Merge tag 'nfs-for-5.9-1' of git://git.linux-nfs.org/projects/trondmy…

…/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Stable fixes:
   - pNFS: Don't return layout segments that are being used for I/O
   - pNFS: Don't move layout segments off the active list when being used for I/O

  Features:
   - NFS: Add support for user xattrs through the NFSv4.2 protocol
   - NFS: Allow applications to speed up readdir+statx() using AT_STATX_DONT_SYNC
   - NFSv4.0 allow nconnect for v4.0

  Bugfixes and cleanups:
   - nfs: ensure correct writeback errors are returned on close()
   - nfs: nfs_file_write() should check for writeback errors
   - nfs: Fix getxattr kernel panic and memory overflow
   - NFS: Fix the pNFS/flexfiles mirrored read failover code
   - SUNRPC: dont update timeout value on connection reset
   - freezer: Add unsafe versions of freezable_schedule_timeout_interruptible for NFS
   - sunrpc: destroy rpc_inode_cachep after unregister_filesystem"

* tag 'nfs-for-5.9-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (32 commits)
  NFS: Fix flexfiles read failover
  fs: nfs: delete repeated words in comments
  rpc_pipefs: convert comma to semicolon
  nfs: Fix getxattr kernel panic and memory overflow
  NFS: Don't return layout segments that are in use
  NFS: Don't move layouts to plh_return_segs list while in use
  NFS: Add layout segment info to pnfs read/write/commit tracepoints
  NFS: Add tracepoints for layouterror and layoutstats.
  NFS: Report the stateid + status in trace_nfs4_layoutreturn_on_close()
  SUNRPC dont update timeout value on connection reset
  nfs: nfs_file_write() should check for writeback errors
  nfs: ensure correct writeback errors are returned on close()
  NFSv4.2: xattr cache: get rid of cache discard work queue
  NFS: remove redundant initialization of variable result
  NFSv4.0 allow nconnect for v4.0
  freezer: Add unsafe versions of freezable_schedule_timeout_interruptible for NFS
  sunrpc: destroy rpc_inode_cachep after unregister_filesystem
  NFSv4.2: add client side xattr caching.
  NFSv4.2: hook in the user extended attribute handlers
  NFSv4.2: add the extended attribute proc functions.
  ...

fs/nfs/Makefile

@@ -30,7 +30,7 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
 nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
-nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
+nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o nfs42xattr.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/

fs/nfs/blocklayout/rpc_pipefs.c

@@ -79,7 +79,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
 		goto out_free_data;
 
 	bl_msg = msg->data;
-	bl_msg->type = BL_DEVICE_MOUNT,
+	bl_msg->type = BL_DEVICE_MOUNT;
 	bl_msg->totallen = b->simple.len;
 	nfs4_encode_simple(msg->data + sizeof(*bl_msg), b);
 

fs/nfs/client.c

@@ -50,6 +50,7 @@
 #include "nfs.h"
 #include "netns.h"
 #include "sysfs.h"
+#include "nfs42.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
@@ -749,7 +750,7 @@ static int nfs_init_server(struct nfs_server *server,
 static void nfs_server_set_fsinfo(struct nfs_server *server,
 				  struct nfs_fsinfo *fsinfo)
 {
-	unsigned long max_rpc_payload;
+	unsigned long max_rpc_payload, raw_max_rpc_payload;
 
 	/* Work out a lot of parameters */
 	if (server->rsize == 0)
@@ -762,7 +763,9 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	if (fsinfo->wtmax >= 512 && server->wsize > fsinfo->wtmax)
 		server->wsize = nfs_block_size(fsinfo->wtmax, NULL);
 
-	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
+	raw_max_rpc_payload = rpc_max_payload(server->client);
+	max_rpc_payload = nfs_block_size(raw_max_rpc_payload, NULL);
+
 	if (server->rsize > max_rpc_payload)
 		server->rsize = max_rpc_payload;
 	if (server->rsize > NFS_MAX_FILE_IO_SIZE)
@@ -795,6 +798,21 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	server->clone_blksize = fsinfo->clone_blksize;
 	/* We're airborne Set socket buffersize */
 	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
+
+#ifdef CONFIG_NFS_V4_2
+	/*
+	 * Defaults until limited by the session parameters.
+	 */
+	server->gxasize = min_t(unsigned int, raw_max_rpc_payload,
+				XATTR_SIZE_MAX);
+	server->sxasize = min_t(unsigned int, raw_max_rpc_payload,
+				XATTR_SIZE_MAX);
+	server->lxasize = min_t(unsigned int, raw_max_rpc_payload,
+				nfs42_listxattr_xdrsize(XATTR_LIST_MAX));
+
+	if (fsinfo->xattr_support)
+		server->caps |= NFS_CAP_XATTR;
+#endif
 }
 
 /*

fs/nfs/dir.c

@@ -2460,7 +2460,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co
 	return NULL;
 }
 
-static int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block)
+static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_access_entry *cache;
@@ -2533,6 +2533,20 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre
 	return err;
 }
 
+int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct
+nfs_access_entry *res, bool may_block)
+{
+	int status;
+
+	status = nfs_access_get_cached_rcu(inode, cred, res);
+	if (status != 0)
+		status = nfs_access_get_cached_locked(inode, cred, res,
+		    may_block);
+
+	return status;
+}
+EXPORT_SYMBOL_GPL(nfs_access_get_cached);
+
 static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -2647,9 +2661,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
 
 	trace_nfs_access_enter(inode);
 
-	status = nfs_access_get_cached_rcu(inode, cred, &cache);
-	if (status != 0)
-		status = nfs_access_get_cached(inode, cred, &cache, may_block);
+	status = nfs_access_get_cached(inode, cred, &cache, may_block);
 	if (status == 0)
 		goto out_cached;
 
@@ -2661,6 +2673,10 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
 	 * Determine which access bits we want to ask for...
 	 */
 	cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND;
+	if (nfs_server_capable(inode, NFS_CAP_XATTR)) {
+		cache.mask |= NFS_ACCESS_XAREAD | NFS_ACCESS_XAWRITE |
+		    NFS_ACCESS_XALIST;
+	}
 	if (S_ISDIR(inode->i_mode))
 		cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP;
 	else

fs/nfs/direct.c

@@ -896,7 +896,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 {
-	ssize_t result = -EINVAL, requested;
+	ssize_t result, requested;
 	size_t count;
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;

fs/nfs/file.c

@@ -140,6 +140,7 @@ static int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
 	struct inode	*inode = file_inode(file);
+	errseq_t since;
 
 	dprintk("NFS: flush(%pD2)\n", file);
 
@@ -148,7 +149,9 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 		return 0;
 
 	/* Flush writes to the server and return any errors */
-	return nfs_wb_all(inode);
+	since = filemap_sample_wb_err(file->f_mapping);
+	nfs_wb_all(inode);
+	return filemap_check_wb_err(file->f_mapping, since);
 }
 
 ssize_t
@@ -587,12 +590,14 @@ static const struct vm_operations_struct nfs_file_vm_ops = {
 	.page_mkwrite = nfs_vm_page_mkwrite,
 };
 
-static int nfs_need_check_write(struct file *filp, struct inode *inode)
+static int nfs_need_check_write(struct file *filp, struct inode *inode,
+				int error)
 {
 	struct nfs_open_context *ctx;
 
 	ctx = nfs_file_open_context(filp);
-	if (nfs_ctx_key_to_expire(ctx, inode))
+	if (nfs_error_is_fatal_on_server(error) ||
+	    nfs_ctx_key_to_expire(ctx, inode))
 		return 1;
 	return 0;
 }
@@ -603,6 +608,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(file);
 	unsigned long written = 0;
 	ssize_t result;
+	errseq_t since;
+	int error;
 
 	result = nfs_key_timeout_notify(file, inode);
 	if (result)
@@ -627,6 +634,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	if (iocb->ki_pos > i_size_read(inode))
 		nfs_revalidate_mapping(inode, file->f_mapping);
 
+	since = filemap_sample_wb_err(file->f_mapping);
 	nfs_start_io_write(inode);
 	result = generic_write_checks(iocb, from);
 	if (result > 0) {
@@ -645,7 +653,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 
 	/* Return error values */
-	if (nfs_need_check_write(file, inode)) {
+	error = filemap_check_wb_err(file->f_mapping, since);
+	if (nfs_need_check_write(file, inode, error)) {
 		int err = nfs_wb_all(inode);
 		if (err < 0)
 			result = err;

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -790,6 +790,19 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
 	return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx);
 }
 
+static struct nfs4_pnfs_ds *
+ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx)
+{
+	struct pnfs_layout_segment *lseg = pgio->pg_lseg;
+	struct nfs4_pnfs_ds *ds;
+
+	ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx,
+					       best_idx);
+	if (ds || !pgio->pg_mirror_idx)
+		return ds;
+	return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx);
+}
+
 static void
 ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
 		      struct nfs_page *req,
@@ -840,12 +853,11 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			goto out_nolseg;
 	}
 
-	ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
+	ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
 	if (!ds) {
 		if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 			goto out_mds;
-		pnfs_put_lseg(pgio->pg_lseg);
-		pgio->pg_lseg = NULL;
+		pnfs_generic_pg_cleanup(pgio);
 		/* Sleep for 1 second before retrying */
 		ssleep(1);
 		goto retry;
@@ -871,8 +883,6 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			0, NFS4_MAX_UINT64, IOMODE_READ,
 			NFS_I(pgio->pg_inode)->layout,
 			pgio->pg_lseg);
-	pnfs_put_lseg(pgio->pg_lseg);
-	pgio->pg_lseg = NULL;
 	pgio->pg_maxretrans = 0;
 	nfs_pageio_reset_read_mds(pgio);
 }
@@ -916,8 +926,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 		if (!ds) {
 			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 				goto out_mds;
-			pnfs_put_lseg(pgio->pg_lseg);
-			pgio->pg_lseg = NULL;
+			pnfs_generic_pg_cleanup(pgio);
 			/* Sleep for 1 second before retrying */
 			ssleep(1);
 			goto retry;
@@ -939,8 +948,6 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			0, NFS4_MAX_UINT64, IOMODE_RW,
 			NFS_I(pgio->pg_inode)->layout,
 			pgio->pg_lseg);
-	pnfs_put_lseg(pgio->pg_lseg);
-	pgio->pg_lseg = NULL;
 	pgio->pg_maxretrans = 0;
 	nfs_pageio_reset_write_mds(pgio);
 	pgio->pg_error = -EAGAIN;
@@ -953,8 +960,8 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   nfs_req_openctx(req),
-						   0,
-						   NFS4_MAX_UINT64,
+						   req_offset(req),
+						   req->wb_bytes,
 						   IOMODE_RW,
 						   false,
 						   GFP_NOFS);
@@ -1028,11 +1035,24 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 	}
 }
 
+static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
+{
+	u32 idx = hdr->pgio_mirror_idx + 1;
+	int new_idx = 0;
+
+	if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx))
+		ff_layout_send_layouterror(hdr->lseg);
+	else
+		pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
+	pnfs_read_resend_pnfs(hdr, new_idx);
+}
+
 static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
 {
 	struct rpc_task *task = &hdr->task;
 
 	pnfs_layoutcommit_inode(hdr->inode, false);
+	pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
 
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
 		dprintk("%s Reset task %5u for i/o through MDS "
@@ -1234,6 +1254,12 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 		break;
 	case NFS4ERR_NXIO:
 		ff_layout_mark_ds_unreachable(lseg, idx);
+		/*
+		 * Don't return the layout if this is a read and we still
+		 * have layouts to try
+		 */
+		if (opnum == OP_READ)
+			break;
 		/* Fallthrough */
 	default:
 		pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode,
@@ -1247,7 +1273,6 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 static int ff_layout_read_done_cb(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
-	int new_idx = hdr->pgio_mirror_idx;
 	int err;
 
 	if (task->tk_status < 0) {
@@ -1267,10 +1292,6 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 	clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
 	switch (err) {
 	case -NFS4ERR_RESET_TO_PNFS:
-		if (ff_layout_choose_best_ds_for_read(hdr->lseg,
-					hdr->pgio_mirror_idx + 1,
-					&new_idx))
-			goto out_layouterror;
 		set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
 		return task->tk_status;
 	case -NFS4ERR_RESET_TO_MDS:
@@ -1281,10 +1302,6 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 	}
 
 	return 0;
-out_layouterror:
-	ff_layout_read_record_layoutstats_done(task, hdr);
-	ff_layout_send_layouterror(hdr->lseg);
-	hdr->pgio_mirror_idx = new_idx;
 out_eagain:
 	rpc_restart_call_prepare(task);
 	return -EAGAIN;
@@ -1411,10 +1428,9 @@ static void ff_layout_read_release(void *data)
 	struct nfs_pgio_header *hdr = data;
 
 	ff_layout_read_record_layoutstats_done(&hdr->task, hdr);
-	if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) {
-		ff_layout_send_layouterror(hdr->lseg);
-		pnfs_read_resend_pnfs(hdr);
-	} else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+	if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+		ff_layout_resend_pnfs_read(hdr);
+	else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
 		ff_layout_reset_read(hdr);
 	pnfs_generic_rw_release(data);
 }

fs/nfs/fs_context.c

@@ -982,7 +982,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 		/*
 		 * The legacy version 6 binary mount data from userspace has a
 		 * field used only to transport selinux information into the
-		 * the kernel.  To continue to support that functionality we
+		 * kernel.  To continue to support that functionality we
 		 * have a touch of selinux knowledge here in the NFS code. The
 		 * userspace code converted context=blah to just blah so we are
 		 * converting back to the full string selinux understands.