Merge tag 'nfsd-4.16' of git://linux-nfs.org/~bfields/linux

Pull nfsd update from Bruce Fields:
 "A fairly small update this time around. Some cleanup, RDMA fixes,
  overlayfs fixes, and a fix for an NFSv4 state bug.

  The bigger deal for nfsd this time around was Jeff Layton's
  already-merged i_version patches"

* tag 'nfsd-4.16' of git://linux-nfs.org/~bfields/linux:
  svcrdma: Fix Read chunk round-up
  NFSD: hide unused svcxdr_dupstr()
  nfsd: store stat times in fill_pre_wcc() instead of inode times
  nfsd: encode stat->mtime for getattr instead of inode->i_mtime
  nfsd: return RESOURCE not GARBAGE_ARGS on too many ops
  nfsd4: don't set lock stateid's sc_type to CLOSED
  nfsd: Detect unhashed stids in nfsd4_verify_open_stid()
  sunrpc: remove dead code in svc_sock_setbufsize
  svcrdma: Post Receives in the Receive completion handler
  nfsd4: permit layoutget of executable-only files
  lockd: convert nlm_rqst.a_count from atomic_t to refcount_t
  lockd: convert nlm_lockowner.count from atomic_t to refcount_t
  lockd: convert nsm_handle.sm_count from atomic_t to refcount_t

fs/locks.c

@@ -1554,9 +1554,9 @@ out:
 EXPORT_SYMBOL(__break_lease);
 
 /**
- *	lease_get_mtime - get the last modified time of an inode
+ *	lease_get_mtime - update modified time of an inode with exclusive lease
  *	@inode: the inode
- *      @time:  pointer to a timespec which will contain the last modified time
+ *      @time:  pointer to a timespec which contains the last modified time
  *
  * This is to force NFS clients to flush their caches for files with
  * exclusive leases.  The justification is that if someone has an
@@ -1580,8 +1580,6 @@ void lease_get_mtime(struct inode *inode, struct timespec *time)
 
 	if (has_lease)
 		*time = current_time(inode);
-	else
-		*time = inode->i_mtime;
 }
 
 EXPORT_SYMBOL(lease_get_mtime);

fs/nfsd/nfs3xdr.c

@@ -250,6 +250,34 @@ encode_wcc_data(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
 	return encode_post_op_attr(rqstp, p, fhp);
 }
 
+/*
+ * Fill in the pre_op attr for the wcc data
+ */
+void fill_pre_wcc(struct svc_fh *fhp)
+{
+	struct inode    *inode;
+	struct kstat	stat;
+	__be32 err;
+
+	if (fhp->fh_pre_saved)
+		return;
+
+	inode = d_inode(fhp->fh_dentry);
+	err = fh_getattr(fhp, &stat);
+	if (err) {
+		/* Grab the times from inode anyway */
+		stat.mtime = inode->i_mtime;
+		stat.ctime = inode->i_ctime;
+		stat.size  = inode->i_size;
+	}
+
+	fhp->fh_pre_mtime = stat.mtime;
+	fhp->fh_pre_ctime = stat.ctime;
+	fhp->fh_pre_size  = stat.size;
+	fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
+	fhp->fh_pre_saved = true;
+}
+
 /*
  * Fill in the post_op attr for the wcc data
  */
@@ -261,7 +289,8 @@ void fill_post_wcc(struct svc_fh *fhp)
 		printk("nfsd: inode locked twice during operation.\n");
 
 	err = fh_getattr(fhp, &fhp->fh_post_attr);
-	fhp->fh_post_change = nfsd4_change_attribute(d_inode(fhp->fh_dentry));
+	fhp->fh_post_change = nfsd4_change_attribute(&fhp->fh_post_attr,
+						     d_inode(fhp->fh_dentry));
 	if (err) {
 		fhp->fh_post_saved = false;
 		/* Grab the ctime anyway - set_change_info might use it */

fs/nfsd/nfs4proc.c

@@ -1363,14 +1363,14 @@ nfsd4_layoutget(struct svc_rqst *rqstp,
 	const struct nfsd4_layout_ops *ops;
 	struct nfs4_layout_stateid *ls;
 	__be32 nfserr;
-	int accmode;
+	int accmode = NFSD_MAY_READ_IF_EXEC;
 
 	switch (lgp->lg_seg.iomode) {
 	case IOMODE_READ:
-		accmode = NFSD_MAY_READ;
+		accmode |= NFSD_MAY_READ;
 		break;
 	case IOMODE_RW:
-		accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
+		accmode |= NFSD_MAY_READ | NFSD_MAY_WRITE;
 		break;
 	default:
 		dprintk("%s: invalid iomode %d\n",
@@ -1703,6 +1703,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
 	status = nfserr_minor_vers_mismatch;
 	if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0)
 		goto out;
+	status = nfserr_resource;
+	if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND)
+		goto out;
 
 	status = nfs41_check_op_ordering(args);
 	if (status) {

fs/nfsd/nfs4state.c

@@ -3590,6 +3590,7 @@ nfsd4_verify_open_stid(struct nfs4_stid *s)
 	switch (s->sc_type) {
 	default:
 		break;
+	case 0:
 	case NFS4_CLOSED_STID:
 	case NFS4_CLOSED_DELEG_STID:
 		ret = nfserr_bad_stateid;
@@ -5182,7 +5183,6 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
 			    lockowner(stp->st_stateowner)))
 		goto out;
 
-	stp->st_stid.sc_type = NFS4_CLOSED_STID;
 	release_lock_stateid(stp);
 	ret = nfs_ok;
 
@@ -6078,10 +6078,8 @@ out:
 		 * If this is a new, never-before-used stateid, and we are
 		 * returning an error, then just go ahead and release it.
 		 */
-		if (status && new) {
-			lock_stp->st_stid.sc_type = NFS4_CLOSED_STID;
+		if (status && new)
 			release_lock_stateid(lock_stp);
-		}
 
 		mutex_unlock(&lock_stp->st_mutex);
 

fs/nfsd/nfs4xdr.c

@@ -455,8 +455,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 	}
 
 	label->len = 0;
-#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-	if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
+	if (IS_ENABLED(CONFIG_NFSD_V4_SECURITY_LABEL) &&
+	    bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
 		READ_BUF(4);
 		len += 4;
 		dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */
@@ -476,7 +476,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		if (!label->data)
 			return nfserr_jukebox;
 	}
-#endif
 	if (bmval[2] & FATTR4_WORD2_MODE_UMASK) {
 		if (!umask)
 			goto xdr_error;
@@ -1918,8 +1917,13 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 
 	if (argp->taglen > NFSD4_MAX_TAGLEN)
 		goto xdr_error;
-	if (argp->opcnt > 100)
-		goto xdr_error;
+	/*
+	 * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS
+	 * here, so we return success at the xdr level so that
+	 * nfsd4_proc can handle this is an NFS-level error.
+	 */
+	if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND)
+		return 0;
 
 	if (argp->opcnt > ARRAY_SIZE(argp->iops)) {
 		argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL);
@@ -1991,7 +1995,7 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode,
 		*p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time));
 		*p++ = 0;
 	} else if (IS_I_VERSION(inode)) {
-		p = xdr_encode_hyper(p, nfsd4_change_attribute(inode));
+		p = xdr_encode_hyper(p, nfsd4_change_attribute(stat, inode));
 	} else {
 		*p++ = cpu_to_be32(stat->ctime.tv_sec);
 		*p++ = cpu_to_be32(stat->ctime.tv_nsec);

fs/nfsd/nfsfh.h

@@ -253,36 +253,20 @@ fh_clear_wcc(struct svc_fh *fhp)
  * By using both ctime and the i_version counter we guarantee that as
  * long as time doesn't go backwards we never reuse an old value.
  */
-static inline u64 nfsd4_change_attribute(struct inode *inode)
+static inline u64 nfsd4_change_attribute(struct kstat *stat,
+					 struct inode *inode)
 {
 	u64 chattr;
 
-	chattr =  inode->i_ctime.tv_sec;
+	chattr =  stat->ctime.tv_sec;
 	chattr <<= 30;
-	chattr += inode->i_ctime.tv_nsec;
+	chattr += stat->ctime.tv_nsec;
 	chattr += inode_query_iversion(inode);
 	return chattr;
 }
 
-/*
- * Fill in the pre_op attr for the wcc data
- */
-static inline void
-fill_pre_wcc(struct svc_fh *fhp)
-{
-	struct inode    *inode;
-
-	inode = d_inode(fhp->fh_dentry);
-	if (!fhp->fh_pre_saved) {
-		fhp->fh_pre_mtime = inode->i_mtime;
-		fhp->fh_pre_ctime = inode->i_ctime;
-		fhp->fh_pre_size  = inode->i_size;
-		fhp->fh_pre_change = nfsd4_change_attribute(inode);
-		fhp->fh_pre_saved = true;
-	}
-}
-
-extern void fill_post_wcc(struct svc_fh *);
+extern void fill_pre_wcc(struct svc_fh *fhp);
+extern void fill_post_wcc(struct svc_fh *fhp);
 #else
 #define fh_clear_wcc(ignored)
 #define fill_pre_wcc(ignored)

fs/nfsd/nfsxdr.c

@@ -188,6 +188,7 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
 	*p++ = htonl((u32) stat->ino);
 	*p++ = htonl((u32) stat->atime.tv_sec);
 	*p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
+	time = stat->mtime;
 	lease_get_mtime(d_inode(dentry), &time); 
 	*p++ = htonl((u32) time.tv_sec);
 	*p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0); 

include/linux/sunrpc/svc_rdma.h

@@ -185,8 +185,6 @@ extern void svc_rdma_wc_reg(struct ib_cq *, struct ib_wc *);
 extern void svc_rdma_wc_read(struct ib_cq *, struct ib_wc *);
 extern void svc_rdma_wc_inv(struct ib_cq *, struct ib_wc *);
 extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *);
-extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t);
-extern int svc_rdma_repost_recv(struct svcxprt_rdma *, gfp_t);
 extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
 extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
 extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);

net/sunrpc/svcsock.c

@@ -384,25 +384,11 @@ static int svc_partial_recvfrom(struct svc_rqst *rqstp,
 static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 				unsigned int rcv)
 {
-#if 0
-	mm_segment_t	oldfs;
-	oldfs = get_fs(); set_fs(KERNEL_DS);
-	sock_setsockopt(sock, SOL_SOCKET, SO_SNDBUF,
-			(char*)&snd, sizeof(snd));
-	sock_setsockopt(sock, SOL_SOCKET, SO_RCVBUF,
-			(char*)&rcv, sizeof(rcv));
-#else
-	/* sock_setsockopt limits use to sysctl_?mem_max,
-	 * which isn't acceptable.  Until that is made conditional
-	 * on not having CAP_SYS_RESOURCE or similar, we go direct...
-	 * DaveM said I could!
-	 */
 	lock_sock(sock->sk);
 	sock->sk->sk_sndbuf = snd * 2;
 	sock->sk->sk_rcvbuf = rcv * 2;
 	sock->sk->sk_write_space(sock->sk);
 	release_sock(sock->sk);
-#endif
 }
 
 static int svc_sock_secure_port(struct svc_rqst *rqstp)

net/sunrpc/xprtrdma/svc_rdma_backchannel.c

@@ -95,7 +95,6 @@ out_shortreply:
 out_notfound:
 	dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n",
 		xprt, be32_to_cpu(xid));
-
 	goto out_unlock;
 }
 
@@ -129,10 +128,6 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 	if (ret < 0)
 		goto out_err;
 
-	ret = svc_rdma_repost_recv(rdma, GFP_NOIO);
-	if (ret)
-		goto out_err;
-
 	/* Bump page refcnt so Send completion doesn't release
 	 * the rq_buffer before all retransmits are complete.
 	 */

net/sunrpc/xprtrdma/svc_rdma_recvfrom.c

@@ -400,10 +400,6 @@ static void svc_rdma_send_error(struct svcxprt_rdma *xprt,
 	struct page *page;
 	int ret;
 
-	ret = svc_rdma_repost_recv(xprt, GFP_KERNEL);
-	if (ret)
-		return;
-
 	page = alloc_page(GFP_KERNEL);
 	if (!page)
 		return;
@@ -554,8 +550,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p,
 					       &rqstp->rq_arg);
 		svc_rdma_put_context(ctxt, 0);
-		if (ret)
-			goto repost;
 		return ret;
 	}
 
@@ -590,6 +584,5 @@ out_postfail:
 
 out_drop:
 	svc_rdma_put_context(ctxt, 1);
-repost:
-	return svc_rdma_repost_recv(rdma_xprt, GFP_KERNEL);
+	return 0;
 }

net/sunrpc/xprtrdma/svc_rdma_rw.c

@@ -727,12 +727,16 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
 		head->arg.head[0].iov_len - info->ri_position;
 	head->arg.head[0].iov_len = info->ri_position;
 
-	/* Read chunk may need XDR roundup (see RFC 5666, s. 3.7).
+	/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
 	 *
-	 * NFSv2/3 write decoders need the length of the tail to
-	 * contain the size of the roundup padding.
+	 * If the client already rounded up the chunk length, the
+	 * length does not change. Otherwise, the length of the page
+	 * list is increased to include XDR round-up.
+	 *
+	 * Currently these chunks always start at page offset 0,
+	 * thus the rounded-up length never crosses a page boundary.
 	 */
-	head->arg.tail[0].iov_len += 4 - (info->ri_chunklen & 3);
+	info->ri_chunklen = XDR_QUADLEN(info->ri_chunklen) << 2;
 
 	head->arg.page_len = info->ri_chunklen;
 	head->arg.len += info->ri_chunklen;

net/sunrpc/xprtrdma/svc_rdma_sendto.c

@@ -674,9 +674,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 		svc_rdma_xdr_encode_reply_chunk(rdma_resp, rp_ch, ret);
 	}
 
-	ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
-	if (ret)
-		goto err1;
 	ret = svc_rdma_send_reply_msg(rdma, rdma_argp, rdma_resp, rqstp,
 				      wr_lst, rp_ch);
 	if (ret < 0)
@@ -687,9 +684,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 	if (ret != -E2BIG && ret != -EINVAL)
 		goto err1;
 
-	ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
-	if (ret)
-		goto err1;
 	ret = svc_rdma_send_error_msg(rdma, rdma_resp, rqstp);
 	if (ret < 0)
 		goto err0;

net/sunrpc/xprtrdma/svc_rdma_transport.c

@@ -58,6 +58,7 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
+static int svc_rdma_post_recv(struct svcxprt_rdma *xprt);
 static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *, int);
 static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 					struct net *net,
@@ -320,6 +321,8 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	list_add_tail(&ctxt->list, &xprt->sc_rq_dto_q);
 	spin_unlock(&xprt->sc_rq_dto_lock);
 
+	svc_rdma_post_recv(xprt);
+
 	set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
 	if (test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags))
 		goto out;
@@ -404,7 +407,8 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 	return cma_xprt;
 }
 
-int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags)
+static int
+svc_rdma_post_recv(struct svcxprt_rdma *xprt)
 {
 	struct ib_recv_wr recv_wr, *bad_recv_wr;
 	struct svc_rdma_op_ctxt *ctxt;
@@ -423,7 +427,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags)
 			pr_err("svcrdma: Too many sges (%d)\n", sge_no);
 			goto err_put_ctxt;
 		}
-		page = alloc_page(flags);
+		page = alloc_page(GFP_KERNEL);
 		if (!page)
 			goto err_put_ctxt;
 		ctxt->pages[sge_no] = page;
@@ -459,21 +463,6 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags)
 	return -ENOMEM;
 }
 
-int svc_rdma_repost_recv(struct svcxprt_rdma *xprt, gfp_t flags)
-{
-	int ret = 0;
-
-	ret = svc_rdma_post_recv(xprt, flags);
-	if (ret) {
-		pr_err("svcrdma: could not post a receive buffer, err=%d.\n",
-		       ret);
-		pr_err("svcrdma: closing transport %p.\n", xprt);
-		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
-		ret = -ENOTCONN;
-	}
-	return ret;
-}
-
 static void
 svc_rdma_parse_connect_private(struct svcxprt_rdma *newxprt,
 			       struct rdma_conn_param *param)
@@ -833,7 +822,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 
 	/* Post receive buffers */
 	for (i = 0; i < newxprt->sc_max_requests; i++) {
-		ret = svc_rdma_post_recv(newxprt, GFP_KERNEL);
+		ret = svc_rdma_post_recv(newxprt);
 		if (ret) {
 			dprintk("svcrdma: failure posting receive buffers\n");
 			goto errout;