Merge tag 'nfs-for-7.2-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New features:
   - XPRTRDMA: Decouple req recycling from RPC completion
   - NFS: Expose FMODE_NOWAIT for read-only files

  Bugfixes:
   - SUNRPC:
      - Fix sunrpc sysfs error handling
      - Fix uninitialized xprt_create_args structure
   - XPRTRDMA:
      - Harden connect and reply handling
   - NFS:
      - Fix EOF updates after fallocate/zero-range
      - Keep PG_UPTODATE clear after read errors in page groups
      - Use nfsi->rwsem to protect traversal of the file lock list
      - Prevent resource leak in nfs_alloc_server()
   - NFSv4:
      - Clear exception state on successful mkdir retry
      - Don't skip revalidate when holding a dir delegation and attrs are stale
   - pNFS:
      - Fix use-after-free in pnfs_update_layout()
      - Defer return_range callbacks until after inode unlock
      - Fix LAYOUTCOMMIT retry loop on OLD_STATEID
      - Reject zero-length r_addr in nfs4_decode_mp_ds_addr
   - NFS/flexfiles:
      - Reject zero-length filehandle version arrays
      - Fix checking if a layout is striped
      - Fixes for honoring FF_FLAGS_NO_IO_THRU_MDS

  Other cleanups and improvements:
   - Remove the fileid field from struct nfs_inode
   - Move long-delayed xprtrdma work onto the system_dfl_long_wq
   - Convert xprtrdma send buffer free list to an llist
   - Show "<redacted>" for cert_serial and privkey_serial mount options"

* tag 'nfs-for-7.2-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (42 commits)
  NFS: Use common error handling code in nfs_alloc_server()
  NFS: Prevent resource leak in nfs_alloc_server()
  NFSv4/pNFS: reject zero-length r_addr in nfs4_decode_mp_ds_addr
  nfs: don't skip revalidate on directory delegation when attrs flagged stale
  xprtrdma: Return sendctx slot after Send preparation failure
  xprtrdma: Repost Receive buffers for malformed replies
  xprtrdma: Sanitize the reply credit grant after parsing
  xprtrdma: Fix bcall rep leak and unbounded peek
  xprtrdma: Resize reply buffers before reposting receives
  xprtrdma: Check frwr_wp_create() during connect
  xprtrdma: Initialize re_id before removal registration
  xprtrdma: Fix ep kref imbalance on ADDR_CHANGE
  xprtrdma: Convert send buffer free list to llist
  NFS: correct CONFIG_NFS_V4 macro name in #endif comment
  nfs: use nfsi->rwsem to protect traversal of the file lock list
  NFSv4.1/pNFS: fix LAYOUTCOMMIT retry loop on OLD_STATEID
  nfs: expose FMODE_NOWAIT for read-only files
  nfs: add nowait version of nfs_start_io_direct
  NFSv4/flexfiles: honor FF_FLAGS_NO_IO_THRU_MDS in pg_get_mirror_count_write
  NFSv4/flexfiles: honor FF_FLAGS_NO_IO_THRU_MDS on fatal DS connect errors
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -4288,13 +4288,6 @@ Kernel parameters
 			Only applies if the softerr mount option is enabled,
 			and the specified value is >= 0.
 
-	nfs.enable_ino64=
-			[NFS] enable 64-bit inode numbers.
-			If zero, the NFS client will fake up a 32-bit inode
-			number for the readdir() and stat() syscalls instead
-			of returning the full 64-bit number.
-			The default is to return 64-bit inode numbers.
-
 	nfs.idmap_cache_timeout=
 			[NFS] set the maximum lifetime for idmapper cache
 			entries.

fs/nfs/callback_proc.c

@@ -257,6 +257,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	struct pnfs_layout_hdr *lo;
 	u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
 	LIST_HEAD(free_me_list);
+	bool return_range = false;
 
 	ino = nfs_layout_find_inode(clp, &args->cbl_fh, &args->cbl_stateid);
 	if (IS_ERR(ino)) {
@@ -301,13 +302,13 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 		/* Embrace your forgetfulness! */
 		rv = NFS4ERR_NOMATCHING_LAYOUT;
 
-		if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
-			NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
-				&args->cbl_range);
-		}
+		return_range = true;
 	}
 unlock:
 	spin_unlock(&ino->i_lock);
+	if (return_range && NFS_SERVER(ino)->pnfs_curr_ld->return_range)
+		NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo,
+			&args->cbl_range);
 	pnfs_free_lseg_list(&free_me_list);
 	/* Free all lsegs that are attached to commit buckets */
 	nfs_commit_inode(ino, 0);

fs/nfs/client.c

@@ -1063,10 +1063,8 @@ struct nfs_server *nfs_alloc_server(void)
 		return NULL;
 
 	server->s_sysfs_id = ida_alloc(&s_sysfs_ids, GFP_KERNEL);
-	if (server->s_sysfs_id < 0) {
-		kfree(server);
-		return NULL;
-	}
+	if (server->s_sysfs_id < 0)
+		goto free_server;
 
 	server->client = server->client_acl = ERR_PTR(-EINVAL);
 
@@ -1088,8 +1086,8 @@ struct nfs_server *nfs_alloc_server(void)
 
 	server->io_stats = nfs_alloc_iostats();
 	if (!server->io_stats) {
-		kfree(server);
-		return NULL;
+		ida_free(&s_sysfs_ids, server->s_sysfs_id);
+		goto free_server;
 	}
 
 	server->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED;
@@ -1103,6 +1101,10 @@ struct nfs_server *nfs_alloc_server(void)
 	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 
 	return server;
+
+free_server:
+	kfree(server);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(nfs_alloc_server);
 

fs/nfs/delegation.c

@@ -173,6 +173,7 @@ int nfs4_check_delegation(struct inode *inode, fmode_t type)
 static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_stateid *stateid)
 {
 	struct inode *inode = state->inode;
+	struct nfs_inode *nfsi = NFS_I(inode);
 	struct file_lock *fl;
 	struct file_lock_context *flctx = locks_inode_context(inode);
 	struct list_head *list;
@@ -182,22 +183,28 @@ static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_state
 		goto out;
 
 	list = &flctx->flc_posix;
+
+	/* Guard against reclaim and new lock/unlock calls */
+	down_write(&nfsi->rwsem);
 	spin_lock(&flctx->flc_lock);
 restart:
 	for_each_file_lock(fl, list) {
 		if (nfs_file_open_context(fl->c.flc_file)->state != state)
 			continue;
 		spin_unlock(&flctx->flc_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
-		if (status < 0)
+		if (status < 0) {
+			up_write(&nfsi->rwsem);
 			goto out;
+		}
 		spin_lock(&flctx->flc_lock);
 	}
 	if (list == &flctx->flc_posix) {
 		list = &flctx->flc_flock;
 		goto restart;
 	}
 	spin_unlock(&flctx->flc_lock);
+	up_write(&nfsi->rwsem);
 out:
 	return status;
 }

fs/nfs/dir.c

@@ -650,7 +650,7 @@ int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 		return 0;
 
 	nfsi = NFS_I(inode);
-	if (entry->fattr->fileid != nfsi->fileid)
+	if (entry->fattr->fileid != inode->i_ino)
 		return 0;
 	if (entry->fh->size && nfs_compare_fh(entry->fh, &nfsi->fh) != 0)
 		return 0;
@@ -1105,7 +1105,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
 
 		ent = &array->array[i];
 		if (!dir_emit(desc->ctx, ent->name, ent->name_len,
-		    nfs_compat_user_ino64(ent->ino), ent->d_type)) {
+		    ent->ino, ent->d_type)) {
 			desc->eob = true;
 			break;
 		}
@@ -2301,7 +2301,7 @@ nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name,
 	return nfs_do_lookup_revalidate(dir, name, dentry, flags);
 }
 
-#endif /* CONFIG_NFSV4 */
+#endif /* CONFIG_NFS_V4 */
 
 int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
 			struct file *file, unsigned int open_flags,

fs/nfs/direct.c

@@ -466,14 +466,22 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 		goto out_release;
 	}
 	dreq->l_ctx = l_ctx;
-	if (!is_sync_kiocb(iocb))
+	if (!is_sync_kiocb(iocb)) {
 		dreq->iocb = iocb;
+	} else if (iocb->ki_flags & IOCB_NOWAIT) {
+		result = -EAGAIN;
+		nfs_direct_req_release(dreq);
+		goto out_release;
+	}
 
 	if (user_backed_iter(iter))
 		dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;
 
 	if (!swap) {
-		result = nfs_start_io_direct(inode);
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			result = nfs_start_io_direct_nowait(inode);
+		else
+			result = nfs_start_io_direct(inode);
 		if (result) {
 			/* release the reference that would usually be
 			 * consumed by nfs_direct_read_schedule_iovec()

fs/nfs/export.c

@@ -49,14 +49,14 @@ nfs_encode_fh(struct inode *inode, __u32 *p, int *max_len, struct inode *parent)
 		return FILEID_INVALID;
 	}
 
-	p[FILEID_HIGH_OFF] = NFS_FILEID(inode) >> 32;
-	p[FILEID_LOW_OFF] = NFS_FILEID(inode);
+	p[FILEID_HIGH_OFF] = inode->i_ino >> 32;
+	p[FILEID_LOW_OFF] = inode->i_ino;
 	p[FILE_I_TYPE_OFF] = inode->i_mode & S_IFMT;
 	p[len - 1] = 0; /* Padding */
 	nfs_copy_fh(clnt_fh, server_fh);
 	*max_len = len;
 	dprintk("%s: result fh fileid %llu mode %u size %d\n",
-		__func__, NFS_FILEID(inode), inode->i_mode, *max_len);
+		__func__, inode->i_ino, inode->i_mode, *max_len);
 	return *max_len;
 }
 

fs/nfs/file.c

@@ -72,8 +72,12 @@ nfs_file_open(struct inode *inode, struct file *filp)
 		return res;
 
 	res = nfs_open(inode, filp);
-	if (res == 0)
+	if (res == 0) {
 		filp->f_mode |= FMODE_CAN_ODIRECT;
+		/* flag NOWAIT on read-only files only */
+		if (!(filp->f_mode & FMODE_WRITE))
+			filp->f_mode |= FMODE_NOWAIT;
+	}
 	return res;
 }
 
@@ -166,6 +170,10 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 	if (iocb->ki_flags & IOCB_DIRECT)
 		return nfs_file_direct_read(iocb, to, false);
 
+	/* NOWAIT only supported on direct reads */
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		return -EAGAIN;
+
 	dprintk("NFS: read(%pD2, %zu@%lu)\n",
 		iocb->ki_filp,
 		iov_iter_count(to), (unsigned long) iocb->ki_pos);
@@ -705,6 +713,12 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 
 	trace_nfs_file_write(iocb, from);
 
+	/*
+	 * FMODE_NOWAIT is not set for writable files
+	 */
+	if (WARN_ON_ONCE(iocb->ki_flags & IOCB_NOWAIT))
+		return -EAGAIN;
+
 	result = nfs_key_timeout_notify(file, inode);
 	if (result)
 		return result;

fs/nfs/filelayout/filelayout.c

@@ -95,7 +95,7 @@ static void filelayout_reset_write(struct nfs_pgio_header *hdr)
 			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
 			hdr->task.tk_pid,
 			hdr->inode->i_sb->s_id,
-			(unsigned long long)NFS_FILEID(hdr->inode),
+			(unsigned long long)hdr->inode->i_ino,
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
@@ -112,7 +112,7 @@ static void filelayout_reset_read(struct nfs_pgio_header *hdr)
 			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
 			hdr->task.tk_pid,
 			hdr->inode->i_sb->s_id,
-			(unsigned long long)NFS_FILEID(hdr->inode),
+			(unsigned long long)hdr->inode->i_ino,
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
@@ -778,6 +778,8 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 static bool
 filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg)
 {
+	if (flseg->dsaddr)
+		return flseg->dsaddr->stripe_count > 1;
 	return flseg->num_fh > 1;
 }
 

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -551,6 +551,10 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 			if (!p)
 				goto out_err_free;
 			fh_count = be32_to_cpup(p);
+			if (fh_count == 0) {
+				rc = -EINVAL;
+				goto out_err_free;
+			}
 
 			dss_info->fh_versions =
 			    kzalloc_objs(struct nfs_fh, fh_count, gfp_flags);
@@ -632,6 +636,9 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 	if (!p)
 		goto out_sort_mirrors;
 	fls->flags = be32_to_cpup(p);
+	if (fls->flags & FF_FLAGS_NO_IO_THRU_MDS)
+		set_bit(NFS4_FF_HDR_NO_IO_THRU_MDS,
+			&FF_LAYOUT_FROM_HDR(lh)->flags);
 
 	p = xdr_inline_decode(&stream, 4);
 	if (!p)
@@ -1181,6 +1188,16 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
 			0, NFS4_MAX_UINT64, IOMODE_RW,
 			NFS_I(pgio->pg_inode)->layout,
 			pgio->pg_lseg);
+	if (NFS_I(pgio->pg_inode)->layout &&
+	    ff_layout_hdr_no_fallback_to_mds(NFS_I(pgio->pg_inode)->layout)) {
+		/*
+		 * FF_FLAGS_NO_IO_THRU_MDS: no current lseg but the server's
+		 * policy forbids MDS fallback.  Surface -EAGAIN so writeback
+		 * retries rather than silently issuing the WRITE via MDS.
+		 */
+		pgio->pg_error = -EAGAIN;
+		goto out;
+	}
 	/* no lseg means that pnfs is not in use, so no mirroring here */
 	nfs_pageio_reset_write_mds(pgio);
 out:
@@ -1230,7 +1247,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
 			hdr->task.tk_pid,
 			hdr->inode->i_sb->s_id,
-			(unsigned long long)NFS_FILEID(hdr->inode),
+			(unsigned long long)hdr->inode->i_ino,
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
@@ -1243,7 +1260,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
 			hdr->task.tk_pid,
 			hdr->inode->i_sb->s_id,
-			(unsigned long long)NFS_FILEID(hdr->inode),
+			(unsigned long long)hdr->inode->i_ino,
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
@@ -1283,7 +1300,7 @@ static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
 			"(req %s/%llu, %u bytes @ offset %llu)\n", __func__,
 			hdr->task.tk_pid,
 			hdr->inode->i_sb->s_id,
-			(unsigned long long)NFS_FILEID(hdr->inode),
+			(unsigned long long)hdr->inode->i_ino,
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
@@ -2200,6 +2217,14 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 out_failed:
 	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
+	if (ff_layout_no_fallback_to_mds(lseg)) {
+		/*
+		 * FF_FLAGS_NO_IO_THRU_MDS: force fresh LAYOUTGET,
+		 * never fall through to MDS I/O.
+		 */
+		pnfs_error_mark_layout_for_return(hdr->inode, lseg);
+		return PNFS_TRY_AGAIN;
+	}
 	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
 			IOMODE_READ, NFS_I(hdr->inode)->layout, lseg);
@@ -2285,6 +2310,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 out_failed:
 	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
+	if (ff_layout_no_fallback_to_mds(lseg)) {
+		/*
+		 * FF_FLAGS_NO_IO_THRU_MDS: force fresh LAYOUTGET,
+		 * never fall through to MDS I/O.
+		 */
+		pnfs_error_mark_layout_for_return(hdr->inode, lseg);
+		return PNFS_TRY_AGAIN;
+	}
 	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
 			IOMODE_RW, NFS_I(hdr->inode)->layout, lseg);