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.

fs/nfs/inode.c

@@ -193,6 +193,7 @@ bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags)
 
 	return nfs_check_cache_invalid_not_delegated(inode, flags);
 }
+EXPORT_SYMBOL_GPL(nfs_check_cache_invalid);
 
 static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 {
@@ -204,7 +205,8 @@ static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 			flags &= ~NFS_INO_INVALID_OTHER;
 		flags &= ~(NFS_INO_INVALID_CHANGE
 				| NFS_INO_INVALID_SIZE
-				| NFS_INO_REVAL_PAGECACHE);
+				| NFS_INO_REVAL_PAGECACHE
+				| NFS_INO_INVALID_XATTR);
 	}
 
 	if (inode->i_mapping->nrpages == 0)
@@ -233,11 +235,13 @@ static void nfs_zap_caches_locked(struct inode *inode)
 					| NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
+					| NFS_INO_INVALID_XATTR
 					| NFS_INO_REVAL_PAGECACHE);
 	} else
 		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
+					| NFS_INO_INVALID_XATTR
 					| NFS_INO_REVAL_PAGECACHE);
 	nfs_zap_label_cache_locked(nfsi);
 }
@@ -542,6 +546,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 			inode->i_gid = fattr->gid;
 		else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+		if (nfs_server_capable(inode, NFS_CAP_XATTR))
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 			inode->i_blocks = fattr->du.nfs2.blocks;
 		if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -794,8 +800,10 @@ int nfs_getattr(const struct path *path, struct kstat *stat,
 
 	trace_nfs_getattr_enter(inode);
 
-	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync)
+	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
+		nfs_readdirplus_parent_cache_hit(path->dentry);
 		goto out_no_update;
+	}
 
 	/* Flush out writes to the server in order to update c/mtime.  */
 	if ((request_mask & (STATX_CTIME|STATX_MTIME)) &&
@@ -1375,6 +1383,8 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		inode_set_iversion_raw(inode, fattr->change_attr);
 		if (S_ISDIR(inode->i_mode))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
+		else if (nfs_server_capable(inode, NFS_CAP_XATTR))
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
 	}
 	/* If we have atomic WCC data, we may update some attributes */
 	ts = inode->i_ctime;
@@ -1892,7 +1902,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			if (!(have_writers || have_delegation)) {
 				invalid |= NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
-					| NFS_INO_INVALID_ACL;
+					| NFS_INO_INVALID_ACL
+					| NFS_INO_INVALID_XATTR;
 				/* Force revalidate of all attributes */
 				save_cache_validity |= NFS_INO_INVALID_CTIME
 					| NFS_INO_INVALID_MTIME
@@ -2095,6 +2106,9 @@ struct inode *nfs_alloc_inode(struct super_block *sb)
 #if IS_ENABLED(CONFIG_NFS_V4)
 	nfsi->nfs4_acl = NULL;
 #endif /* CONFIG_NFS_V4 */
+#ifdef CONFIG_NFS_V4_2
+	nfsi->xattr_cache = NULL;
+#endif
 	return &nfsi->vfs_inode;
 }
 EXPORT_SYMBOL_GPL(nfs_alloc_inode);

fs/nfs/nfs42.h

@@ -6,6 +6,8 @@
 #ifndef __LINUX_FS_NFS_NFS4_2_H
 #define __LINUX_FS_NFS_NFS4_2_H
 
+#include <linux/xattr.h>
+
 /*
  * FIXME:  four LAYOUTSTATS calls per compound at most! Do we need to support
  * more? Need to consider not to pre-alloc too much for a compound.
@@ -36,5 +38,27 @@ static inline bool nfs42_files_from_same_server(struct file *in,
 	return nfs4_check_serverowner_major_id(c_in->cl_serverowner,
 					       c_out->cl_serverowner);
 }
+
+ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name,
+			    void *buf, size_t buflen);
+int nfs42_proc_setxattr(struct inode *inode, const char *name,
+			const void *buf, size_t buflen, int flags);
+ssize_t nfs42_proc_listxattrs(struct inode *inode, void *buf,
+			       size_t buflen, u64 *cookiep, bool *eofp);
+int nfs42_proc_removexattr(struct inode *inode, const char *name);
+
+/*
+ * Maximum XDR buffer size needed for a listxattr buffer of buflen size.
+ *
+ * The upper boundary is a buffer with all 1-byte sized attribute names.
+ * They would be 7 bytes long in the eventual buffer ("user.x\0"), and
+ * 8 bytes long XDR-encoded.
+ *
+ * Include the trailing eof word as well.
+ */
+static inline u32 nfs42_listxattr_xdrsize(u32 buflen)
+{
+	return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4;
+}
 #endif /* CONFIG_NFS_V4_2 */
 #endif /* __LINUX_FS_NFS_NFS4_2_H */

fs/nfs/nfs42proc.c

@@ -17,6 +17,7 @@
 #include "nfs4session.h"
 #include "internal.h"
 #include "delegation.h"
+#include "nfs4trace.h"
 
 #define NFSDBG_FACILITY NFSDBG_PROC
 static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std);
@@ -714,7 +715,7 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
 
 	switch (task->tk_status) {
 	case 0:
-		break;
+		return;
 	case -NFS4ERR_BADHANDLE:
 	case -ESTALE:
 		pnfs_destroy_layout(NFS_I(inode));
@@ -760,6 +761,8 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
 	case -EOPNOTSUPP:
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
 	}
+
+	trace_nfs4_layoutstats(inode, &data->args.stateid, task->tk_status);
 }
 
 static void
@@ -882,7 +885,7 @@ nfs42_layouterror_done(struct rpc_task *task, void *calldata)
 
 	switch (task->tk_status) {
 	case 0:
-		break;
+		return;
 	case -NFS4ERR_BADHANDLE:
 	case -ESTALE:
 		pnfs_destroy_layout(NFS_I(inode));
@@ -926,6 +929,9 @@ nfs42_layouterror_done(struct rpc_task *task, void *calldata)
 	case -EOPNOTSUPP:
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTERROR;
 	}
+
+	trace_nfs4_layouterror(inode, &data->args.errors[0].stateid,
+			       task->tk_status);
 }
 
 static void
@@ -1088,3 +1094,251 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f,
 	nfs_put_lock_context(src_lock);
 	return err;
 }
+
+#define NFS4XATTR_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE)
+
+static int _nfs42_proc_removexattr(struct inode *inode, const char *name)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs42_removexattrargs args = {
+		.fh = NFS_FH(inode),
+		.xattr_name = name,
+	};
+	struct nfs42_removexattrres res;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVEXATTR],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+	int ret;
+	unsigned long timestamp = jiffies;
+
+	ret = nfs4_call_sync(server->client, server, &msg, &args.seq_args,
+	    &res.seq_res, 1);
+	if (!ret)
+		nfs4_update_changeattr(inode, &res.cinfo, timestamp, 0);
+
+	return ret;
+}
+
+static int _nfs42_proc_setxattr(struct inode *inode, const char *name,
+				const void *buf, size_t buflen, int flags)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct page *pages[NFS4XATTR_MAXPAGES];
+	struct nfs42_setxattrargs arg = {
+		.fh		= NFS_FH(inode),
+		.xattr_pages	= pages,
+		.xattr_len	= buflen,
+		.xattr_name	= name,
+		.xattr_flags	= flags,
+	};
+	struct nfs42_setxattrres res;
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_SETXATTR],
+		.rpc_argp	= &arg,
+		.rpc_resp	= &res,
+	};
+	int ret, np;
+	unsigned long timestamp = jiffies;
+
+	if (buflen > server->sxasize)
+		return -ERANGE;
+
+	if (buflen > 0) {
+		np = nfs4_buf_to_pages_noslab(buf, buflen, arg.xattr_pages);
+		if (np < 0)
+			return np;
+	} else
+		np = 0;
+
+	ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args,
+	    &res.seq_res, 1);
+
+	for (; np > 0; np--)
+		put_page(pages[np - 1]);
+
+	if (!ret)
+		nfs4_update_changeattr(inode, &res.cinfo, timestamp, 0);
+
+	return ret;
+}
+
+static ssize_t _nfs42_proc_getxattr(struct inode *inode, const char *name,
+				void *buf, size_t buflen)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct page *pages[NFS4XATTR_MAXPAGES] = {};
+	struct nfs42_getxattrargs arg = {
+		.fh		= NFS_FH(inode),
+		.xattr_pages	= pages,
+		.xattr_len	= buflen,
+		.xattr_name	= name,
+	};
+	struct nfs42_getxattrres res;
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_GETXATTR],
+		.rpc_argp	= &arg,
+		.rpc_resp	= &res,
+	};
+	int ret, np;
+
+	ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args,
+	    &res.seq_res, 0);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Normally, the caching is done one layer up, but for successful
+	 * RPCS, always cache the result here, even if the caller was
+	 * just querying the length, or if the reply was too big for
+	 * the caller. This avoids a second RPC in the case of the
+	 * common query-alloc-retrieve cycle for xattrs.
+	 *
+	 * Note that xattr_len is always capped to XATTR_SIZE_MAX.
+	 */
+
+	nfs4_xattr_cache_add(inode, name, NULL, pages, res.xattr_len);
+
+	if (buflen) {
+		if (res.xattr_len > buflen)
+			return -ERANGE;
+		_copy_from_pages(buf, pages, 0, res.xattr_len);
+	}
+
+	np = DIV_ROUND_UP(res.xattr_len, PAGE_SIZE);
+	while (--np >= 0)
+		__free_page(pages[np]);
+
+	return res.xattr_len;
+}
+
+static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf,
+				 size_t buflen, u64 *cookiep, bool *eofp)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct page **pages;
+	struct nfs42_listxattrsargs arg = {
+		.fh		= NFS_FH(inode),
+		.cookie		= *cookiep,
+	};
+	struct nfs42_listxattrsres res = {
+		.eof = false,
+		.xattr_buf = buf,
+		.xattr_len = buflen,
+	};
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_LISTXATTRS],
+		.rpc_argp	= &arg,
+		.rpc_resp	= &res,
+	};
+	u32 xdrlen;
+	int ret, np;
+
+
+	res.scratch = alloc_page(GFP_KERNEL);
+	if (!res.scratch)
+		return -ENOMEM;
+
+	xdrlen = nfs42_listxattr_xdrsize(buflen);
+	if (xdrlen > server->lxasize)
+		xdrlen = server->lxasize;
+	np = xdrlen / PAGE_SIZE + 1;
+
+	pages = kcalloc(np, sizeof(struct page *), GFP_KERNEL);
+	if (pages == NULL) {
+		__free_page(res.scratch);
+		return -ENOMEM;
+	}
+
+	arg.xattr_pages = pages;
+	arg.count = xdrlen;
+
+	ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args,
+	    &res.seq_res, 0);
+
+	if (ret >= 0) {
+		ret = res.copied;
+		*cookiep = res.cookie;
+		*eofp = res.eof;
+	}
+
+	while (--np >= 0) {
+		if (pages[np])
+			__free_page(pages[np]);
+	}
+
+	__free_page(res.scratch);
+	kfree(pages);
+
+	return ret;
+
+}
+
+ssize_t nfs42_proc_getxattr(struct inode *inode, const char *name,
+			      void *buf, size_t buflen)
+{
+	struct nfs4_exception exception = { };
+	ssize_t err;
+
+	do {
+		err = _nfs42_proc_getxattr(inode, name, buf, buflen);
+		if (err >= 0)
+			break;
+		err = nfs4_handle_exception(NFS_SERVER(inode), err,
+				&exception);
+	} while (exception.retry);
+
+	return err;
+}
+
+int nfs42_proc_setxattr(struct inode *inode, const char *name,
+			      const void *buf, size_t buflen, int flags)
+{
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = _nfs42_proc_setxattr(inode, name, buf, buflen, flags);
+		if (!err)
+			break;
+		err = nfs4_handle_exception(NFS_SERVER(inode), err,
+				&exception);
+	} while (exception.retry);
+
+	return err;
+}
+
+ssize_t nfs42_proc_listxattrs(struct inode *inode, void *buf,
+			      size_t buflen, u64 *cookiep, bool *eofp)
+{
+	struct nfs4_exception exception = { };
+	ssize_t err;
+
+	do {
+		err = _nfs42_proc_listxattrs(inode, buf, buflen,
+		    cookiep, eofp);
+		if (err >= 0)
+			break;
+		err = nfs4_handle_exception(NFS_SERVER(inode), err,
+				&exception);
+	} while (exception.retry);
+
+	return err;
+}
+
+int nfs42_proc_removexattr(struct inode *inode, const char *name)
+{
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = _nfs42_proc_removexattr(inode, name);
+		if (!err)
+			break;
+		err = nfs4_handle_exception(NFS_SERVER(inode), err,
+				&exception);
+	} while (exception.retry);
+
+	return err;
+}

fs/nfs/nfs4_fs.h

@@ -324,6 +324,13 @@ extern int update_open_stateid(struct nfs4_state *state,
 
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
+extern void nfs4_update_changeattr(struct inode *dir,
+				   struct nfs4_change_info *cinfo,
+				   unsigned long timestamp,
+				   unsigned long cache_validity);
+extern int nfs4_buf_to_pages_noslab(const void *buf, size_t buflen,
+				    struct page **pages);
+
 #if defined(CONFIG_NFS_V4_1)
 extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
 extern int nfs4_proc_create_session(struct nfs_client *, const struct cred *);
@@ -557,6 +564,12 @@ static inline void nfs4_unregister_sysctl(void)
 /* nfs4xdr.c */
 extern const struct rpc_procinfo nfs4_procedures[];
 
+#ifdef CONFIG_NFS_V4_2
+extern const u32 nfs42_maxsetxattr_overhead;
+extern const u32 nfs42_maxgetxattr_overhead;
+extern const u32 nfs42_maxlistxattrs_overhead;
+#endif
+
 struct nfs4_mount_data;
 
 /* callback_xdr.c */
@@ -613,12 +626,34 @@ static inline bool nfs4_state_match_open_stateid_other(const struct nfs4_state *
 		nfs4_stateid_match_other(&state->open_stateid, stateid);
 }
 
+/* nfs42xattr.c */
+#ifdef CONFIG_NFS_V4_2
+extern int __init nfs4_xattr_cache_init(void);
+extern void nfs4_xattr_cache_exit(void);
+extern void nfs4_xattr_cache_add(struct inode *inode, const char *name,
+				 const char *buf, struct page **pages,
+				 ssize_t buflen);
+extern void nfs4_xattr_cache_remove(struct inode *inode, const char *name);
+extern ssize_t nfs4_xattr_cache_get(struct inode *inode, const char *name,
+				char *buf, ssize_t buflen);
+extern void nfs4_xattr_cache_set_list(struct inode *inode, const char *buf,
+				      ssize_t buflen);
+extern ssize_t nfs4_xattr_cache_list(struct inode *inode, char *buf,
+				     ssize_t buflen);
+extern void nfs4_xattr_cache_zap(struct inode *inode);
 #else
+static inline void nfs4_xattr_cache_zap(struct inode *inode)
+{
+}
+#endif /* CONFIG_NFS_V4_2 */
+
+#else /* CONFIG_NFS_V4 */
 
 #define nfs4_close_state(a, b) do { } while (0)
 #define nfs4_close_sync(a, b) do { } while (0)
 #define nfs4_state_protect(a, b, c, d) do { } while (0)
 #define nfs4_state_protect_write(a, b, c, d) do { } while (0)
 
+
 #endif /* CONFIG_NFS_V4 */
 #endif /* __LINUX_FS_NFS_NFS4_FS.H */

fs/nfs/nfs4client.c

@@ -880,7 +880,7 @@ static int nfs4_set_client(struct nfs_server *server,
 
 	if (minorversion == 0)
 		__set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags);
-	else if (proto == XPRT_TRANSPORT_TCP)
+	if (proto == XPRT_TRANSPORT_TCP)
 		cl_init.nconnect = nconnect;
 
 	if (server->flags & NFS_MOUNT_NORESVPORT)
@@ -992,6 +992,36 @@ static void nfs4_session_limit_rwsize(struct nfs_server *server)
 #endif /* CONFIG_NFS_V4_1 */
 }
 
+/*
+ * Limit xattr sizes using the channel attributes.
+ */
+static void nfs4_session_limit_xasize(struct nfs_server *server)
+{
+#ifdef CONFIG_NFS_V4_2
+	struct nfs4_session *sess;
+	u32 server_gxa_sz;
+	u32 server_sxa_sz;
+	u32 server_lxa_sz;
+
+	if (!nfs4_has_session(server->nfs_client))
+		return;
+
+	sess = server->nfs_client->cl_session;
+
+	server_gxa_sz = sess->fc_attrs.max_resp_sz - nfs42_maxgetxattr_overhead;
+	server_sxa_sz = sess->fc_attrs.max_rqst_sz - nfs42_maxsetxattr_overhead;
+	server_lxa_sz = sess->fc_attrs.max_resp_sz -
+	    nfs42_maxlistxattrs_overhead;
+
+	if (server->gxasize > server_gxa_sz)
+		server->gxasize = server_gxa_sz;
+	if (server->sxasize > server_sxa_sz)
+		server->sxasize = server_sxa_sz;
+	if (server->lxasize > server_lxa_sz)
+		server->lxasize = server_lxa_sz;
+#endif
+}
+
 static int nfs4_server_common_setup(struct nfs_server *server,
 		struct nfs_fh *mntfh, bool auth_probe)
 {
@@ -1039,6 +1069,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 		goto out;
 
 	nfs4_session_limit_rwsize(server);
+	nfs4_session_limit_xasize(server);
 
 	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
 		server->namelen = NFS4_MAXNAMLEN;

fs/nfs/nfs4file.c

@@ -110,6 +110,7 @@ static int
 nfs4_file_flush(struct file *file, fl_owner_t id)
 {
 	struct inode	*inode = file_inode(file);
+	errseq_t since;
 
 	dprintk("NFS: flush(%pD2)\n", file);
 
@@ -125,7 +126,9 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
 		return filemap_fdatawrite(file->f_mapping);
 
 	/* 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);
 }
 
 #ifdef CONFIG_NFS_V4_2

fs/nfs/nfs4super.c

@@ -69,6 +69,7 @@ static void nfs4_evict_inode(struct inode *inode)
 	pnfs_destroy_layout(NFS_I(inode));
 	/* First call standard NFS clear_inode() code */
 	nfs_clear_inode(inode);
+	nfs4_xattr_cache_zap(inode);
 }
 
 struct nfs_referral_count {
@@ -268,6 +269,12 @@ static int __init init_nfs_v4(void)
 	if (err)
 		goto out1;
 
+#ifdef CONFIG_NFS_V4_2
+	err = nfs4_xattr_cache_init();
+	if (err)
+		goto out2;
+#endif
+
 	err = nfs4_register_sysctl();
 	if (err)
 		goto out2;
@@ -288,6 +295,9 @@ static void __exit exit_nfs_v4(void)
 	nfs4_pnfs_v3_ds_connect_unload();
 
 	unregister_nfs_version(&nfs_v4);
+#ifdef CONFIG_NFS_V4_2
+	nfs4_xattr_cache_exit();
+#endif
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();
 	nfs_dns_resolver_destroy();

fs/nfs/nfs4trace.h

@@ -1727,6 +1727,13 @@ DEFINE_NFS4_IDMAP_EVENT(nfs4_map_group_to_gid);
 DEFINE_NFS4_IDMAP_EVENT(nfs4_map_uid_to_name);
 DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group);
 
+#ifdef CONFIG_NFS_V4_1
+#define NFS4_LSEG_LAYOUT_STATEID_HASH(lseg) \
+	(lseg ? nfs_stateid_hash(&lseg->pls_layout->plh_stateid) : 0)
+#else
+#define NFS4_LSEG_LAYOUT_STATEID_HASH(lseg) (0)
+#endif
+
 DECLARE_EVENT_CLASS(nfs4_read_event,
 		TP_PROTO(
 			const struct nfs_pgio_header *hdr,
@@ -1745,6 +1752,8 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 			__field(unsigned long, error)
 			__field(int, stateid_seq)
 			__field(u32, stateid_hash)
+			__field(int, layoutstateid_seq)
+			__field(u32, layoutstateid_hash)
 		),
 
 		TP_fast_assign(
@@ -1754,6 +1763,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 						  hdr->args.fh : &nfsi->fh;
 			const struct nfs4_state *state =
 				hdr->args.context->state;
+			const struct pnfs_layout_segment *lseg = hdr->lseg;
 
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = nfsi->fileid;
@@ -1766,11 +1776,15 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 				be32_to_cpu(state->stateid.seqid);
 			__entry->stateid_hash =
 				nfs_stateid_hash(&state->stateid);
+			__entry->layoutstateid_seq = lseg ? lseg->pls_seq : 0;
+			__entry->layoutstateid_hash =
+				NFS4_LSEG_LAYOUT_STATEID_HASH(lseg);
 		),
 
 		TP_printk(
 			"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%u res=%u stateid=%d:0x%08x",
+			"offset=%lld count=%u res=%u stateid=%d:0x%08x "
+			"layoutstateid=%d:0x%08x",
 			-__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -1778,7 +1792,8 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 			__entry->fhandle,
 			(long long)__entry->offset,
 			__entry->arg_count, __entry->res_count,
-			__entry->stateid_seq, __entry->stateid_hash
+			__entry->stateid_seq, __entry->stateid_hash,
+			__entry->layoutstateid_seq, __entry->layoutstateid_hash
 		)
 );
 #define DEFINE_NFS4_READ_EVENT(name) \
@@ -1811,6 +1826,8 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 			__field(unsigned long, error)
 			__field(int, stateid_seq)
 			__field(u32, stateid_hash)
+			__field(int, layoutstateid_seq)
+			__field(u32, layoutstateid_hash)
 		),
 
 		TP_fast_assign(
@@ -1820,6 +1837,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 						  hdr->args.fh : &nfsi->fh;
 			const struct nfs4_state *state =
 				hdr->args.context->state;
+			const struct pnfs_layout_segment *lseg = hdr->lseg;
 
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = nfsi->fileid;
@@ -1832,11 +1850,15 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 				be32_to_cpu(state->stateid.seqid);
 			__entry->stateid_hash =
 				nfs_stateid_hash(&state->stateid);
+			__entry->layoutstateid_seq = lseg ? lseg->pls_seq : 0;
+			__entry->layoutstateid_hash =
+				NFS4_LSEG_LAYOUT_STATEID_HASH(lseg);
 		),
 
 		TP_printk(
 			"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%u res=%u stateid=%d:0x%08x",
+			"offset=%lld count=%u res=%u stateid=%d:0x%08x "
+			"layoutstateid=%d:0x%08x",
 			-__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
@@ -1844,7 +1866,8 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 			__entry->fhandle,
 			(long long)__entry->offset,
 			__entry->arg_count, __entry->res_count,
-			__entry->stateid_seq, __entry->stateid_hash
+			__entry->stateid_seq, __entry->stateid_hash,
+			__entry->layoutstateid_seq, __entry->layoutstateid_hash
 		)
 );
 
@@ -1875,6 +1898,8 @@ DECLARE_EVENT_CLASS(nfs4_commit_event,
 			__field(unsigned long, error)
 			__field(loff_t, offset)
 			__field(u32, count)
+			__field(int, layoutstateid_seq)
+			__field(u32, layoutstateid_hash)
 		),
 
 		TP_fast_assign(
@@ -1882,6 +1907,7 @@ DECLARE_EVENT_CLASS(nfs4_commit_event,
 			const struct nfs_inode *nfsi = NFS_I(inode);
 			const struct nfs_fh *fh = data->args.fh ?
 						  data->args.fh : &nfsi->fh;
+			const struct pnfs_layout_segment *lseg = data->lseg;
 
 			__entry->dev = inode->i_sb->s_dev;
 			__entry->fileid = nfsi->fileid;
@@ -1889,18 +1915,22 @@ DECLARE_EVENT_CLASS(nfs4_commit_event,
 			__entry->offset = data->args.offset;
 			__entry->count = data->args.count;
 			__entry->error = error < 0 ? -error : 0;
+			__entry->layoutstateid_seq = lseg ? lseg->pls_seq : 0;
+			__entry->layoutstateid_hash =
+				NFS4_LSEG_LAYOUT_STATEID_HASH(lseg);
 		),
 
 		TP_printk(
 			"error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x "
-			"offset=%lld count=%u",
+			"offset=%lld count=%u layoutstateid=%d:0x%08x",
 			-__entry->error,
 			show_nfsv4_errors(__entry->error),
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
 			(long long)__entry->offset,
-			__entry->count
+			__entry->count,
+			__entry->layoutstateid_seq, __entry->layoutstateid_hash
 		)
 );
 #define DEFINE_NFS4_COMMIT_EVENT(name) \
@@ -1993,7 +2023,9 @@ TRACE_EVENT(nfs4_layoutget,
 
 DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutcommit);
 DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn);
-DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn_on_close);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layouterror);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutstats);
 
 TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_UNKNOWN);
 TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_NO_PNFS);

fs/nfs/nfs4xdr.c

@@ -4166,7 +4166,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap,
 			return -EIO;
 		if (len < NFS4_MAXLABELLEN) {
 			if (label) {
-				memcpy(label->label, p, len);
+				if (label->len) {
+					if (label->len < len)
+						return -ERANGE;
+					memcpy(label->label, p, len);
+				}
 				label->len = len;
 				label->pi = pi;
 				label->lfs = lfs;
@@ -4201,6 +4205,26 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str
 	return status;
 }
 
+static int decode_attr_xattrsupport(struct xdr_stream *xdr, uint32_t *bitmap,
+				    uint32_t *res)
+{
+	__be32 *p;
+
+	*res = 0;
+	if (unlikely(bitmap[2] & (FATTR4_WORD2_XATTR_SUPPORT - 1U)))
+		return -EIO;
+	if (likely(bitmap[2] & FATTR4_WORD2_XATTR_SUPPORT)) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			return -EIO;
+		*res = be32_to_cpup(p);
+		bitmap[2] &= ~FATTR4_WORD2_XATTR_SUPPORT;
+	}
+	dprintk("%s: XATTR support=%s\n", __func__,
+		*res == 0 ? "false" : "true");
+	return 0;
+}
+
 static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen)
 {
 	unsigned int attrwords = XDR_QUADLEN(attrlen);
@@ -4855,6 +4879,11 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	if (status)
 		goto xdr_error;
 
+	status = decode_attr_xattrsupport(xdr, bitmap,
+					  &fsinfo->xattr_support);
+	if (status)
+		goto xdr_error;
+
 	status = verify_attr_len(xdr, savep, attrlen);
 xdr_error:
 	dprintk("%s: xdr returned %d!\n", __func__, -status);
@@ -5227,7 +5256,7 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req)
 	 * The XDR encode routine has set things up so that
 	 * the link text will be copied directly into the
 	 * buffer.  We just have to do overflow-checking,
-	 * and and null-terminate the text (the VFS expects
+	 * and null-terminate the text (the VFS expects
 	 * null-termination).
 	 */
 	xdr_terminate_string(rcvbuf, len);
@@ -7456,6 +7485,8 @@ static struct {
 	{ NFS4ERR_SYMLINK,	-ELOOP		},
 	{ NFS4ERR_OP_ILLEGAL,	-EOPNOTSUPP	},
 	{ NFS4ERR_DEADLOCK,	-EDEADLK	},
+	{ NFS4ERR_NOXATTR,	-ENODATA	},
+	{ NFS4ERR_XATTR2BIG,	-E2BIG		},
 	{ -1,			-EIO		}
 };
 
@@ -7584,6 +7615,10 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(COPY_NOTIFY,	enc_copy_notify,	dec_copy_notify),
 	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC42(LAYOUTERROR,	enc_layouterror,	dec_layouterror),
+	PROC42(GETXATTR,	enc_getxattr,		dec_getxattr),
+	PROC42(SETXATTR,	enc_setxattr,		dec_setxattr),
+	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
+	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];

fs/nfs/nfstrace.h

@@ -59,7 +59,8 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
 			{ NFS_INO_INVALID_CTIME, "INVALID_CTIME" }, \
 			{ NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \
 			{ NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \
-			{ NFS_INO_INVALID_OTHER, "INVALID_OTHER" })
+			{ NFS_INO_INVALID_OTHER, "INVALID_OTHER" }, \
+			{ NFS_INO_INVALID_XATTR, "INVALID_XATTR" })
 
 TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS);
 TRACE_DEFINE_ENUM(NFS_INO_STALE);

fs/nfs/pnfs.c

@@ -1226,31 +1226,27 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo,
 	return status;
 }
 
+static bool
+pnfs_layout_segments_returnable(struct pnfs_layout_hdr *lo,
+				enum pnfs_iomode iomode,
+				u32 seq)
+{
+	struct pnfs_layout_range recall_range = {
+		.length = NFS4_MAX_UINT64,
+		.iomode = iomode,
+	};
+	return pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+					       &recall_range, seq) != -EBUSY;
+}
+
 /* Return true if layoutreturn is needed */
 static bool
 pnfs_layout_need_return(struct pnfs_layout_hdr *lo)
 {
-	struct pnfs_layout_segment *s;
-	enum pnfs_iomode iomode;
-	u32 seq;
-
 	if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
 		return false;
-
-	seq = lo->plh_return_seq;
-	iomode = lo->plh_return_iomode;
-
-	/* Defer layoutreturn until all recalled lsegs are done */
-	list_for_each_entry(s, &lo->plh_segs, pls_list) {
-		if (seq && pnfs_seqid_is_newer(s->pls_seq, seq))
-			continue;
-		if (iomode != IOMODE_ANY && s->pls_range.iomode != iomode)
-			continue;
-		if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
-			return false;
-	}
-
-	return true;
+	return pnfs_layout_segments_returnable(lo, lo->plh_return_iomode,
+					       lo->plh_return_seq);
 }
 
 static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
@@ -1549,12 +1545,12 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 	default:
 		arg_stateid = &args->stateid;
 	}
+	trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret);
 	pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range,
 			res_stateid);
 	if (ld_private && ld_private->ops && ld_private->ops->free)
 		ld_private->ops->free(ld_private);
 	pnfs_put_layout_hdr(lo);
-	trace_nfs4_layoutreturn_on_close(args->inode, 0);
 }
 
 bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
@@ -2392,16 +2388,6 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 	return ERR_PTR(-EAGAIN);
 }
 
-static int
-mark_lseg_invalid_or_return(struct pnfs_layout_segment *lseg,
-		struct list_head *tmp_list)
-{
-	if (!mark_lseg_invalid(lseg, tmp_list))
-		return 0;
-	pnfs_cache_lseg_for_layoutreturn(lseg->pls_layout, lseg);
-	return 1;
-}
-
 /**
  * pnfs_mark_matching_lsegs_return - Free or return matching layout segments
  * @lo: pointer to layout header
@@ -2438,7 +2424,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				lseg, lseg->pls_range.iomode,
 				lseg->pls_range.offset,
 				lseg->pls_range.length);
-			if (mark_lseg_invalid_or_return(lseg, tmp_list))
+			if (mark_lseg_invalid(lseg, tmp_list))
 				continue;
 			remaining++;
 			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
@@ -2953,7 +2939,8 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
 }
 
 /* Resend all requests through pnfs. */
-void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
+void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr,
+			   unsigned int mirror_idx)
 {
 	struct nfs_pageio_descriptor pgio;
 
@@ -2964,6 +2951,7 @@ void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
 
 		nfs_pageio_init_read(&pgio, hdr->inode, false,
 					hdr->completion_ops);
+		pgio.pg_mirror_idx = mirror_idx;
 		hdr->task.tk_status = nfs_pageio_resend(&pgio, hdr);
 	}
 }

fs/nfs/pnfs.h

@@ -311,7 +311,7 @@ int _pnfs_return_layout(struct inode *);
 int pnfs_commit_and_return_layout(struct inode *);
 void pnfs_ld_write_done(struct nfs_pgio_header *);
 void pnfs_ld_read_done(struct nfs_pgio_header *);
-void pnfs_read_resend_pnfs(struct nfs_pgio_header *);
+void pnfs_read_resend_pnfs(struct nfs_pgio_header *, unsigned int mirror_idx);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,

include/linux/nfs4.h

@@ -553,6 +553,11 @@ enum {
 	NFSPROC4_CLNT_LAYOUTERROR,
 
 	NFSPROC4_CLNT_COPY_NOTIFY,
+
+	NFSPROC4_CLNT_GETXATTR,
+	NFSPROC4_CLNT_SETXATTR,
+	NFSPROC4_CLNT_LISTXATTRS,
+	NFSPROC4_CLNT_REMOVEXATTR,
 };
 
 /* nfs41 types */

include/linux/nfs_fs.h

@@ -102,6 +102,8 @@ struct nfs_delegation;
 
 struct posix_acl;
 
+struct nfs4_xattr_cache;
+
 /*
  * nfs fs inode data in memory
  */
@@ -188,6 +190,10 @@ struct nfs_inode {
 	struct fscache_cookie	*fscache;
 #endif
 	struct inode		vfs_inode;
+
+#ifdef CONFIG_NFS_V4_2
+	struct nfs4_xattr_cache *xattr_cache;
+#endif
 };
 
 struct nfs4_copy_state {
@@ -212,6 +218,9 @@ struct nfs4_copy_state {
 #define NFS_ACCESS_EXTEND      0x0008
 #define NFS_ACCESS_DELETE      0x0010
 #define NFS_ACCESS_EXECUTE     0x0020
+#define NFS_ACCESS_XAREAD      0x0040
+#define NFS_ACCESS_XAWRITE     0x0080
+#define NFS_ACCESS_XALIST      0x0100
 
 /*
  * Cache validity bit flags
@@ -231,6 +240,7 @@ struct nfs4_copy_state {
 #define NFS_INO_DATA_INVAL_DEFER	\
 				BIT(13)		/* Deferred cache invalidation */
 #define NFS_INO_INVALID_BLOCKS	BIT(14)         /* cached blocks are invalid */
+#define NFS_INO_INVALID_XATTR	BIT(15)		/* xattrs are invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
@@ -490,6 +500,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh,
 			struct nfs_fattr *fattr, struct nfs4_label *label);
 extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags);
 extern void nfs_access_zap_cache(struct inode *inode);
+extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res,
+				 bool may_block);
 
 /*
  * linux/fs/nfs/symlink.c

include/linux/nfs_fs_sb.h

@@ -163,6 +163,11 @@ struct nfs_server {
 	unsigned int		dtsize;		/* readdir size */
 	unsigned short		port;		/* "port=" setting */
 	unsigned int		bsize;		/* server block size */
+#ifdef CONFIG_NFS_V4_2
+	unsigned int		gxasize;	/* getxattr size */
+	unsigned int		sxasize;	/* setxattr size */
+	unsigned int		lxasize;	/* listxattr size */
+#endif
 	unsigned int		acregmin;	/* attr cache timeouts */
 	unsigned int		acregmax;
 	unsigned int		acdirmin;
@@ -281,5 +286,6 @@ struct nfs_server {
 #define NFS_CAP_OFFLOAD_CANCEL	(1U << 25)
 #define NFS_CAP_LAYOUTERROR	(1U << 26)
 #define NFS_CAP_COPY_NOTIFY	(1U << 27)
+#define NFS_CAP_XATTR		(1U << 28)
 
 #endif

include/linux/nfs_xdr.h

@@ -150,6 +150,7 @@ struct nfs_fsinfo {
 	__u32			layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */
 	__u32			blksize; /* preferred pnfs io block size */
 	__u32			clone_blksize; /* granularity of a CLONE operation */
+	__u32			xattr_support; /* User xattrs supported */
 };
 
 struct nfs_fsstat {
@@ -1497,7 +1498,64 @@ struct nfs42_seek_res {
 	u32	sr_eof;
 	u64	sr_offset;
 };
-#endif
+
+struct nfs42_setxattrargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	const char			*xattr_name;
+	u32				xattr_flags;
+	size_t				xattr_len;
+	struct page			**xattr_pages;
+};
+
+struct nfs42_setxattrres {
+	struct nfs4_sequence_res	seq_res;
+	struct nfs4_change_info		cinfo;
+};
+
+struct nfs42_getxattrargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	const char			*xattr_name;
+	size_t				xattr_len;
+	struct page			**xattr_pages;
+};
+
+struct nfs42_getxattrres {
+	struct nfs4_sequence_res	seq_res;
+	size_t				xattr_len;
+};
+
+struct nfs42_listxattrsargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	u32				count;
+	u64				cookie;
+	struct page			**xattr_pages;
+};
+
+struct nfs42_listxattrsres {
+	struct nfs4_sequence_res	seq_res;
+	struct page			*scratch;
+	void				*xattr_buf;
+	size_t				xattr_len;
+	u64				cookie;
+	bool				eof;
+	size_t				copied;
+};
+
+struct nfs42_removexattrargs {
+	struct nfs4_sequence_args	seq_args;
+	struct nfs_fh			*fh;
+	const char			*xattr_name;
+};
+
+struct nfs42_removexattrres {
+	struct nfs4_sequence_res	seq_res;
+	struct nfs4_change_info		cinfo;
+};
+
+#endif /* CONFIG_NFS_V4_2 */
 
 struct nfs_page;
 

include/linux/sunrpc/xprt.h

@@ -101,6 +101,7 @@ struct rpc_rqst {
 							 * used in the softirq.
 							 */
 	unsigned long		rq_majortimeo;	/* major timeout alarm */
+	unsigned long		rq_minortimeo;	/* minor timeout alarm */
 	unsigned long		rq_timeout;	/* Current timeout value */
 	ktime_t			rq_rtt;		/* round-trip time */
 	unsigned int		rq_retries;	/* # of retries */

include/uapi/linux/nfs_fs.h

@@ -56,6 +56,7 @@
 #define NFSDBG_PNFS		0x1000
 #define NFSDBG_PNFS_LD		0x2000
 #define NFSDBG_STATE		0x4000
+#define NFSDBG_XATTRCACHE	0x8000
 #define NFSDBG_ALL		0xFFFF
 
 

net/sunrpc/rpc_pipe.c

@@ -1510,6 +1510,6 @@ int register_rpc_pipefs(void)
 void unregister_rpc_pipefs(void)
 {
 	rpc_clients_notifier_unregister();
-	kmem_cache_destroy(rpc_inode_cachep);
 	unregister_filesystem(&rpc_pipe_fs_type);
+	kmem_cache_destroy(rpc_inode_cachep);
 }

net/sunrpc/xprt.c

@@ -607,6 +607,11 @@ static void xprt_reset_majortimeo(struct rpc_rqst *req)
 	req->rq_majortimeo += xprt_calc_majortimeo(req);
 }
 
+static void xprt_reset_minortimeo(struct rpc_rqst *req)
+{
+	req->rq_minortimeo += req->rq_timeout;
+}
+
 static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
 {
 	unsigned long time_init;
@@ -618,6 +623,7 @@ static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req)
 		time_init = xprt_abs_ktime_to_jiffies(task->tk_start);
 	req->rq_timeout = task->tk_client->cl_timeout->to_initval;
 	req->rq_majortimeo = time_init + xprt_calc_majortimeo(req);
+	req->rq_minortimeo = time_init + req->rq_timeout;
 }
 
 /**
@@ -631,6 +637,8 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
 	int status = 0;
 
+	if (time_before(jiffies, req->rq_minortimeo))
+		return status;
 	if (time_before(jiffies, req->rq_majortimeo)) {
 		if (to->to_exponential)
 			req->rq_timeout <<= 1;
@@ -649,6 +657,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 		spin_unlock(&xprt->transport_lock);
 		status = -ETIMEDOUT;
 	}
+	xprt_reset_minortimeo(req);
 
 	if (req->rq_timeout == 0) {
 		printk(KERN_WARNING "xprt_adjust_timeout: rq_timeout = 0!\n");