Merge tag 'nfs-for-6.18-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Add a Kconfig option to redirect dfprintk() to the trace buffer
   - Enable use of the RWF_DONTCACHE flag on the NFS client
   - Add striped layout handling to pNFS flexfiles
   - Add proper localio handling for READ and WRITE O_DIRECT

  Bugfixes:
   - Handle NFS4ERR_GRACE errors during delegation recall
   - Fix NFSv4.1 backchannel max_resp_sz verification check
   - Fix mount hang after CREATE_SESSION failure
   - Fix d_parent->d_inode locking in nfs4_setup_readdir()

  Other Cleanups and Improvements:
   - Improvements to write handling tracepoints
   - Fix a few trivial spelling mistakes
   - Cleanups to the rpcbind cleanup call sites
   - Convert the SUNRPC xdr_buf to use a scratch folio instead of
     scratch page
   - Remove unused NFS_WBACK_BUSY() macro
   - Remove __GFP_NOWARN flags
   - Unexport rpc_malloc() and rpc_free()"

* tag 'nfs-for-6.18-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (46 commits)
  NFS: add basic STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
  nfs/localio: add tracepoints for misaligned DIO READ and WRITE support
  nfs/localio: add proper O_DIRECT support for READ and WRITE
  nfs/localio: refactor iocb initialization
  nfs/localio: refactor iocb and iov_iter_bvec initialization
  nfs/localio: avoid issuing misaligned IO using O_DIRECT
  nfs/localio: make trace_nfs_local_open_fh more useful
  NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
  sunrpc: unexport rpc_malloc() and rpc_free()
  NFSv4/flexfiles: Add support for striped layouts
  NFSv4/flexfiles: Update layout stats & error paths for striped layouts
  NFSv4/flexfiles: Write path updates for striped layouts
  NFSv4/flexfiles: Commit path updates for striped layouts
  NFSv4/flexfiles: Read path updates for striped layouts
  NFSv4/flexfiles: Update low level helper functions to be DS stripe aware.
  NFSv4/flexfiles: Add data structure support for striped layouts
  NFSv4/flexfiles: Use ds_commit_idx when marking a write commit
  NFSv4/flexfiles: Remove cred local variable dependency
  nfs4_setup_readdir(): insufficient locking for ->d_parent->d_inode dereferencing
  NFS: Enable use of the RWF_DONTCACHE flag on the NFS client
  ...

Author: torvalds

fs/lockd/svc.c

@@ -216,8 +216,7 @@ static int make_socks(struct svc_serv *serv, struct net *net,
 	if (warned++ == 0)
 		printk(KERN_WARNING
 			"lockd_up: makesock failed, error=%d\n", err);
-	svc_xprt_destroy_all(serv, net);
-	svc_rpcb_cleanup(serv, net);
+	svc_xprt_destroy_all(serv, net, true);
 	return err;
 }
 
@@ -255,8 +254,7 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 			nlm_shutdown_hosts_net(net);
 			cancel_delayed_work_sync(&ln->grace_period_end);
 			locks_end_grace(&ln->lockd_manager);
-			svc_xprt_destroy_all(serv, net);
-			svc_rpcb_cleanup(serv, net);
+			svc_xprt_destroy_all(serv, net, true);
 		}
 	} else {
 		pr_err("%s: no users! net=%x\n",

fs/nfs/blocklayout/blocklayout.c

@@ -676,7 +676,7 @@ bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
 	struct pnfs_layout_segment *lseg;
 	struct xdr_buf buf;
 	struct xdr_stream xdr;
-	struct page *scratch;
+	struct folio *scratch;
 	int status, i;
 	uint32_t count;
 	__be32 *p;
@@ -689,13 +689,13 @@ bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
 		return ERR_PTR(-ENOMEM);
 
 	status = -ENOMEM;
-	scratch = alloc_page(gfp_mask);
+	scratch = folio_alloc(gfp_mask, 0);
 	if (!scratch)
 		goto out;
 
 	xdr_init_decode_pages(&xdr, &buf,
 			lgr->layoutp->pages, lgr->layoutp->len);
-	xdr_set_scratch_page(&xdr, scratch);
+	xdr_set_scratch_folio(&xdr, scratch);
 
 	status = -EIO;
 	p = xdr_inline_decode(&xdr, 4);
@@ -744,7 +744,7 @@ bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
 	}
 
 out_free_scratch:
-	__free_page(scratch);
+	folio_put(scratch);
 out:
 	dprintk("%s returns %d\n", __func__, status);
 	switch (status) {

fs/nfs/blocklayout/dev.c

@@ -541,16 +541,16 @@ bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct pnfs_block_dev *top;
 	struct xdr_stream xdr;
 	struct xdr_buf buf;
-	struct page *scratch;
+	struct folio *scratch;
 	int nr_volumes, ret, i;
 	__be32 *p;
 
-	scratch = alloc_page(gfp_mask);
+	scratch = folio_alloc(gfp_mask, 0);
 	if (!scratch)
 		goto out;
 
 	xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen);
-	xdr_set_scratch_page(&xdr, scratch);
+	xdr_set_scratch_folio(&xdr, scratch);
 
 	p = xdr_inline_decode(&xdr, sizeof(__be32));
 	if (!p)
@@ -582,7 +582,7 @@ bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 out_free_volumes:
 	kfree(volumes);
 out_free_scratch:
-	__free_page(scratch);
+	folio_put(scratch);
 out:
 	return node;
 }

fs/nfs/callback.c

@@ -136,7 +136,7 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc
 		return;
 
 	dprintk("NFS: destroy per-net callback data; net=%x\n", net->ns.inum);
-	svc_xprt_destroy_all(serv, net);
+	svc_xprt_destroy_all(serv, net, false);
 }
 
 static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
@@ -153,7 +153,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 	ret = svc_bind(serv, net);
 	if (ret < 0) {
 		printk(KERN_WARNING "NFS: bind callback service failed\n");
-		goto err_bind;
+		goto err;
 	}
 
 	ret = 0;
@@ -166,13 +166,11 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 
 	if (ret < 0) {
 		printk(KERN_ERR "NFS: callback service start failed\n");
-		goto err_socks;
+		goto err;
 	}
 	return 0;
 
-err_socks:
-	svc_rpcb_cleanup(serv, net);
-err_bind:
+err:
 	nn->cb_users[minorversion]--;
 	dprintk("NFS: Couldn't create callback socket: err = %d; "
 			"net = %x\n", ret, net->ns.inum);

fs/nfs/dir.c

@@ -829,17 +829,17 @@ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc,
 	struct address_space *mapping = desc->file->f_mapping;
 	struct folio *new, *folio = *arrays;
 	struct xdr_stream stream;
-	struct page *scratch;
+	struct folio *scratch;
 	struct xdr_buf buf;
 	u64 cookie;
 	int status;
 
-	scratch = alloc_page(GFP_KERNEL);
+	scratch = folio_alloc(GFP_KERNEL, 0);
 	if (scratch == NULL)
 		return -ENOMEM;
 
 	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
-	xdr_set_scratch_page(&stream, scratch);
+	xdr_set_scratch_folio(&stream, scratch);
 
 	do {
 		status = nfs_readdir_entry_decode(desc, entry, &stream);
@@ -891,7 +891,7 @@ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc,
 	if (folio != *arrays)
 		nfs_readdir_folio_unlock_and_put(folio);
 
-	put_page(scratch);
+	folio_put(scratch);
 	return status;
 }
 

fs/nfs/file.c

@@ -161,6 +161,8 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t result;
 
+	trace_nfs_file_read(iocb, to);
+
 	if (iocb->ki_flags & IOCB_DIRECT)
 		return nfs_file_direct_read(iocb, to, false);
 
@@ -361,6 +363,8 @@ static bool nfs_want_read_modify_write(struct file *file, struct folio *folio,
 
 	if (pnfs_ld_read_whole_page(file_inode(file)))
 		return true;
+	if (folio_test_dropbehind(folio))
+		return false;
 	/* Open for reading too? */
 	if (file->f_mode & FMODE_READ)
 		return true;
@@ -380,22 +384,23 @@ static int nfs_write_begin(const struct kiocb *iocb,
 			   loff_t pos, unsigned len, struct folio **foliop,
 			   void **fsdata)
 {
-	fgf_t fgp = FGP_WRITEBEGIN;
 	struct folio *folio;
 	struct file *file = iocb->ki_filp;
 	int once_thru = 0;
 	int ret;
 
+	trace_nfs_write_begin(file_inode(file), pos, len);
+
 	dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
 		file, mapping->host->i_ino, len, (long long) pos);
 	nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos);
 
-	fgp |= fgf_set_order(len);
 start:
-	folio = __filemap_get_folio(mapping, pos >> PAGE_SHIFT, fgp,
-				    mapping_gfp_mask(mapping));
-	if (IS_ERR(folio))
-		return PTR_ERR(folio);
+	folio = write_begin_get_folio(iocb, mapping, pos >> PAGE_SHIFT, len);
+	if (IS_ERR(folio)) {
+		ret = PTR_ERR(folio);
+		goto out;
+	}
 	*foliop = folio;
 
 	ret = nfs_flush_incompatible(file, folio);
@@ -405,11 +410,14 @@ static int nfs_write_begin(const struct kiocb *iocb,
 	} else if (!once_thru &&
 		   nfs_want_read_modify_write(file, folio, pos, len)) {
 		once_thru = 1;
+		folio_clear_dropbehind(folio);
 		ret = nfs_read_folio(file, folio);
 		folio_put(folio);
 		if (!ret)
 			goto start;
 	}
+out:
+	trace_nfs_write_begin_done(file_inode(file), pos, len, ret);
 	return ret;
 }
 
@@ -423,6 +431,7 @@ static int nfs_write_end(const struct kiocb *iocb,
 	unsigned offset = offset_in_folio(folio, pos);
 	int status;
 
+	trace_nfs_write_end(file_inode(file), pos, len);
 	dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n",
 		file, mapping->host->i_ino, len, (long long) pos);
 
@@ -451,13 +460,16 @@ static int nfs_write_end(const struct kiocb *iocb,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (status < 0)
+	if (status < 0) {
+		trace_nfs_write_end_done(file_inode(file), pos, len, status);
 		return status;
+	}
 	NFS_I(mapping->host)->write_io += copied;
 
 	if (nfs_ctx_key_to_expire(ctx, mapping->host))
 		nfs_wb_all(mapping->host);
 
+	trace_nfs_write_end_done(file_inode(file), pos, len, copied);
 	return copied;
 }
 
@@ -690,6 +702,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	errseq_t since;
 	int error;
 
+	trace_nfs_file_write(iocb, from);
+
 	result = nfs_key_timeout_notify(file, inode);
 	if (result)
 		return result;
@@ -949,5 +963,6 @@ const struct file_operations nfs_file_operations = {
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,
+	.fop_flags	= FOP_DONTCACHE,
 };
 EXPORT_SYMBOL_GPL(nfs_file_operations);

fs/nfs/filelayout/filelayout.c

@@ -646,19 +646,19 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 {
 	struct xdr_stream stream;
 	struct xdr_buf buf;
-	struct page *scratch;
+	struct folio *scratch;
 	__be32 *p;
 	uint32_t nfl_util;
 	int i;
 
 	dprintk("%s: set_layout_map Begin\n", __func__);
 
-	scratch = alloc_page(gfp_flags);
+	scratch = folio_alloc(gfp_flags, 0);
 	if (!scratch)
 		return -ENOMEM;
 
 	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
-	xdr_set_scratch_page(&stream, scratch);
+	xdr_set_scratch_folio(&stream, scratch);
 
 	/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
 	 * num_fh (4) */
@@ -724,11 +724,11 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 			fl->fh_array[i]->size);
 	}
 
-	__free_page(scratch);
+	folio_put(scratch);
 	return 0;
 
 out_err:
-	__free_page(scratch);
+	folio_put(scratch);
 	return -EIO;
 }
 

fs/nfs/filelayout/filelayoutdev.c

@@ -73,18 +73,18 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
 	struct xdr_stream stream;
 	struct xdr_buf buf;
-	struct page *scratch;
+	struct folio *scratch;
 	struct list_head dsaddrs;
 	struct nfs4_pnfs_ds_addr *da;
 	struct net *net = server->nfs_client->cl_net;
 
 	/* set up xdr stream */
-	scratch = alloc_page(gfp_flags);
+	scratch = folio_alloc(gfp_flags, 0);
 	if (!scratch)
 		goto out_err;
 
 	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
-	xdr_set_scratch_page(&stream, scratch);
+	xdr_set_scratch_folio(&stream, scratch);
 
 	/* Get the stripe count (number of stripe index) */
 	p = xdr_inline_decode(&stream, 4);
@@ -186,7 +186,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 		}
 	}
 
-	__free_page(scratch);
+	folio_put(scratch);
 	return dsaddr;
 
 out_err_drain_dsaddrs:
@@ -204,7 +204,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 out_err_free_stripe_indices:
 	kfree(stripe_indices);
 out_err_free_scratch:
-	__free_page(scratch);
+	folio_put(scratch);
 out_err:
 	dprintk("%s ERROR: returning NULL\n", __func__);
 	return NULL;