Merge tag 'nfs-for-6.6-1' of git://git.linux-nfs.org/projects/anna/li…

…nux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Enable the NFS v4.2 READ_PLUS operation by default

  Stable Fixes:
   - NFSv4/pnfs: minor fix for cleanup path in nfs4_get_device_info
   - NFS: Fix a potential data corruption

  Bugfixes:
   - Fix various READ_PLUS issues including:
      - smatch warnings
      - xdr size calculations
      - scratch buffer handling
      - 32bit / highmem xdr page handling
   - Fix checkpatch errors in file.c
   - Fix redundant readdir request after an EOF
   - Fix handling of COPY ERR_OFFLOAD_NO_REQ
   - Fix assignment of xprtdata.cred

  Cleanups:
   - Remove unused xprtrdma function declarations
   - Clean up an integer overflow check to avoid a warning
   - Clean up #includes in dns_resolve.c
   - Clean up nfs4_get_device_info so we don't pass a NULL pointer
     to __free_page()
   - Clean up sunrpc TCP socket timeout configuration
   - Guard against READDIR loops when entry names are too long
   - Use EXCHID4_FLAG_USE_PNFS_DS for DS servers"

* tag 'nfs-for-6.6-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (22 commits)
  pNFS: Fix assignment of xprtdata.cred
  NFSv4.2: fix handling of COPY ERR_OFFLOAD_NO_REQ
  NFS: Guard against READDIR loop when entry names exceed MAXNAMELEN
  NFSv4.1: use EXCHGID4_FLAG_USE_PNFS_DS for DS server
  NFS/pNFS: Set the connect timeout for the pNFS flexfiles driver
  SUNRPC: Don't override connect timeouts in rpc_clnt_add_xprt()
  SUNRPC: Allow specification of TCP client connect timeout at setup
  SUNRPC: Refactor and simplify connect timeout
  SUNRPC: Set the TCP_SYNCNT to match the socket timeout
  NFS: Fix a potential data corruption
  nfs: fix redundant readdir request after get eof
  nfs/blocklayout: Use the passed in gfp flags
  filemap: Fix errors in file.c
  NFSv4/pnfs: minor fix for cleanup path in nfs4_get_device_info
  NFS: Move common includes outside ifdef
  SUNRPC: clean up integer overflow check
  xprtrdma: Remove unused function declaration rpcrdma_bc_post_recv()
  NFS: Enable the READ_PLUS operation by default
  SUNRPC: kmap() the xdr pages during decode
  NFSv4.2: Rework scratch handling for READ_PLUS (again)
  ...

fs/nfs/Kconfig

@@ -209,8 +209,6 @@ config NFS_DISABLE_UDP_SUPPORT
 config NFS_V4_2_READ_PLUS
 	bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation"
 	depends on NFS_V4_2
-	default n
+	default y
 	help
-	 This is intended for developers only. The READ_PLUS operation has
-	 been shown to have issues under specific conditions and should not
-	 be used in production.
+	 Choose Y here to enable use of the NFS v4.2 READ_PLUS operation.

fs/nfs/blocklayout/dev.c

@@ -404,7 +404,7 @@ bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d,
 	int ret, i;
 
 	d->children = kcalloc(v->concat.volumes_count,
-			sizeof(struct pnfs_block_dev), GFP_KERNEL);
+			sizeof(struct pnfs_block_dev), gfp_mask);
 	if (!d->children)
 		return -ENOMEM;
 
@@ -433,7 +433,7 @@ bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d,
 	int ret, i;
 
 	d->children = kcalloc(v->stripe.volumes_count,
-			sizeof(struct pnfs_block_dev), GFP_KERNEL);
+			sizeof(struct pnfs_block_dev), gfp_mask);
 	if (!d->children)
 		return -ENOMEM;
 

fs/nfs/client.c

@@ -517,6 +517,8 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 		.authflavor	= flavor,
 		.cred		= cl_init->cred,
 		.xprtsec	= cl_init->xprtsec,
+		.connect_timeout = cl_init->connect_timeout,
+		.reconnect_timeout = cl_init->reconnect_timeout,
 	};
 
 	if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags))

fs/nfs/dir.c

@@ -1089,6 +1089,17 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
 	for (i = desc->cache_entry_index; i < array->size; i++) {
 		struct nfs_cache_array_entry *ent;
 
+		/*
+		 * nfs_readdir_handle_cache_misses return force clear at
+		 * (cache_misses > NFS_READDIR_CACHE_MISS_THRESHOLD) for
+		 * readdir heuristic, NFS_READDIR_CACHE_MISS_THRESHOLD + 1
+		 * entries need be emitted here.
+		 */
+		if (first_emit && i > NFS_READDIR_CACHE_MISS_THRESHOLD + 2) {
+			desc->eob = true;
+			break;
+		}
+
 		ent = &array->array[i];
 		if (!dir_emit(desc->ctx, ent->name, ent->name_len,
 		    nfs_compat_user_ino64(ent->ino), ent->d_type)) {
@@ -1107,10 +1118,6 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
 			desc->ctx->pos = desc->dir_cookie;
 		else
 			desc->ctx->pos++;
-		if (first_emit && i > NFS_READDIR_CACHE_MISS_THRESHOLD + 1) {
-			desc->eob = true;
-			break;
-		}
 	}
 	if (array->folio_is_eof)
 		desc->eof = !desc->eob;

fs/nfs/direct.c

@@ -472,13 +472,31 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
 	return result;
 }
 
+static void nfs_direct_add_page_head(struct list_head *list,
+				     struct nfs_page *req)
+{
+	struct nfs_page *head = req->wb_head;
+
+	if (!list_empty(&head->wb_list) || !nfs_lock_request(head))
+		return;
+	if (!list_empty(&head->wb_list)) {
+		nfs_unlock_request(head);
+		return;
+	}
+	list_add(&head->wb_list, list);
+	kref_get(&head->wb_kref);
+	kref_get(&head->wb_kref);
+}
+
 static void nfs_direct_join_group(struct list_head *list, struct inode *inode)
 {
 	struct nfs_page *req, *subreq;
 
 	list_for_each_entry(req, list, wb_list) {
-		if (req->wb_head != req)
+		if (req->wb_head != req) {
+			nfs_direct_add_page_head(&req->wb_list, req);
 			continue;
+		}
 		subreq = req->wb_this_page;
 		if (subreq == req)
 			continue;

fs/nfs/dns_resolve.c

@@ -7,14 +7,16 @@
  * Resolves DNS hostnames into valid ip addresses
  */
 
-#ifdef CONFIG_NFS_USE_KERNEL_DNS
-
 #include <linux/module.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/addr.h>
-#include <linux/dns_resolver.h>
+
 #include "dns_resolve.h"
 
+#ifdef CONFIG_NFS_USE_KERNEL_DNS
+
+#include <linux/dns_resolver.h>
+
 ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
 		struct sockaddr_storage *ss, size_t salen)
 {
@@ -35,23 +37,19 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
 
 #else
 
-#include <linux/module.h>
 #include <linux/hash.h>
 #include <linux/string.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/seq_file.h>
 #include <linux/inet.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/addr.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/svcauth.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/nfs_fs.h>
 
 #include "nfs4_fs.h"
-#include "dns_resolve.h"
 #include "cache_lib.h"
 #include "netns.h"
 

fs/nfs/file.c

@@ -200,7 +200,7 @@ nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe
 EXPORT_SYMBOL_GPL(nfs_file_splice_read);
 
 int
-nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
+nfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
 	int	status;

fs/nfs/internal.h

@@ -82,6 +82,8 @@ struct nfs_client_initdata {
 	const struct rpc_timeout *timeparms;
 	const struct cred *cred;
 	struct xprtsec_parms xprtsec;
+	unsigned long connect_timeout;
+	unsigned long reconnect_timeout;
 };
 
 /*
@@ -493,6 +495,7 @@ extern const struct nfs_pgio_completion_ops nfs_async_read_completion_ops;
 extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 			struct inode *inode, bool force_mds,
 			const struct nfs_pgio_completion_ops *compl_ops);
+extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size);
 extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio,
 			       struct nfs_open_context *ctx,
 			       struct folio *folio);

fs/nfs/nfs2xdr.c

@@ -949,7 +949,7 @@ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 
 	error = decode_filename_inline(xdr, &entry->name, &entry->len);
 	if (unlikely(error))
-		return -EAGAIN;
+		return error == -ENAMETOOLONG ? -ENAMETOOLONG : -EAGAIN;
 
 	/*
 	 * The type (size and byte order) of nfscookie isn't defined in

fs/nfs/nfs3client.c

@@ -86,6 +86,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
 {
 	struct rpc_timeout ds_timeout;
+	unsigned long connect_timeout = ds_timeo * (ds_retrans + 1) * HZ / 10;
 	struct nfs_client *mds_clp = mds_srv->nfs_client;
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,
@@ -98,6 +99,8 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 		.timeparms = &ds_timeout,
 		.cred = mds_srv->cred,
 		.xprtsec = mds_clp->cl_xprtsec,
+		.connect_timeout = connect_timeout,
+		.reconnect_timeout = connect_timeout,
 	};
 	struct nfs_client *clp;
 	char buf[INET6_ADDRSTRLEN + 1];

fs/nfs/nfs3xdr.c

@@ -1991,7 +1991,7 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 
 	error = decode_inline_filename3(xdr, &entry->name, &entry->len);
 	if (unlikely(error))
-		return -EAGAIN;
+		return error == -ENAMETOOLONG ? -ENAMETOOLONG : -EAGAIN;
 
 	error = decode_cookie3(xdr, &new_cookie);
 	if (unlikely(error))

fs/nfs/nfs42.h

@@ -13,6 +13,7 @@
  * more? Need to consider not to pre-alloc too much for a compound.
  */
 #define PNFS_LAYOUTSTATS_MAXDEV (4)
+#define READ_PLUS_SCRATCH_SIZE (16)
 
 /* nfs4.2proc.c */
 #ifdef CONFIG_NFS_V4_2

fs/nfs/nfs42proc.c

@@ -471,8 +471,9 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 				continue;
 			}
 			break;
-		} else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) {
-			args.sync = true;
+		} else if (err == -NFS4ERR_OFFLOAD_NO_REQS &&
+				args.sync != res.synchronous) {
+			args.sync = res.synchronous;
 			dst_exception.retry = 1;
 			continue;
 		} else if ((err == -ESTALE ||

fs/nfs/nfs42xdr.c

@@ -54,10 +54,16 @@
 					(1 /* data_content4 */ + \
 					 2 /* data_info4.di_offset */ + \
 					 1 /* data_info4.di_length */)
+#define NFS42_READ_PLUS_HOLE_SEGMENT_SIZE \
+					(1 /* data_content4 */ + \
+					 2 /* data_info4.di_offset */ + \
+					 2 /* data_info4.di_length */)
+#define READ_PLUS_SEGMENT_SIZE_DIFF	(NFS42_READ_PLUS_HOLE_SEGMENT_SIZE - \
+					 NFS42_READ_PLUS_DATA_SEGMENT_SIZE)
 #define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
 					 1 /* rpr_eof */ + \
 					 1 /* rpr_contents count */ + \
-					 NFS42_READ_PLUS_DATA_SEGMENT_SIZE)
+					 NFS42_READ_PLUS_HOLE_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -617,8 +623,8 @@ static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
 	encode_putfh(xdr, args->fh, &hdr);
 	encode_read_plus(xdr, args, &hdr);
 
-	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
-				args->count, hdr.replen);
+	rpc_prepare_reply_pages(req, args->pages, args->pgbase, args->count,
+				hdr.replen - READ_PLUS_SEGMENT_SIZE_DIFF);
 	encode_nops(&hdr);
 }
 
@@ -1056,13 +1062,12 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
 	res->eof = be32_to_cpup(p++);
 	segments = be32_to_cpup(p++);
 	if (segments == 0)
-		return status;
+		return 0;
 
 	segs = kmalloc_array(segments, sizeof(*segs), GFP_KERNEL);
 	if (!segs)
 		return -ENOMEM;
 
-	status = -EIO;
 	for (i = 0; i < segments; i++) {
 		status = decode_read_plus_segment(xdr, &segs[i]);
 		if (status < 0)
@@ -1428,7 +1433,7 @@ static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
 	struct compound_hdr hdr;
 	int status;
 
-	xdr_set_scratch_buffer(xdr, res->scratch, sizeof(res->scratch));
+	xdr_set_scratch_buffer(xdr, res->scratch, READ_PLUS_SCRATCH_SIZE);
 
 	status = decode_compound_hdr(xdr, &hdr);
 	if (status)

fs/nfs/nfs4client.c

@@ -232,6 +232,8 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
 	__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
 
+	if (test_bit(NFS_CS_DS, &cl_init->init_flags))
+		__set_bit(NFS_CS_DS, &clp->cl_flags);
 	/*
 	 * Set up the connection to the server before we add add to the
 	 * global list.
@@ -1007,6 +1009,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
+	__set_bit(NFS_CS_DS, &cl_init.init_flags);
 	/*
 	 * Set an authflavor equual to the MDS value. Use the MDS nfs_client
 	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS

fs/nfs/nfs4proc.c

@@ -5438,18 +5438,8 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task,
 	return false;
 }
 
-static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr)
-{
-	if (hdr->res.scratch) {
-		kfree(hdr->res.scratch);
-		hdr->res.scratch = NULL;
-	}
-}
-
 static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	nfs4_read_plus_scratch_free(hdr);
-
 	if (!nfs4_sequence_done(task, &hdr->res.seq_res))
 		return -EAGAIN;
 	if (nfs4_read_stateid_changed(task, &hdr->args))
@@ -5469,8 +5459,7 @@ static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr,
 	/* Note: We don't use READ_PLUS with pNFS yet */
 	if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) {
 		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS];
-		hdr->res.scratch = kmalloc(32, GFP_KERNEL);
-		return hdr->res.scratch != NULL;
+		return nfs_read_alloc_scratch(hdr, READ_PLUS_SCRATCH_SIZE);
 	}
 	return false;
 }
@@ -8798,6 +8787,8 @@ nfs4_run_exchange_id(struct nfs_client *clp, const struct cred *cred,
 #ifdef CONFIG_NFS_V4_1_MIGRATION
 	calldata->args.flags |= EXCHGID4_FLAG_SUPP_MOVED_MIGR;
 #endif
+	if (test_bit(NFS_CS_DS, &clp->cl_flags))
+		calldata->args.flags |= EXCHGID4_FLAG_USE_PNFS_DS;
 	msg.rpc_argp = &calldata->args;
 	msg.rpc_resp = &calldata->res;
 	task_setup_data.callback_data = calldata;
@@ -8875,6 +8866,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
 	/* Save the EXCHANGE_ID verifier session trunk tests */
 	memcpy(clp->cl_confirm.data, argp->verifier.data,
 	       sizeof(clp->cl_confirm.data));
+	if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS)
+		set_bit(NFS_CS_DS, &clp->cl_flags);
 out:
 	trace_nfs4_exchange_id(clp, status);
 	rpc_put_task(task);

fs/nfs/pnfs_dev.c

@@ -154,7 +154,7 @@ nfs4_get_device_info(struct nfs_server *server,
 		set_bit(NFS_DEVICEID_NOCACHE, &d->flags);
 
 out_free_pages:
-	for (i = 0; i < max_pages; i++)
+	while (--i >= 0)
 		__free_page(pages[i]);
 	kfree(pages);
 out_free_pdev:

fs/nfs/pnfs_nfs.c

@@ -852,6 +852,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 {
 	struct nfs_client *clp = ERR_PTR(-EIO);
 	struct nfs4_pnfs_ds_addr *da;
+	unsigned long connect_timeout = timeo * (retrans + 1) * HZ / 10;
 	int status = 0;
 
 	dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
@@ -870,6 +871,8 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 				.dstaddr = (struct sockaddr *)&da->da_addr,
 				.addrlen = da->da_addrlen,
 				.servername = clp->cl_hostname,
+				.connect_timeout = connect_timeout,
+				.reconnect_timeout = connect_timeout,
 			};
 
 			if (da->da_transport != clp->cl_proto)
@@ -943,7 +946,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 			* Test this address for session trunking and
 			* add as an alias
 			*/
-			xprtdata.cred = nfs4_get_clid_cred(clp),
+			xprtdata.cred = nfs4_get_clid_cred(clp);
 			rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
 					  rpc_clnt_setup_test_and_add_xprt,
 					  &rpcdata);