		status = nfserr_seq_misordered;
@@ -4457,23 +4542,6 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 out:
-	seq->maxslots = 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;
 	trace_nfsd_seq4_status(rqstp, seq);
 out_no_session:
 	if (conn)
@@ -6157,7 +6225,8 @@ nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh,
 	path.dentry = file_dentry(nf->nf_file);
 
 	rc = vfs_getattr(&path, stat,
-			 (STATX_MODE | STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
+			 STATX_MODE | STATX_SIZE | STATX_ATIME |
+			 STATX_MTIME | STATX_CTIME | STATX_CHANGE_COOKIE,
 			 AT_STATX_SYNC_AS_STAT);
 
 	nfsd_file_put(nf);
@@ -6264,6 +6333,8 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open,
 	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) {
+		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);
@@ -6274,10 +6345,17 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open,
 						    OPEN_DELEGATE_WRITE;
 		dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
 		dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat);
+		dp->dl_atime = stat.atime;
+		dp->dl_ctime = stat.ctime;
+		dp->dl_mtime = stat.mtime;
+		spin_lock(&f->f_lock);
+		f->f_mode |= FMODE_NOCMTIME;
+		spin_unlock(&f->f_lock);
 		trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
 	} else {
-		open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG :
-						    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);
@@ -7781,7 +7859,8 @@ 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, SC_STATUS_REVOKED, &s, nn);
@@ -9130,25 +9209,25 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
 }
 
 /**
- * set_cb_time - vet and set the timespec for a cb_getattr update
- * @cb: timestamp from the CB_GETATTR response
+ * 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 in a CB_GETATTR response, check it against the
+ * 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.
- * @cb may also be changed if the timestamp needs to be clamped.
+ * @req may also be changed if the timestamp needs to be clamped.
  */
-static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig,
-			const struct timespec64 *now)
+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(cb, orig) <= 0)
+	if (timespec64_compare(req, orig) <= 0)
 		return false;
 
 	/*
@@ -9156,10 +9235,8 @@ static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig,
 	 *  clamp the new time to the current time, or it may
 	 *  return NFS4ERR_DELAY to the client, allowing it to retry."
 	 */
-	if (timespec64_compare(cb, now) > 0) {
-		/* clamp it */
-		*cb = *now;
-	}
+	if (timespec64_compare(req, now) > 0)
+		*req = *now;
 
 	return true;
 }
@@ -9167,28 +9244,27 @@ static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig,
 static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp)
 {
 	struct inode *inode = d_inode(dentry);
-	struct timespec64 now = current_time(inode);
 	struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr;
 	struct iattr attrs = { };
 	int ret;
 
 	if (deleg_attrs_deleg(dp->dl_type)) {
-		struct timespec64 atime = inode_get_atime(inode);
-		struct timespec64 mtime = inode_get_mtime(inode);
+		struct timespec64 now = current_time(inode);
 
 		attrs.ia_atime = ncf->ncf_cb_atime;
 		attrs.ia_mtime = ncf->ncf_cb_mtime;
 
-		if (set_cb_time(&attrs.ia_atime, &atime, &now))
+		if (nfsd4_vet_deleg_time(&attrs.ia_atime, &dp->dl_atime, &now))
 			attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET;
 
-		if (set_cb_time(&attrs.ia_mtime, &mtime, &now)) {
-			attrs.ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_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;
-		attrs.ia_mtime = attrs.ia_ctime = now;
 	}
 
 	if (!attrs.ia_valid)
@@ -9302,3 +9378,103 @@ 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);
+}