NFS client updates for Linux 6.17

Highlights include:
 
 Stable fixes:
 - NFS don't inherit NFS filesystem capabilities when crossing from one
   filesystem to another.
 
 Bugfixes:
 - NFS wakeup of __nfs_lookup_revalidate() needs memory barriers.
 - NFS improve bounds checking in nfs_fh_to_dentry().
 - NFS Fix allocation errors when writing to a NFS file backed loopback
   device.
 - NFSv4: More listxattr fixes
 - SUNRPC: fix client handling of TLS alerts.
 - pNFS block/scsi layout fix for an uninitialised pointer dereference.
 - pNFS block/scsi layout fixes for the extent encoding, stripe mapping,
   and disk offset overflows.
 - pNFS layoutcommit work around for RPC size limitations.
 - pNFS/flexfiles avoid looping when handling fatal errors after layoutget.
 - localio: fix various race conditions.
 
 Features and cleanups:
 - Add NFSv4 support for retrieving the btime.
 - NFS: Allow folio migration for the case of mode == MIGRATE_SYNC.
 - NFS: Support using a kernel keyring to store TLS certificates.
 - NFSv4: Speed up delegation lookup using a hash table.
 - Assorted cleanups to remove unused variables and struct fields.
 - Assorted new tracepoints to improve debugging.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEESQctxSBg8JpV8KqEZwvnipYKAPIFAmiWBC8ACgkQZwvnipYK
 APKTfRAAn3ETKN15+yR6wYr/wiibaL6sRzQVo8OzFSI9hEVxljX6kK2HEHXIV93T
 F8bjUMB24KK+Eim8zIeLf4Ke7ldbRqtbiYLJox/I12TtQ6yaiFF+xDm7Fyc7UwcT
 ZUl1UnGeNY30RfQ1n8O4O/suBOsTJy1rpWBWynGeQZLiNHFVDoxH4OgCXGZ5579p
 3GACtToDDH9lgCBbKLM3J0nrcW5Or6BidFxT+zN/FXqeroepuvEcloiwJY7N4f/o
 DW436v7ep92WlaJfuypeMmdusx6+vVaYJEKw+B+UjS3tRjbDmhj2FL3su4dQVCqU
 JVW7TwGFL2zwfjTZjfp43ACN16goqRhX7DnTQkgD1mDnnhENqOsa0rqyIS3Wla4d
 W9phfGmOo2FwuVOUXH2L4k7cfPIsktsZ0s/xg+5UfcsoG2yxUxnY9HaWQGFw6fnN
 Fr9B7gUmaO6o1qpZ3emjecoOdQM9IqxMo39P9/72J9pWFstO9Js/kmGXcfsDo2IE
 z2ZYd+roj2ylcLD9mCJ94tjNsAx0ytvUl1fxNFTRLToQ3Nti+jNy22i4jrCgWfyW
 5jwCjjO87CJlJC0kixEPtQXAB6HQSraZw3Qmok1Ywez3fp4+j+QDFYP7OPJPQ0LY
 C3R1uzvUQKqsbsE8cwYQBrG0VNzZrET6x1dxunVtcYGOkU8s4YA=
 =HCFp
 -----END PGP SIGNATURE-----

Merge tag 'nfs-for-6.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:
   - don't inherit NFS filesystem capabilities when crossing from one
     filesystem to another

  Bugfixes:
   - NFS wakeup of __nfs_lookup_revalidate() needs memory barriers
   - NFS improve bounds checking in nfs_fh_to_dentry()
   - NFS Fix allocation errors when writing to a NFS file backed
     loopback device
   - NFSv4: More listxattr fixes
   - SUNRPC: fix client handling of TLS alerts
   - pNFS block/scsi layout fix for an uninitialised pointer
     dereference
   - pNFS block/scsi layout fixes for the extent encoding, stripe
     mapping, and disk offset overflows
   - pNFS layoutcommit work around for RPC size limitations
   - pNFS/flexfiles avoid looping when handling fatal errors after
     layoutget
   - localio: fix various race conditions

  Features and cleanups:
   - Add NFSv4 support for retrieving the btime
   - NFS: Allow folio migration for the case of mode == MIGRATE_SYNC
   - NFS: Support using a kernel keyring to store TLS certificates
   - NFSv4: Speed up delegation lookup using a hash table
   - Assorted cleanups to remove unused variables and struct fields
   - Assorted new tracepoints to improve debugging"

* tag 'nfs-for-6.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (44 commits)
  NFS/localio: nfs_uuid_put() fix the wake up after unlinking the file
  NFS/localio: nfs_uuid_put() fix races with nfs_open/close_local_fh()
  NFS/localio: nfs_close_local_fh() fix check for file closed
  NFSv4: Remove duplicate lookups, capability probes and fsinfo calls
  NFS: Fix the setting of capabilities when automounting a new filesystem
  sunrpc: fix client side handling of tls alerts
  nfs/localio: use read_seqbegin() rather than read_seqbegin_or_lock()
  NFS: Fixup allocation flags for nfsiod's __GFP_NORETRY
  NFSv4.2: another fix for listxattr
  NFS: Fix filehandle bounds checking in nfs_fh_to_dentry()
  SUNRPC: Silence warnings about parameters not being described
  NFS: Clean up pnfs_put_layout_hdr()/pnfs_destroy_layout_final()
  NFS: Fix wakeup of __nfs_lookup_revalidate() in unblock_revalidate()
  NFS: use a hash table for delegation lookup
  NFS: track active delegations per-server
  NFS: move the delegation_watermark module parameter
  NFS: cleanup nfs_inode_reclaim_delegation
  NFS: cleanup error handling in nfs4_server_common_setup
  pNFS/flexfiles: don't attempt pnfs on fatal DS errors
  NFS: drop __exit from nfs_exit_keyring
  ...

fs/nfs/blocklayout/blocklayout.c

@@ -149,8 +149,8 @@ do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect,
 
 	/* limit length to what the device mapping allows */
 	end = disk_addr + *len;
-	if (end >= map->start + map->len)
+	if (end >= map->disk_offset + map->len)
-		*len = map->start + map->len - disk_addr;
+		*len = map->disk_offset + map->len - disk_addr;
 
 retry:
 	if (!bio) {

fs/nfs/blocklayout/dev.c

@@ -257,10 +257,11 @@ static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
 	struct pnfs_block_dev *child;
 	u64 chunk;
 	u32 chunk_idx;
+	u64 disk_chunk;
 	u64 disk_offset;
 
 	chunk = div_u64(offset, dev->chunk_size);
-	div_u64_rem(chunk, dev->nr_children, &chunk_idx);
+	disk_chunk = div_u64_rem(chunk, dev->nr_children, &chunk_idx);
 
 	if (chunk_idx >= dev->nr_children) {
 		dprintk("%s: invalid chunk idx %d (%lld/%lld)\n",
@@ -273,7 +274,7 @@ static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
 	offset = chunk * dev->chunk_size;
 
 	/* disk offset of the stripe */
-	disk_offset = div_u64(offset, dev->nr_children);
+	disk_offset = disk_chunk * dev->chunk_size;
 
 	child = &dev->children[chunk_idx];
 	child->map(child, disk_offset, map);

fs/nfs/blocklayout/extent_tree.c

@@ -6,6 +6,7 @@
 #include <linux/vmalloc.h>
 
 #include "blocklayout.h"
+#include "../nfs4trace.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
@@ -520,10 +521,71 @@ static __be32 *encode_scsi_range(struct pnfs_block_extent *be, __be32 *p)
 	return xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
 }
 
-static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+/**
+ * ext_tree_try_encode_commit - try to encode all extents into the buffer
+ * @bl: pointer to the layout
+ * @p: pointer to the output buffer
+ * @buffer_size: size of the output buffer
+ * @count: output pointer to the number of encoded extents
+ * @lastbyte: output pointer to the last written byte
+ *
+ * Return values:
+ *   %0: Success, all required extents encoded, outputs are valid
+ *   %-ENOSPC: Buffer too small, nothing encoded, outputs are invalid
+ */
+static int
+ext_tree_try_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 		size_t buffer_size, size_t *count, __u64 *lastbyte)
 {
 	struct pnfs_block_extent *be;
+
+	spin_lock(&bl->bl_ext_lock);
+	for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+		if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+		    be->be_tag != EXTENT_WRITTEN)
+			continue;
+
+		(*count)++;
+		if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
+			spin_unlock(&bl->bl_ext_lock);
+			return -ENOSPC;
+		}
+	}
+	for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+		if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+		    be->be_tag != EXTENT_WRITTEN)
+			continue;
+
+		if (bl->bl_scsi_layout)
+			p = encode_scsi_range(be, p);
+		else
+			p = encode_block_extent(be, p);
+		be->be_tag = EXTENT_COMMITTING;
+	}
+	*lastbyte = (bl->bl_lwb != 0) ? bl->bl_lwb - 1 : U64_MAX;
+	bl->bl_lwb = 0;
+	spin_unlock(&bl->bl_ext_lock);
+
+	return 0;
+}
+
+/**
+ * ext_tree_encode_commit - encode as much as possible extents into the buffer
+ * @bl: pointer to the layout
+ * @p: pointer to the output buffer
+ * @buffer_size: size of the output buffer
+ * @count: output pointer to the number of encoded extents
+ * @lastbyte: output pointer to the last written byte
+ *
+ * Return values:
+ *   %0: Success, all required extents encoded, outputs are valid
+ *   %-ENOSPC: Buffer too small, some extents are encoded, outputs are valid
+ */
+static int
+ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+		size_t buffer_size, size_t *count, __u64 *lastbyte)
+{
+	struct pnfs_block_extent *be, *be_prev;
 	int ret = 0;
 
 	spin_lock(&bl->bl_ext_lock);
@@ -534,9 +596,9 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 
 		(*count)++;
 		if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
-			/* keep counting.. */
+			(*count)--;
 			ret = -ENOSPC;
-			continue;
+			break;
 		}
 
 		if (bl->bl_scsi_layout)
@@ -544,14 +606,30 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 		else
 			p = encode_block_extent(be, p);
 		be->be_tag = EXTENT_COMMITTING;
+		be_prev = be;
+	}
+	if (!ret) {
+		*lastbyte = (bl->bl_lwb != 0) ? bl->bl_lwb - 1 : U64_MAX;
+		bl->bl_lwb = 0;
+	} else {
+		*lastbyte = be_prev->be_f_offset + be_prev->be_length;
+		*lastbyte <<= SECTOR_SHIFT;
+		*lastbyte -= 1;
 	}
-	*lastbyte = bl->bl_lwb - 1;
-	bl->bl_lwb = 0;
 	spin_unlock(&bl->bl_ext_lock);
 
 	return ret;
 }
 
+/**
+ * ext_tree_prepare_commit - encode extents that need to be committed
+ * @arg: layout commit data
+ *
+ * Return values:
+ *   %0: Success, all required extents are encoded
+ *   %-ENOSPC: Some extents are encoded, but not all, due to RPC size limit
+ *   %-ENOMEM: Out of memory, extents not encoded
+ */
 int
 ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
 {
@@ -560,20 +638,18 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
 	__be32 *start_p;
 	int ret;
 
-	dprintk("%s enter\n", __func__);
-
 	arg->layoutupdate_page = alloc_page(GFP_NOFS);
 	if (!arg->layoutupdate_page)
 		return -ENOMEM;
 	start_p = page_address(arg->layoutupdate_page);
 	arg->layoutupdate_pages = &arg->layoutupdate_page;
 
-retry:
+	ret = ext_tree_try_encode_commit(bl, start_p + 1, buffer_size,
-	ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count, &arg->lastbytewritten);
+			&count, &arg->lastbytewritten);
 	if (unlikely(ret)) {
 		ext_tree_free_commitdata(arg, buffer_size);
 
-		buffer_size = ext_tree_layoutupdate_size(bl, count);
+		buffer_size = NFS_SERVER(arg->inode)->wsize;
 		count = 0;
 
 		arg->layoutupdate_pages =
@@ -588,7 +664,8 @@ retry:
 			return -ENOMEM;
 		}
 
-		goto retry;
+		ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size,
+				&count, &arg->lastbytewritten);
 	}
 
 	*start_p = cpu_to_be32(count);
@@ -607,8 +684,9 @@ retry:
 		}
 	}
 
-	dprintk("%s found %zu ranges\n", __func__, count);
+	trace_bl_ext_tree_prepare_commit(ret, count,
-	return 0;
+			arg->lastbytewritten, !!ret);
+	return ret;
 }
 
 void

fs/nfs/client.c

@@ -682,6 +682,44 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp,
 }
 EXPORT_SYMBOL_GPL(nfs_init_client);
 
+static void nfs4_server_set_init_caps(struct nfs_server *server)
+{
+#if IS_ENABLED(CONFIG_NFS_V4)
+	/* Set the basic capabilities */
+	server->caps = server->nfs_client->cl_mvops->init_caps;
+	if (server->flags & NFS_MOUNT_NORDIRPLUS)
+		server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
+
+	/*
+	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+	 * authentication.
+	 */
+	if (nfs4_disable_idmapping &&
+	    server->client->cl_auth->au_flavor == RPC_AUTH_UNIX)
+		server->caps |= NFS_CAP_UIDGID_NOMAP;
+#endif
+}
+
+void nfs_server_set_init_caps(struct nfs_server *server)
+{
+	switch (server->nfs_client->rpc_ops->version) {
+	case 2:
+		server->caps = NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+		break;
+	case 3:
+		server->caps = NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+		if (!(server->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
+		break;
+	default:
+		nfs4_server_set_init_caps(server);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(nfs_server_set_init_caps);
+
 /*
  * Create a version 2 or 3 client
  */
@@ -726,7 +764,6 @@ static int nfs_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = ctx->flags;
 	server->options = ctx->options;
-	server->caps |= NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
 
 	switch (clp->rpc_ops->version) {
 	case 2:
@@ -762,6 +799,8 @@ static int nfs_init_server(struct nfs_server *server,
 	if (error < 0)
 		goto error;
 
+	nfs_server_set_init_caps(server);
+
 	/* Preserve the values of mount_server-related mount options */
 	if (ctx->mount_server.addrlen) {
 		memcpy(&server->mountd_address, &ctx->mount_server.address,
@@ -814,7 +853,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->wsize = max_rpc_payload;
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
-	server->wpages = (server->wsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
@@ -831,7 +869,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 
 	server->maxfilesize = fsinfo->maxfilesize;
 
-	server->time_delta = fsinfo->time_delta;
 	server->change_attr_type = fsinfo->change_attr_type;
 
 	server->clone_blksize = fsinfo->clone_blksize;
@@ -936,7 +973,6 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour
 	target->acregmax = source->acregmax;
 	target->acdirmin = source->acdirmin;
 	target->acdirmax = source->acdirmax;
-	target->caps = source->caps;
 	target->options = source->options;
 	target->auth_info = source->auth_info;
 	target->port = source->port;
@@ -1007,6 +1043,7 @@ struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->ss_src_copies);
 
 	atomic_set(&server->active, 0);
+	atomic_long_set(&server->nr_active_delegations, 0);
 
 	server->io_stats = nfs_alloc_iostats();
 	if (!server->io_stats) {
@@ -1170,6 +1207,8 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	if (error < 0)
 		goto out_free_server;
 
+	nfs_server_set_init_caps(server);
+
 	/* probe the filesystem info for this server filesystem */
 	error = nfs_probe_server(server, fh);
 	if (error < 0)

fs/nfs/delegation.c

@@ -27,8 +27,15 @@
 
 #define NFS_DEFAULT_DELEGATION_WATERMARK (5000U)
 
-static atomic_long_t nfs_active_delegations;
 static unsigned nfs_delegation_watermark = NFS_DEFAULT_DELEGATION_WATERMARK;
+module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644);
+
+static struct hlist_head *nfs_delegation_hash(struct nfs_server *server,
+		const struct nfs_fh *fhandle)
+{
+	return server->delegation_hash_table +
+		(nfs_fhandle_hash(fhandle) & server->delegation_hash_mask);
+}
 
 static void __nfs_free_delegation(struct nfs_delegation *delegation)
 {
@@ -37,11 +44,12 @@ static void __nfs_free_delegation(struct nfs_delegation *delegation)
 	kfree_rcu(delegation, rcu);
 }
 
-static void nfs_mark_delegation_revoked(struct nfs_delegation *delegation)
+static void nfs_mark_delegation_revoked(struct nfs_server *server,
+		struct nfs_delegation *delegation)
 {
 	if (!test_and_set_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
 		delegation->stateid.type = NFS4_INVALID_STATEID_TYPE;
-		atomic_long_dec(&nfs_active_delegations);
+		atomic_long_dec(&server->nr_active_delegations);
 		if (!test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
 			nfs_clear_verifier_delegated(delegation->inode);
 	}
@@ -59,9 +67,10 @@ static void nfs_put_delegation(struct nfs_delegation *delegation)
 		__nfs_free_delegation(delegation);
 }
 
-static void nfs_free_delegation(struct nfs_delegation *delegation)
+static void nfs_free_delegation(struct nfs_server *server,
+		struct nfs_delegation *delegation)
 {
-	nfs_mark_delegation_revoked(delegation);
+	nfs_mark_delegation_revoked(server, delegation);
 	nfs_put_delegation(delegation);
 }
 
@@ -237,34 +246,34 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
 
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
-	if (delegation != NULL) {
+	if (!delegation) {
-		spin_lock(&delegation->lock);
-		nfs4_stateid_copy(&delegation->stateid, stateid);
-		delegation->type = type;
-		delegation->pagemod_limit = pagemod_limit;
-		oldcred = delegation->cred;
-		delegation->cred = get_cred(cred);
-		switch (deleg_type) {
-		case NFS4_OPEN_DELEGATE_READ_ATTRS_DELEG:
-		case NFS4_OPEN_DELEGATE_WRITE_ATTRS_DELEG:
-			set_bit(NFS_DELEGATION_DELEGTIME, &delegation->flags);
-			break;
-		default:
-			clear_bit(NFS_DELEGATION_DELEGTIME, &delegation->flags);
-		}
-		clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
-		if (test_and_clear_bit(NFS_DELEGATION_REVOKED,
-				       &delegation->flags))
-			atomic_long_inc(&nfs_active_delegations);
-		spin_unlock(&delegation->lock);
-		rcu_read_unlock();
-		put_cred(oldcred);
-		trace_nfs4_reclaim_delegation(inode, type);
-	} else {
 		rcu_read_unlock();
 		nfs_inode_set_delegation(inode, cred, type, stateid,
 					 pagemod_limit, deleg_type);
+		return;
 	}
+
+	spin_lock(&delegation->lock);
+	nfs4_stateid_copy(&delegation->stateid, stateid);
+	delegation->type = type;
+	delegation->pagemod_limit = pagemod_limit;
+	oldcred = delegation->cred;
+	delegation->cred = get_cred(cred);
+	switch (deleg_type) {
+	case NFS4_OPEN_DELEGATE_READ_ATTRS_DELEG:
+	case NFS4_OPEN_DELEGATE_WRITE_ATTRS_DELEG:
+		set_bit(NFS_DELEGATION_DELEGTIME, &delegation->flags);
+		break;
+	default:
+		clear_bit(NFS_DELEGATION_DELEGTIME, &delegation->flags);
+	}
+	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
+	if (test_and_clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+		atomic_long_inc(&NFS_SERVER(inode)->nr_active_delegations);
+	spin_unlock(&delegation->lock);
+	rcu_read_unlock();
+	put_cred(oldcred);
+	trace_nfs4_reclaim_delegation(inode, type);
 }
 
 static int nfs_do_return_delegation(struct inode *inode,
@@ -355,6 +364,8 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi,
 		rcu_dereference_protected(nfsi->delegation,
 				lockdep_is_held(&clp->cl_lock));
 
+	trace_nfs4_detach_delegation(&nfsi->vfs_inode, delegation->type);
+
 	if (deleg_cur == NULL || delegation != deleg_cur)
 		return NULL;
 
@@ -363,6 +374,7 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi,
 		spin_unlock(&delegation->lock);
 		return NULL;
 	}
+	hlist_del_init_rcu(&delegation->hash);
 	list_del_rcu(&delegation->super_list);
 	delegation->inode = NULL;
 	rcu_assign_pointer(nfsi->delegation, NULL);
@@ -410,7 +422,8 @@ nfs_update_delegation_cred(struct nfs_delegation *delegation,
 }
 
 static void
-nfs_update_inplace_delegation(struct nfs_delegation *delegation,
+nfs_update_inplace_delegation(struct nfs_server *server,
+		struct nfs_delegation *delegation,
 		const struct nfs_delegation *update)
 {
 	if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) {
@@ -423,7 +436,7 @@ nfs_update_inplace_delegation(struct nfs_delegation *delegation,
 			nfs_update_delegation_cred(delegation, update->cred);
 			/* smp_mb__before_atomic() is implicit due to xchg() */
 			clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
-			atomic_long_inc(&nfs_active_delegations);
+			atomic_long_inc(&server->nr_active_delegations);
 		}
 	}
 }
@@ -478,7 +491,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
 	if (nfs4_stateid_match_other(&old_delegation->stateid,
 				&delegation->stateid)) {
 		spin_lock(&old_delegation->lock);
-		nfs_update_inplace_delegation(old_delegation,
+		nfs_update_inplace_delegation(server, old_delegation,
 				delegation);
 		spin_unlock(&old_delegation->lock);
 		goto out;
@@ -524,10 +537,12 @@ add_new:
 	spin_unlock(&inode->i_lock);
 
 	list_add_tail_rcu(&delegation->super_list, &server->delegations);
+	hlist_add_head_rcu(&delegation->hash,
+			nfs_delegation_hash(server, &NFS_I(inode)->fh));
 	rcu_assign_pointer(nfsi->delegation, delegation);
 	delegation = NULL;
 
-	atomic_long_inc(&nfs_active_delegations);
+	atomic_long_inc(&server->nr_active_delegations);
 
 	trace_nfs4_set_delegation(inode, type);
 
@@ -541,7 +556,7 @@ out:
 		__nfs_free_delegation(delegation);
 	if (freeme != NULL) {
 		nfs_do_return_delegation(inode, freeme, 0);
-		nfs_free_delegation(freeme);
+		nfs_free_delegation(server, freeme);
 	}
 	return status;
 }
@@ -592,6 +607,8 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 {
 	bool ret = false;
 
+	trace_nfs_delegation_need_return(delegation);
+
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
 	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) ||
@@ -751,7 +768,7 @@ void nfs_inode_evict_delegation(struct inode *inode)
 		set_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 		set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags);
 		nfs_do_return_delegation(inode, delegation, 1);
-		nfs_free_delegation(delegation);
+		nfs_free_delegation(NFS_SERVER(inode), delegation);
 	}
 }
 
@@ -837,7 +854,8 @@ void nfs4_inode_return_delegation_on_close(struct inode *inode)
 	if (!delegation)
 		goto out;
 	if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) ||
-	    atomic_long_read(&nfs_active_delegations) >= nfs_delegation_watermark) {
+	    atomic_long_read(&NFS_SERVER(inode)->nr_active_delegations) >=
+	    nfs_delegation_watermark) {
 		spin_lock(&delegation->lock);
 		if (delegation->inode &&
 		    list_empty(&NFS_I(inode)->open_files) &&
@@ -1013,7 +1031,7 @@ static void nfs_revoke_delegation(struct inode *inode,
 		}
 		spin_unlock(&delegation->lock);
 	}
-	nfs_mark_delegation_revoked(delegation);
+	nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation);
 	ret = true;
 out:
 	rcu_read_unlock();
@@ -1045,7 +1063,7 @@ void nfs_delegation_mark_returned(struct inode *inode,
 			delegation->stateid.seqid = stateid->seqid;
 	}
 
-	nfs_mark_delegation_revoked(delegation);
+	nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation);
 	clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 	spin_unlock(&delegation->lock);
 	if (nfs_detach_delegation(NFS_I(inode), delegation, NFS_SERVER(inode)))
@@ -1158,11 +1176,12 @@ static struct inode *
 nfs_delegation_find_inode_server(struct nfs_server *server,
 				 const struct nfs_fh *fhandle)
 {
+	struct hlist_head *head = nfs_delegation_hash(server, fhandle);
 	struct nfs_delegation *delegation;
 	struct super_block *freeme = NULL;
 	struct inode *res = NULL;
 
-	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
+	hlist_for_each_entry_rcu(delegation, head, hash) {
 		spin_lock(&delegation->lock);
 		if (delegation->inode != NULL &&
 		    !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
@@ -1265,7 +1284,7 @@ restart:
 		if (delegation != NULL) {
 			if (nfs_detach_delegation(NFS_I(inode), delegation,
 						server) != NULL)
-				nfs_free_delegation(delegation);
+				nfs_free_delegation(server, delegation);
 			/* Match nfs_start_delegation_return_locked */
 			nfs_put_delegation(delegation);
 		}
@@ -1570,4 +1589,17 @@ out:
 	return ret;
 }
 
-module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644);
+int nfs4_delegation_hash_alloc(struct nfs_server *server)
+{
+	int delegation_buckets, i;
+
+	delegation_buckets = roundup_pow_of_two(nfs_delegation_watermark / 16);
+	server->delegation_hash_mask = delegation_buckets - 1;
+	server->delegation_hash_table = kmalloc_array(delegation_buckets,
+			sizeof(*server->delegation_hash_table), GFP_KERNEL);
+	if (!server->delegation_hash_table)
+		return -ENOMEM;
+	for (i = 0; i < delegation_buckets; i++)
+		INIT_HLIST_HEAD(&server->delegation_hash_table[i]);
+	return 0;
+}

fs/nfs/delegation.h

@@ -14,6 +14,7 @@
  * NFSv4 delegation
  */
 struct nfs_delegation {
+	struct hlist_node hash;
 	struct list_head super_list;
 	const struct cred *cred;
 	struct inode *inode;
@@ -123,4 +124,6 @@ static inline int nfs_have_delegated_mtime(struct inode *inode)
 						 NFS_DELEGATION_FLAG_TIME);
 }
 
+int nfs4_delegation_hash_alloc(struct nfs_server *server);
+
 #endif

fs/nfs/dir.c

@@ -1828,9 +1828,7 @@ static void block_revalidate(struct dentry *dentry)
 
 static void unblock_revalidate(struct dentry *dentry)
 {
-	/* store_release ensures wait_var_event() sees the update */
+	store_release_wake_up(&dentry->d_fsdata, NULL);
-	smp_store_release(&dentry->d_fsdata, NULL);
-	wake_up_var(&dentry->d_fsdata);
 }
 
 /*

fs/nfs/export.c

@@ -66,14 +66,21 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 {
 	struct nfs_fattr *fattr = NULL;
 	struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw);
-	size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size;
+	size_t fh_size = offsetof(struct nfs_fh, data);
 	const struct nfs_rpc_ops *rpc_ops;
 	struct dentry *dentry;
 	struct inode *inode;
-	int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size);
+	int len = EMBED_FH_OFF;
 	u32 *p = fid->raw;
 	int ret;
 
+	/* Initial check of bounds */
+	if (fh_len < len + XDR_QUADLEN(fh_size) ||
+	    fh_len > XDR_QUADLEN(NFS_MAXFHSIZE))
+		return NULL;
+	/* Calculate embedded filehandle size */
+	fh_size += server_fh->size;
+	len += XDR_QUADLEN(fh_size);
 	/* NULL translates to ESTALE */
 	if (fh_len < len || fh_type != len)
 		return NULL;

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -762,14 +762,14 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
-	struct nfs4_pnfs_ds *ds;
+	struct nfs4_pnfs_ds *ds = ERR_PTR(-EAGAIN);
 	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
 		mirror = FF_LAYOUT_COMP(lseg, idx);
 		ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-		if (!ds)
+		if (IS_ERR(ds))
 			continue;
 
 		if (check_device &&
@@ -777,10 +777,10 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 			continue;
 
 		*best_idx = idx;
-		return ds;
+		break;
 	}
 
-	return NULL;
+	return ds;
 }
 
 static struct nfs4_pnfs_ds *
@@ -942,7 +942,7 @@ retry:
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
 		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true);
-		if (!ds) {
+		if (IS_ERR(ds)) {
 			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 				goto out_mds;
 			pnfs_generic_pg_cleanup(pgio);
@@ -1867,6 +1867,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	u32 idx = hdr->pgio_mirror_idx;
 	int vers;
 	struct nfs_fh *fh;
+	bool ds_fatal_error = false;
 
 	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
 		__func__, hdr->inode->i_ino,
@@ -1874,8 +1875,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);
@@ -1923,7 +1926,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
@@ -1945,11 +1948,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	int vers;
 	struct nfs_fh *fh;
 	u32 idx = hdr->pgio_mirror_idx;
+	bool ds_fatal_error = false;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);
@@ -2000,7 +2006,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
@@ -2043,7 +2049,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds))
 		goto out_err;
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,

fs/nfs/flexfilelayout/flexfilelayoutdev.c

@@ -370,11 +370,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 			  struct nfs4_ff_layout_mirror *mirror,
 			  bool fail_return)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
+	struct nfs4_pnfs_ds *ds;
 	struct inode *ino = lseg->pls_layout->plh_inode;
 	struct nfs_server *s = NFS_SERVER(ino);
 	unsigned int max_payload;
-	int status;
+	int status = -EAGAIN;
 
 	if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror))
 		goto noconnect;
@@ -418,7 +418,7 @@ noconnect:
 	ff_layout_send_layouterror(lseg);
 	if (fail_return || !ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(ino, lseg);
-	ds = NULL;
+	ds = ERR_PTR(status);
 out:
 	return ds;
 }

fs/nfs/fs_context.c

@@ -96,6 +96,8 @@ enum nfs_param {
 	Opt_wsize,
 	Opt_write,
 	Opt_xprtsec,
+	Opt_cert_serial,
+	Opt_privkey_serial,
 };
 
 enum {
@@ -221,6 +223,8 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_enum  ("write",		Opt_write, nfs_param_enums_write),
 	fsparam_u32   ("wsize",		Opt_wsize),
 	fsparam_string("xprtsec",	Opt_xprtsec),
+	fsparam_s32("cert_serial",	Opt_cert_serial),
+	fsparam_s32("privkey_serial",	Opt_privkey_serial),
 	{}
 };
 
@@ -551,6 +555,32 @@ static int nfs_parse_version_string(struct fs_context *fc,
 	return 0;
 }
 
+#ifdef CONFIG_KEYS
+static int nfs_tls_key_verify(key_serial_t key_id)
+{
+	struct key *key = key_lookup(key_id);
+	int error = 0;
+
+	if (IS_ERR(key)) {
+		pr_err("key id %08x not found\n", key_id);
+		return PTR_ERR(key);
+	}
+	if (test_bit(KEY_FLAG_REVOKED, &key->flags) ||
+	    test_bit(KEY_FLAG_INVALIDATED, &key->flags)) {
+		pr_err("key id %08x revoked\n", key_id);
+		error = -EKEYREVOKED;
+	}
+
+	key_put(key);
+	return error;
+}
+#else
+static inline int nfs_tls_key_verify(key_serial_t key_id)
+{
+	return -ENOENT;
+}
+#endif /* CONFIG_KEYS */
+
 /*
  * Parse a single mount parameter.
  */
@@ -807,6 +837,18 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		if (ret < 0)
 			return ret;
 		break;
+	case Opt_cert_serial:
+		ret = nfs_tls_key_verify(result.int_32);
+		if (ret < 0)
+			return ret;
+		ctx->xprtsec.cert_serial = result.int_32;
+		break;
+	case Opt_privkey_serial:
+		ret = nfs_tls_key_verify(result.int_32);
+		if (ret < 0)
+			return ret;
+		ctx->xprtsec.privkey_serial = result.int_32;
+		break;
 
 	case Opt_proto:
 		if (!param->string)

fs/nfs/inode.c

@@ -197,6 +197,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 		if (!(flags & NFS_INO_REVAL_FORCED))
 			flags &= ~(NFS_INO_INVALID_MODE |
 				   NFS_INO_INVALID_OTHER |
+				   NFS_INO_INVALID_BTIME |
 				   NFS_INO_INVALID_XATTR);
 		flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE);
 	}
@@ -522,6 +523,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode_set_atime(inode, 0, 0);
 		inode_set_mtime(inode, 0, 0);
 		inode_set_ctime(inode, 0, 0);
+		memset(&nfsi->btime, 0, sizeof(nfsi->btime));
 		inode_set_iversion_raw(inode, 0);
 		inode->i_size = 0;
 		clear_nlink(inode);
@@ -545,6 +547,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			inode_set_ctime_to_ts(inode, fattr->ctime);
 		else if (fattr_supported & NFS_ATTR_FATTR_CTIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
+		if (fattr->valid & NFS_ATTR_FATTR_BTIME)
+			nfsi->btime = fattr->btime;
+		else if (fattr_supported & NFS_ATTR_FATTR_BTIME)
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_BTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode_set_iversion_raw(inode, fattr->change_attr);
 		else
@@ -931,6 +937,7 @@ static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
 
 static u32 nfs_get_valid_attrmask(struct inode *inode)
 {
+	u64 fattr_valid = NFS_SERVER(inode)->fattr_valid;
 	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
 	u32 reply_mask = STATX_INO | STATX_TYPE;
 
@@ -950,6 +957,9 @@ static u32 nfs_get_valid_attrmask(struct inode *inode)
 		reply_mask |= STATX_UID | STATX_GID;
 	if (!(cache_validity & NFS_INO_INVALID_BLOCKS))
 		reply_mask |= STATX_BLOCKS;
+	if (!(cache_validity & NFS_INO_INVALID_BTIME) &&
+	    (fattr_valid & NFS_ATTR_FATTR_BTIME))
+		reply_mask |= STATX_BTIME;
 	if (!(cache_validity & NFS_INO_INVALID_CHANGE))
 		reply_mask |= STATX_CHANGE_COOKIE;
 	return reply_mask;
@@ -960,6 +970,7 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 {
 	struct inode *inode = d_inode(path->dentry);
 	struct nfs_server *server = NFS_SERVER(inode);
+	u64 fattr_valid = server->fattr_valid;
 	unsigned long cache_validity;
 	int err = 0;
 	bool force_sync = query_flags & AT_STATX_FORCE_SYNC;
@@ -970,9 +981,12 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 	request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID |
 			STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME |
-			STATX_INO | STATX_SIZE | STATX_BLOCKS |
+			STATX_INO | STATX_SIZE | STATX_BLOCKS | STATX_BTIME |
 			STATX_CHANGE_COOKIE;
 
+	if (!(fattr_valid & NFS_ATTR_FATTR_BTIME))
+		request_mask &= ~STATX_BTIME;
+
 	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
 		if (readdirplus_enabled)
 			nfs_readdirplus_parent_cache_hit(path->dentry);
@@ -1004,7 +1018,7 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 	/* Is the user requesting attributes that might need revalidation? */
 	if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME|
 					STATX_MTIME|STATX_UID|STATX_GID|
-					STATX_SIZE|STATX_BLOCKS|
+					STATX_SIZE|STATX_BLOCKS|STATX_BTIME|
 					STATX_CHANGE_COOKIE)))
 		goto out_no_revalidate;
 
@@ -1028,6 +1042,8 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		do_update |= cache_validity & NFS_INO_INVALID_OTHER;
 	if (request_mask & STATX_BLOCKS)
 		do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
+	if (request_mask & STATX_BTIME)
+		do_update |= cache_validity & NFS_INO_INVALID_BTIME;
 
 	if (do_update) {
 		if (readdirplus_enabled)
@@ -1049,6 +1065,7 @@ out_no_revalidate:
 		stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC;
 	if (S_ISDIR(inode->i_mode))
 		stat->blksize = NFS_SERVER(inode)->dtsize;
+	stat->btime = NFS_I(inode)->btime;
 out:
 	trace_nfs_getattr_exit(inode, err);
 	return err;
@@ -1943,7 +1960,7 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr,
 		NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
 		NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
 		NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER |
-		NFS_INO_INVALID_NLINK;
+		NFS_INO_INVALID_NLINK | NFS_INO_INVALID_BTIME;
 	unsigned long cache_validity = NFS_I(inode)->cache_validity;
 	enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type;
 
@@ -2209,7 +2226,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	bool attr_changed = false;
 	bool have_delegation;
 
-	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
+	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%llx)\n",
 			__func__, inode->i_sb->s_id, inode->i_ino,
 			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
@@ -2304,7 +2321,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					| NFS_INO_INVALID_BLOCKS
 					| NFS_INO_INVALID_NLINK
 					| NFS_INO_INVALID_MODE
-					| NFS_INO_INVALID_OTHER;
+					| NFS_INO_INVALID_OTHER
+					| NFS_INO_INVALID_BTIME;
 				if (S_ISDIR(inode->i_mode))
 					nfs_force_lookup_revalidate(inode);
 				attr_changed = true;
@@ -2338,6 +2356,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfsi->cache_validity |=
 			save_cache_validity & NFS_INO_INVALID_CTIME;
 
+	if (fattr->valid & NFS_ATTR_FATTR_BTIME)
+		nfsi->btime = fattr->btime;
+	else if (fattr_supported & NFS_ATTR_FATTR_BTIME)
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_BTIME;
+
 	/* Check if our cached file size is stale */
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		new_isize = nfs_size_to_loff_t(fattr->size);
@@ -2625,6 +2649,35 @@ static struct pernet_operations nfs_net_ops = {
 	.size = sizeof(struct nfs_net),
 };
 
+#ifdef CONFIG_KEYS
+static struct key *nfs_keyring;
+
+static int __init nfs_init_keyring(void)
+{
+	nfs_keyring = keyring_alloc(".nfs",
+			     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+			     current_cred(),
+			     (KEY_POS_ALL & ~KEY_POS_SETATTR) |
+			     (KEY_USR_ALL & ~KEY_USR_SETATTR),
+			     KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+	return PTR_ERR_OR_ZERO(nfs_keyring);
+}
+
+static void nfs_exit_keyring(void)
+{
+	key_put(nfs_keyring);
+}
+#else
+static inline int nfs_init_keyring(void)
+{
+	return 0;
+}
+
+static inline void nfs_exit_keyring(void)
+{
+}
+#endif /* CONFIG_KEYS */
+
 /*
  * Initialize NFS
  */
@@ -2632,6 +2685,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_init_keyring();
+	if (err)
+		return err;
+
 	err = nfs_sysfs_init();
 	if (err < 0)
 		goto out10;
@@ -2692,6 +2749,7 @@ out7:
 out9:
 	nfs_sysfs_exit();
 out10:
+	nfs_exit_keyring();
 	return err;
 }
 
@@ -2707,6 +2765,7 @@ static void __exit exit_nfs_fs(void)
 	nfs_fs_proc_exit();
 	nfsiod_stop();
 	nfs_sysfs_exit();
+	nfs_exit_keyring();
 }
 
 /* Not quite true; I just maintain it */

fs/nfs/internal.h

@@ -207,7 +207,6 @@ struct nfs_mount_request {
 };
 
 extern int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans);
-extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
 extern const struct rpc_program nfs_program;
@@ -232,7 +231,7 @@ extern struct nfs_client *
 nfs4_find_client_sessionid(struct net *, const struct sockaddr *,
 				struct nfs4_sessionid *, u32);
 extern struct nfs_server *nfs_create_server(struct fs_context *);
-extern void nfs4_server_set_init_caps(struct nfs_server *);
+extern void nfs_server_set_init_caps(struct nfs_server *);
 extern struct nfs_server *nfs4_create_server(struct fs_context *);
 extern struct nfs_server *nfs4_create_referral_server(struct fs_context *);
 extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
@@ -671,9 +670,12 @@ nfs_write_match_verf(const struct nfs_writeverf *verf,
 
 static inline gfp_t nfs_io_gfp_mask(void)
 {
-	if (current->flags & PF_WQ_WORKER)
+	gfp_t ret = current_gfp_context(GFP_KERNEL);
-		return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+
-	return GFP_KERNEL;
+	/* For workers __GFP_NORETRY only with __GFP_IO or __GFP_FS */
+	if ((current->flags & PF_WQ_WORKER) && ret == GFP_KERNEL)
+		ret |= __GFP_NORETRY | __GFP_NOWARN;
+	return ret;
 }
 
 /*

fs/nfs/localio.c

@@ -500,14 +500,13 @@ nfs_copy_boot_verifier(struct nfs_write_verifier *verifier, struct inode *inode)
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	u32 *verf = (u32 *)verifier->data;
-	int seq = 0;
+	unsigned int seq;
 
 	do {
-		read_seqbegin_or_lock(&clp->cl_boot_lock, &seq);
+		seq = read_seqbegin(&clp->cl_boot_lock);
 		verf[0] = (u32)clp->cl_nfssvc_boot.tv_sec;
 		verf[1] = (u32)clp->cl_nfssvc_boot.tv_nsec;
-	} while (need_seqretry(&clp->cl_boot_lock, seq));
+	} while (read_seqretry(&clp->cl_boot_lock, seq));
-	done_seqretry(&clp->cl_boot_lock, seq);
 }
 
 static void

fs/nfs/mount_clnt.c

@@ -223,74 +223,6 @@ out_mnt_err:
 	goto out;
 }
 
-/**
- * nfs_umount - Notify a server that we have unmounted this export
- * @info: pointer to umount request arguments
- *
- * MOUNTPROC_UMNT is advisory, so we set a short timeout, and always
- * use UDP.
- */
-void nfs_umount(const struct nfs_mount_request *info)
-{
-	static const struct rpc_timeout nfs_umnt_timeout = {
-		.to_initval = 1 * HZ,
-		.to_maxval = 3 * HZ,
-		.to_retries = 2,
-	};
-	struct rpc_create_args args = {
-		.net		= info->net,
-		.protocol	= IPPROTO_UDP,
-		.address	= (struct sockaddr *)info->sap,
-		.addrsize	= info->salen,
-		.timeout	= &nfs_umnt_timeout,
-		.servername	= info->hostname,
-		.program	= &mnt_program,
-		.version	= info->version,
-		.authflavor	= RPC_AUTH_UNIX,
-		.flags		= RPC_CLNT_CREATE_NOPING,
-		.cred		= current_cred(),
-	};
-	struct rpc_message msg	= {
-		.rpc_argp	= info->dirpath,
-	};
-	struct rpc_clnt *clnt;
-	int status;
-
-	if (strlen(info->dirpath) > MNTPATHLEN)
-		return;
-
-	if (info->noresvport)
-		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
-
-	clnt = rpc_create(&args);
-	if (IS_ERR(clnt))
-		goto out_clnt_err;
-
-	dprintk("NFS: sending UMNT request for %s:%s\n",
-		(info->hostname ? info->hostname : "server"), info->dirpath);
-
-	if (info->version == NFS_MNT3_VERSION)
-		msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC3_UMNT];
-	else
-		msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC_UMNT];
-
-	status = rpc_call_sync(clnt, &msg, 0);
-	rpc_shutdown_client(clnt);
-
-	if (unlikely(status < 0))
-		goto out_call_err;
-
-	return;
-
-out_clnt_err:
-	dprintk("NFS: failed to create UMNT RPC client, status=%ld\n",
-			PTR_ERR(clnt));
-	return;
-
-out_call_err:
-	dprintk("NFS: UMNT request failed, status=%d\n", status);
-}
-
 /*
  * XDR encode/decode functions for MOUNT
  */

fs/nfs/nfs4_fs.h

@@ -63,7 +63,7 @@ struct nfs4_minor_version_ops {
 	bool	(*match_stateid)(const nfs4_stateid *,
 			const nfs4_stateid *);
 	int	(*find_root_sec)(struct nfs_server *, struct nfs_fh *,
-			struct nfs_fsinfo *);
+				 struct nfs_fattr *);
 	void	(*free_lock_state)(struct nfs_server *,
 			struct nfs4_lock_state *);
 	int	(*test_and_free_expired)(struct nfs_server *,
@@ -296,7 +296,8 @@ extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *,
 extern void nfs4_init_sequence(struct nfs4_sequence_args *, struct nfs4_sequence_res *, int, int);
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, const struct cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, const struct cred *);
-extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool);
+extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *,
+				struct nfs_fattr *, bool);
 extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, const struct cred *cred);
 extern int nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred);
 extern int nfs4_destroy_clientid(struct nfs_client *clp);

fs/nfs/nfs4client.c

@@ -802,6 +802,7 @@ static void nfs4_destroy_server(struct nfs_server *server)
 	unset_pnfs_layoutdriver(server);
 	nfs4_purge_state_owners(server, &freeme);
 	nfs4_free_state_owners(&freeme);
+	kfree(server->delegation_hash_table);
 }
 
 /*
@@ -895,55 +896,40 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
  * Set up an NFS4 client
  */
 static int nfs4_set_client(struct nfs_server *server,
-		const char *hostname,
+		struct nfs_client_initdata *cl_init)
-		const struct sockaddr_storage *addr,
-		const size_t addrlen,
-		const char *ip_addr,
-		int proto, const struct rpc_timeout *timeparms,
-		u32 minorversion, unsigned int nconnect,
-		unsigned int max_connect,
-		struct net *net,
-		struct xprtsec_parms *xprtsec)
 {
-	struct nfs_client_initdata cl_init = {
-		.hostname = hostname,
-		.addr = addr,
-		.addrlen = addrlen,
-		.ip_addr = ip_addr,
-		.nfs_mod = &nfs_v4,
-		.proto = proto,
-		.minorversion = minorversion,
-		.net = net,
-		.timeparms = timeparms,
-		.cred = server->cred,
-		.xprtsec = *xprtsec,
-	};
 	struct nfs_client *clp;
 
-	if (minorversion == 0)
+	cl_init->nfs_mod = &nfs_v4;
-		__set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags);
+	cl_init->cred = server->cred;
-	else
+
-		cl_init.max_connect = max_connect;
+	if (cl_init->minorversion == 0) {
-	switch (proto) {
+		__set_bit(NFS_CS_REUSEPORT, &cl_init->init_flags);
+		cl_init->max_connect = 0;
+	}
+
+	switch (cl_init->proto) {
 	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
 	case XPRT_TRANSPORT_TCP_TLS:
-		cl_init.nconnect = nconnect;
+		break;
+	default:
+		cl_init->nconnect = 0;
 	}
 
 	if (server->flags & NFS_MOUNT_NORESVPORT)
-		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+		__set_bit(NFS_CS_NORESVPORT, &cl_init->init_flags);
 	if (server->options & NFS_OPTION_MIGRATION)
-		__set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
+		__set_bit(NFS_CS_MIGRATION, &cl_init->init_flags);
 	if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status))
-		__set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
+		__set_bit(NFS_CS_TSM_POSSIBLE, &cl_init->init_flags);
-	server->port = rpc_get_port((struct sockaddr *)addr);
+	server->port = rpc_get_port((struct sockaddr *)cl_init->addr);
 
 	if (server->flags & NFS_MOUNT_NETUNREACH_FATAL)
-		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init.init_flags);
+		__set_bit(NFS_CS_NETUNREACH_FATAL, &cl_init->init_flags);
 
 	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init);
+	clp = nfs_get_client(cl_init);
 	if (IS_ERR(clp))
 		return PTR_ERR(clp);
 
@@ -1088,29 +1074,15 @@ static void nfs4_session_limit_xasize(struct nfs_server *server)
 #endif
 }
 
-void nfs4_server_set_init_caps(struct nfs_server *server)
-{
-	/* Set the basic capabilities */
-	server->caps |= server->nfs_client->cl_mvops->init_caps;
-	if (server->flags & NFS_MOUNT_NORDIRPLUS)
-			server->caps &= ~NFS_CAP_READDIRPLUS;
-	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
-		server->caps &= ~NFS_CAP_READ_PLUS;
-
-	/*
-	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
-	 * authentication.
-	 */
-	if (nfs4_disable_idmapping &&
-			server->client->cl_auth->au_flavor == RPC_AUTH_UNIX)
-		server->caps |= NFS_CAP_UIDGID_NOMAP;
-}
-
 static int nfs4_server_common_setup(struct nfs_server *server,
 		struct nfs_fh *mntfh, bool auth_probe)
 {
 	int error;
 
+	error = nfs4_delegation_hash_alloc(server);
+	if (error)
+		return error;
+
 	/* data servers support only a subset of NFSv4.1 */
 	if (is_ds_only_client(server->nfs_client))
 		return -EPROTONOSUPPORT;
@@ -1118,14 +1090,14 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	/* We must ensure the session is initialised first */
 	error = nfs4_init_session(server->nfs_client);
 	if (error < 0)
-		goto out;
+		return error;
 
-	nfs4_server_set_init_caps(server);
+	nfs_server_set_init_caps(server);
 
 	/* Probe the root fh to retrieve its FSID and filehandle */
 	error = nfs4_get_rootfh(server, mntfh, auth_probe);
 	if (error < 0)
-		goto out;
+		return error;
 
 	dprintk("Server FSID: %llx:%llx\n",
 			(unsigned long long) server->fsid.major,
@@ -1134,7 +1106,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 
 	error = nfs_probe_server(server, mntfh);
 	if (error < 0)
-		goto out;
+		return error;
 
 	nfs4_session_limit_rwsize(server);
 	nfs4_session_limit_xasize(server);
@@ -1145,8 +1117,7 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	nfs_server_insert_lists(server);
 	server->mount_time = jiffies;
 	server->destroy = nfs4_destroy_server;
-out:
+	return 0;
-	return error;
 }
 
 /*
@@ -1156,6 +1127,19 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc)
 {
 	struct nfs_fs_context *ctx = nfs_fc2context(fc);
 	struct rpc_timeout timeparms;
+	struct nfs_client_initdata cl_init = {
+		.hostname = ctx->nfs_server.hostname,
+		.addr = &ctx->nfs_server._address,
+		.addrlen = ctx->nfs_server.addrlen,
+		.ip_addr = ctx->client_address,
+		.proto = ctx->nfs_server.protocol,
+		.minorversion = ctx->minorversion,
+		.net = fc->net_ns,
+		.timeparms = &timeparms,
+		.xprtsec = ctx->xprtsec,
+		.nconnect = ctx->nfs_server.nconnect,
+		.max_connect = ctx->nfs_server.max_connect,
+	};
 	int error;
 
 	nfs_init_timeout_values(&timeparms, ctx->nfs_server.protocol,
@@ -1175,18 +1159,7 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc)
 		ctx->selected_flavor = RPC_AUTH_UNIX;
 
 	/* Get a client record */
-	error = nfs4_set_client(server,
+	error = nfs4_set_client(server, &cl_init);
-				ctx->nfs_server.hostname,
-				&ctx->nfs_server._address,
-				ctx->nfs_server.addrlen,
-				ctx->client_address,
-				ctx->nfs_server.protocol,
-				&timeparms,
-				ctx->minorversion,
-				ctx->nfs_server.nconnect,
-				ctx->nfs_server.max_connect,
-				fc->net_ns,
-				&ctx->xprtsec);
 	if (error < 0)
 		return error;
 
@@ -1246,18 +1219,28 @@ error:
 struct nfs_server *nfs4_create_referral_server(struct fs_context *fc)
 {
 	struct nfs_fs_context *ctx = nfs_fc2context(fc);
-	struct nfs_client *parent_client;
+	struct nfs_server *parent_server = NFS_SB(ctx->clone_data.sb);
-	struct nfs_server *server, *parent_server;
+	struct nfs_client *parent_client = parent_server->nfs_client;
-	int proto, error;
+	struct nfs_client_initdata cl_init = {
+		.hostname = ctx->nfs_server.hostname,
+		.addr = &ctx->nfs_server._address,
+		.addrlen = ctx->nfs_server.addrlen,
+		.ip_addr = parent_client->cl_ipaddr,
+		.minorversion = parent_client->cl_mvops->minor_version,
+		.net = parent_client->cl_net,
+		.timeparms = parent_server->client->cl_timeout,
+		.xprtsec = parent_client->cl_xprtsec,
+		.nconnect = parent_client->cl_nconnect,
+		.max_connect = parent_client->cl_max_connect,
+	};
+	struct nfs_server *server;
 	bool auth_probe;
+	int error;
 
 	server = nfs_alloc_server();
 	if (!server)
 		return ERR_PTR(-ENOMEM);
 
-	parent_server = NFS_SB(ctx->clone_data.sb);
-	parent_client = parent_server->nfs_client;
-
 	server->cred = get_cred(parent_server->cred);
 
 	/* Initialise the client representation from the parent server */
@@ -1266,38 +1249,17 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc)
 	/* Get a client representation */
 #if IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA)
 	rpc_set_port(&ctx->nfs_server.address, NFS_RDMA_PORT);
-	error = nfs4_set_client(server,
+	cl_init.proto = XPRT_TRANSPORT_RDMA;
-				ctx->nfs_server.hostname,
+	error = nfs4_set_client(server, &cl_init);
-				&ctx->nfs_server._address,
-				ctx->nfs_server.addrlen,
-				parent_client->cl_ipaddr,
-				XPRT_TRANSPORT_RDMA,
-				parent_server->client->cl_timeout,
-				parent_client->cl_mvops->minor_version,
-				parent_client->cl_nconnect,
-				parent_client->cl_max_connect,
-				parent_client->cl_net,
-				&parent_client->cl_xprtsec);
 	if (!error)
 		goto init_server;
 #endif	/* IS_ENABLED(CONFIG_SUNRPC_XPRT_RDMA) */
 
-	proto = XPRT_TRANSPORT_TCP;
+	cl_init.proto = XPRT_TRANSPORT_TCP;
 	if (parent_client->cl_xprtsec.policy != RPC_XPRTSEC_NONE)
-		proto = XPRT_TRANSPORT_TCP_TLS;
+		cl_init.proto = XPRT_TRANSPORT_TCP_TLS;
 	rpc_set_port(&ctx->nfs_server.address, NFS_PORT);
-	error = nfs4_set_client(server,
+	error = nfs4_set_client(server, &cl_init);
-				ctx->nfs_server.hostname,
-				&ctx->nfs_server._address,
-				ctx->nfs_server.addrlen,
-				parent_client->cl_ipaddr,
-				proto,
-				parent_server->client->cl_timeout,
-				parent_client->cl_mvops->minor_version,
-				parent_client->cl_nconnect,
-				parent_client->cl_max_connect,
-				parent_client->cl_net,
-				&parent_client->cl_xprtsec);
 	if (error < 0)
 		goto error;
 
@@ -1353,6 +1315,19 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 	char buf[INET6_ADDRSTRLEN + 1];
 	struct sockaddr_storage address;
 	struct sockaddr *localaddr = (struct sockaddr *)&address;
+	struct nfs_client_initdata cl_init = {
+		.hostname = hostname,
+		.addr = sap,
+		.addrlen = salen,
+		.ip_addr = buf,
+		.proto = clp->cl_proto,
+		.minorversion = clp->cl_minorversion,
+		.net = net,
+		.timeparms = clnt->cl_timeout,
+		.xprtsec = clp->cl_xprtsec,
+		.nconnect = clp->cl_nconnect,
+		.max_connect = clp->cl_max_connect,
+	};
 	int error;
 
 	error = rpc_switch_client_transport(clnt, &xargs, clnt->cl_timeout);
@@ -1368,11 +1343,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 
 	nfs_server_remove_lists(server);
 	set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
-	error = nfs4_set_client(server, hostname, sap, salen, buf,
+	error = nfs4_set_client(server, &cl_init);
-				clp->cl_proto, clnt->cl_timeout,
-				clp->cl_minorversion,
-				clp->cl_nconnect, clp->cl_max_connect,
-				net, &clp->cl_xprtsec);
 	clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	if (error != 0) {
 		nfs_server_insert_lists(server);

fs/nfs/nfs4file.c

@@ -253,7 +253,6 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 	struct nfs_server *server = NFS_SERVER(dst_inode);
 	struct inode *src_inode = file_inode(src_file);
 	unsigned int bs = server->clone_blksize;
-	bool same_inode = false;
 	int ret;
 
 	/* NFS does not support deduplication. */
@@ -275,20 +274,8 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 			goto out;
 	}
 
-	if (src_inode == dst_inode)
-		same_inode = true;
-
 	/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
-	if (same_inode) {
+	lock_two_nondirectories(src_inode, dst_inode);
-		inode_lock(src_inode);
-	} else if (dst_inode < src_inode) {
-		inode_lock_nested(dst_inode, I_MUTEX_PARENT);
-		inode_lock_nested(src_inode, I_MUTEX_CHILD);
-	} else {
-		inode_lock_nested(src_inode, I_MUTEX_PARENT);
-		inode_lock_nested(dst_inode, I_MUTEX_CHILD);
-	}
-
 	/* flush all pending writes on both src and dst so that server
 	 * has the latest data */
 	ret = nfs_sync_inode(src_inode);
@@ -306,15 +293,7 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 		truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
 
 out_unlock:
-	if (same_inode) {
+	unlock_two_nondirectories(src_inode, dst_inode);
-		inode_unlock(src_inode);
-	} else if (dst_inode < src_inode) {
-		inode_unlock(src_inode);
-		inode_unlock(dst_inode);
-	} else {
-		inode_unlock(dst_inode);
-		inode_unlock(src_inode);
-	}
 out:
 	return ret < 0 ? ret : count;
 }

fs/nfs/nfs4getroot.c

@@ -12,30 +12,28 @@
 
 int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool auth_probe)
 {
-	struct nfs_fsinfo fsinfo;
+	struct nfs_fattr *fattr = nfs_alloc_fattr();
 	int ret = -ENOMEM;
 
-	fsinfo.fattr = nfs_alloc_fattr();
+	if (fattr == NULL)
-	if (fsinfo.fattr == NULL)
 		goto out;
 
 	/* Start by getting the root filehandle from the server */
-	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo, auth_probe);
+	ret = nfs4_proc_get_rootfh(server, mntfh, fattr, auth_probe);
 	if (ret < 0) {
 		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
 		goto out;
 	}
 
-	if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE)
+	if (!(fattr->valid & NFS_ATTR_FATTR_TYPE) || !S_ISDIR(fattr->mode)) {
-			|| !S_ISDIR(fsinfo.fattr->mode)) {
 		printk(KERN_ERR "nfs4_get_rootfh:"
 		       " getroot encountered non-directory\n");
 		ret = -ENOTDIR;
 		goto out;
 	}
 
-	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
+	memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid));
 out:
-	nfs_free_fattr(fsinfo.fattr);
+	nfs_free_fattr(fattr);
 	return ret;
 }

fs/nfs/nfs4proc.c

@@ -222,6 +222,7 @@ const u32 nfs4_fattr_bitmap[3] = {
 	| FATTR4_WORD1_RAWDEV
 	| FATTR4_WORD1_SPACE_USED
 	| FATTR4_WORD1_TIME_ACCESS
+	| FATTR4_WORD1_TIME_CREATE
 	| FATTR4_WORD1_TIME_METADATA
 	| FATTR4_WORD1_TIME_MODIFY
 	| FATTR4_WORD1_MOUNTED_ON_FILEID,
@@ -243,6 +244,7 @@ static const u32 nfs4_pnfs_open_bitmap[3] = {
 	| FATTR4_WORD1_RAWDEV
 	| FATTR4_WORD1_SPACE_USED
 	| FATTR4_WORD1_TIME_ACCESS
+	| FATTR4_WORD1_TIME_CREATE
 	| FATTR4_WORD1_TIME_METADATA
 	| FATTR4_WORD1_TIME_MODIFY,
 	FATTR4_WORD2_MDSTHRESHOLD
@@ -323,6 +325,9 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
 	if (!(cache_validity & NFS_INO_INVALID_OTHER))
 		dst[1] &= ~(FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP);
 
+	if (!(cache_validity & NFS_INO_INVALID_BTIME))
+		dst[1] &= ~FATTR4_WORD1_TIME_CREATE;
+
 	if (nfs_have_delegated_mtime(inode)) {
 		if (!(cache_validity & NFS_INO_INVALID_ATIME))
 			dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET);
@@ -1307,7 +1312,8 @@ nfs4_update_changeattr_locked(struct inode *inode,
 				NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL |
 				NFS_INO_INVALID_SIZE | NFS_INO_INVALID_OTHER |
 				NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK |
-				NFS_INO_INVALID_MODE | NFS_INO_INVALID_XATTR;
+				NFS_INO_INVALID_MODE | NFS_INO_INVALID_BTIME |
+				NFS_INO_INVALID_XATTR;
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 	}
 	nfsi->attrtimeo_timestamp = jiffies;
@@ -4047,6 +4053,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 			server->fattr_valid &= ~NFS_ATTR_FATTR_CTIME;
 		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY))
 			server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_CREATE))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_BTIME;
 		memcpy(server->attr_bitmask_nl, res.attr_bitmask,
 				sizeof(server->attr_bitmask));
 		server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
@@ -4082,7 +4092,7 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 	};
 	int err;
 
-	nfs4_server_set_init_caps(server);
+	nfs_server_set_init_caps(server);
 	do {
 		err = nfs4_handle_exception(server,
 				_nfs4_server_capabilities(server, fhandle),
@@ -4230,15 +4240,18 @@ out:
 }
 
 static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
-		struct nfs_fsinfo *info)
+			     struct nfs_fattr *fattr)
 {
-	u32 bitmask[3];
+	u32 bitmask[3] = {
+		[0] = FATTR4_WORD0_TYPE | FATTR4_WORD0_CHANGE |
+		      FATTR4_WORD0_SIZE | FATTR4_WORD0_FSID,
+	};
 	struct nfs4_lookup_root_arg args = {
 		.bitmask = bitmask,
 	};
 	struct nfs4_lookup_res res = {
 		.server = server,
-		.fattr = info->fattr,
+		.fattr = fattr,
 		.fh = fhandle,
 	};
 	struct rpc_message msg = {
@@ -4247,27 +4260,20 @@ static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
 		.rpc_resp = &res,
 	};
 
-	bitmask[0] = nfs4_fattr_bitmap[0];
+	nfs_fattr_init(fattr);
-	bitmask[1] = nfs4_fattr_bitmap[1];
-	/*
-	 * Process the label in the upcoming getfattr
-	 */
-	bitmask[2] = nfs4_fattr_bitmap[2] & ~FATTR4_WORD2_SECURITY_LABEL;
-
-	nfs_fattr_init(info->fattr);
 	return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
 }
 
 static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
-		struct nfs_fsinfo *info)
+			    struct nfs_fattr *fattr)
 {
 	struct nfs4_exception exception = {
 		.interruptible = true,
 	};
 	int err;
 	do {
-		err = _nfs4_lookup_root(server, fhandle, info);
+		err = _nfs4_lookup_root(server, fhandle, fattr);
-		trace_nfs4_lookup_root(server, fhandle, info->fattr, err);
+		trace_nfs4_lookup_root(server, fhandle, fattr, err);
 		switch (err) {
 		case 0:
 		case -NFS4ERR_WRONGSEC:
@@ -4280,8 +4286,9 @@ out:
 	return err;
 }
 
-static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
+static int nfs4_lookup_root_sec(struct nfs_server *server,
-				struct nfs_fsinfo *info, rpc_authflavor_t flavor)
+				struct nfs_fh *fhandle, struct nfs_fattr *fattr,
+				rpc_authflavor_t flavor)
 {
 	struct rpc_auth_create_args auth_args = {
 		.pseudoflavor = flavor,
@@ -4291,7 +4298,7 @@ static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandl
 	auth = rpcauth_create(&auth_args, server->client);
 	if (IS_ERR(auth))
 		return -EACCES;
-	return nfs4_lookup_root(server, fhandle, info);
+	return nfs4_lookup_root(server, fhandle, fattr);
 }
 
 /*
@@ -4304,7 +4311,7 @@ static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandl
  * negative errno value.
  */
 static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
-			      struct nfs_fsinfo *info)
+			      struct nfs_fattr *fattr)
 {
 	/* Per 3530bis 15.33.5 */
 	static const rpc_authflavor_t flav_array[] = {
@@ -4320,8 +4327,9 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	if (server->auth_info.flavor_len > 0) {
 		/* try each flavor specified by user */
 		for (i = 0; i < server->auth_info.flavor_len; i++) {
-			status = nfs4_lookup_root_sec(server, fhandle, info,
+			status = nfs4_lookup_root_sec(
-						server->auth_info.flavors[i]);
+				server, fhandle, fattr,
+				server->auth_info.flavors[i]);
 			if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
 				continue;
 			break;
@@ -4329,7 +4337,7 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	} else {
 		/* no flavors specified by user, try default list */
 		for (i = 0; i < ARRAY_SIZE(flav_array); i++) {
-			status = nfs4_lookup_root_sec(server, fhandle, info,
+			status = nfs4_lookup_root_sec(server, fhandle, fattr,
 						      flav_array[i]);
 			if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
 				continue;
@@ -4353,28 +4361,22 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
  * nfs4_proc_get_rootfh - get file handle for server's pseudoroot
  * @server: initialized nfs_server handle
  * @fhandle: we fill in the pseudo-fs root file handle
- * @info: we fill in an FSINFO struct
+ * @fattr: we fill in a bare bones struct fattr
  * @auth_probe: probe the auth flavours
  *
  * Returns zero on success, or a negative errno.
  */
 int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
-			 struct nfs_fsinfo *info,
+			 struct nfs_fattr *fattr, bool auth_probe)
-			 bool auth_probe)
 {
 	int status = 0;
 
 	if (!auth_probe)
-		status = nfs4_lookup_root(server, fhandle, info);
+		status = nfs4_lookup_root(server, fhandle, fattr);
 
 	if (auth_probe || status == NFS4ERR_WRONGSEC)
-		status = server->nfs_client->cl_mvops->find_root_sec(server,
+		status = server->nfs_client->cl_mvops->find_root_sec(
-				fhandle, info);
+			server, fhandle, fattr);
-
-	if (status == 0)
-		status = nfs4_server_capabilities(server, fhandle);
-	if (status == 0)
-		status = nfs4_do_fsinfo(server, fhandle, info);
 
 	return nfs4_map_errors(status);
 }
@@ -5781,6 +5783,8 @@ void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[],
 		bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
 	if (cache_validity & NFS_INO_INVALID_BLOCKS)
 		bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+	if (cache_validity & NFS_INO_INVALID_BTIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_CREATE;
 
 	if (cache_validity & NFS_INO_INVALID_SIZE)
 		bitmask[0] |= FATTR4_WORD0_SIZE;
@@ -10339,10 +10343,10 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync)
  * Use the state managment nfs_client cl_rpcclient, which uses krb5i (if
  * possible) as per RFC3530bis and RFC5661 Security Considerations sections
  */
-static int
+static int _nfs41_proc_secinfo_no_name(struct nfs_server *server,
-_nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
+				       struct nfs_fh *fhandle,
-		    struct nfs_fsinfo *info,
+				       struct nfs4_secinfo_flavors *flavors,
-		    struct nfs4_secinfo_flavors *flavors, bool use_integrity)
+				       bool use_integrity)
 {
 	struct nfs41_secinfo_no_name_args args = {
 		.style = SECINFO_STYLE_CURRENT_FH,
@@ -10386,9 +10390,9 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 	return status;
 }
 
-static int
+static int nfs41_proc_secinfo_no_name(struct nfs_server *server,
-nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
+				      struct nfs_fh *fhandle,
-			   struct nfs_fsinfo *info, struct nfs4_secinfo_flavors *flavors)
+				      struct nfs4_secinfo_flavors *flavors)
 {
 	struct nfs4_exception exception = {
 		.interruptible = true,
@@ -10400,7 +10404,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 
 		/* try to use integrity protection with machine cred */
 		if (_nfs4_is_integrity_protected(server->nfs_client))
-			err = _nfs41_proc_secinfo_no_name(server, fhandle, info,
+			err = _nfs41_proc_secinfo_no_name(server, fhandle,
 							  flavors, true);
 
 		/*
@@ -10410,7 +10414,7 @@ nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 		 * the current filesystem's rpc_client and the user cred.
 		 */
 		if (err == -NFS4ERR_WRONGSEC)
-			err = _nfs41_proc_secinfo_no_name(server, fhandle, info,
+			err = _nfs41_proc_secinfo_no_name(server, fhandle,
 							  flavors, false);
 
 		switch (err) {
@@ -10426,9 +10430,8 @@ out:
 	return err;
 }
 
-static int
+static int nfs41_find_root_sec(struct nfs_server *server,
-nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
+			       struct nfs_fh *fhandle, struct nfs_fattr *fattr)
-		    struct nfs_fsinfo *info)
 {
 	int err;
 	struct page *page;
@@ -10444,14 +10447,14 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 	}
 
 	flavors = page_address(page);
-	err = nfs41_proc_secinfo_no_name(server, fhandle, info, flavors);
+	err = nfs41_proc_secinfo_no_name(server, fhandle, flavors);
 
 	/*
 	 * Fall back on "guess and check" method if
 	 * the server doesn't support SECINFO_NO_NAME
 	 */
 	if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) {
-		err = nfs4_find_root_sec(server, fhandle, info);
+		err = nfs4_find_root_sec(server, fhandle, fattr);
 		goto out_freepage;
 	}
 	if (err)
@@ -10476,8 +10479,8 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 			flavor = RPC_AUTH_MAXFLAVOR;
 
 		if (flavor != RPC_AUTH_MAXFLAVOR) {
-			err = nfs4_lookup_root_sec(server, fhandle,
+			err = nfs4_lookup_root_sec(server, fhandle, fattr,
-						   info, flavor);
+						   flavor);
 			if (!err)
 				break;
 		}
@@ -10680,6 +10683,8 @@ nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
 static bool nfs41_match_stateid(const nfs4_stateid *s1,
 		const nfs4_stateid *s2)
 {
+	trace_nfs41_match_stateid(s1, s2);
+
 	if (s1->type != s2->type)
 		return false;
 
@@ -10697,6 +10702,8 @@ static bool nfs41_match_stateid(const nfs4_stateid *s1,
 static bool nfs4_match_stateid(const nfs4_stateid *s1,
 		const nfs4_stateid *s2)
 {
+	trace_nfs4_match_stateid(s1, s2);
+
 	return nfs4_stateid_match(s1, s2);
 }
 
@@ -10867,7 +10874,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 
 static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
-	ssize_t error, error2, error3, error4;
+	ssize_t error, error2, error3, error4 = 0;
 	size_t left = size;
 
 	error = generic_listxattr(dentry, list, left);
@@ -10895,9 +10902,11 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 		left -= error3;
 	}
 
-	error4 = security_inode_listsecurity(d_inode(dentry), list, left);
+	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) {
-	if (error4 < 0)
+		error4 = security_inode_listsecurity(d_inode(dentry), list, left);
-		return error4;
+		if (error4 < 0)
+			return error4;
+	}
 
 	error += error2 + error3 + error4;
 	if (size && error > size)
@@ -10951,6 +10960,26 @@ static const struct inode_operations nfs4_file_inode_operations = {
 	.listxattr	= nfs4_listxattr,
 };
 
+static struct nfs_server *nfs4_clone_server(struct nfs_server *source,
+		struct nfs_fh *fh, struct nfs_fattr *fattr,
+		rpc_authflavor_t flavor)
+{
+	struct nfs_server *server;
+	int error;
+
+	server = nfs_clone_server(source, fh, fattr, flavor);
+	if (IS_ERR(server))
+		return server;
+
+	error = nfs4_delegation_hash_alloc(server);
+	if (error) {
+		nfs_free_server(server);
+		return ERR_PTR(error);
+	}
+
+	return server;
+}
+
 const struct nfs_rpc_ops nfs_v4_clientops = {
 	.version	= 4,			/* protocol version */
 	.dentry_ops	= &nfs4_dentry_operations,
@@ -11003,7 +11032,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.init_client	= nfs4_init_client,
 	.free_client	= nfs4_free_client,
 	.create_server	= nfs4_create_server,
-	.clone_server	= nfs_clone_server,
+	.clone_server	= nfs4_clone_server,
 	.discover_trunking = nfs4_discover_trunking,
 	.enable_swap	= nfs4_enable_swap,
 	.disable_swap	= nfs4_disable_swap,

fs/nfs/nfs4trace.c

@@ -26,11 +26,13 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_read_done);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_write_done);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_read_pagelist);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_mds_fallback_write_pagelist);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pnfs_ds_connect);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_read_error);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_write_error);
 EXPORT_TRACEPOINT_SYMBOL_GPL(ff_layout_commit_error);
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(bl_ext_tree_prepare_commit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bl_pr_key_reg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bl_pr_key_reg_err);
 EXPORT_TRACEPOINT_SYMBOL_GPL(bl_pr_key_unreg);

fs/nfs/nfs4trace.h

@@ -14,6 +14,8 @@
 #include <trace/misc/fs.h>
 #include <trace/misc/nfs.h>
 
+#include "delegation.h"
+
 #define show_nfs_fattr_flags(valid) \
 	__print_flags((unsigned long)valid, "|", \
 		{ NFS_ATTR_FATTR_TYPE, "TYPE" }, \
@@ -30,7 +32,8 @@
 		{ NFS_ATTR_FATTR_CTIME, "CTIME" }, \
 		{ NFS_ATTR_FATTR_CHANGE, "CHANGE" }, \
 		{ NFS_ATTR_FATTR_OWNER_NAME, "OWNER_NAME" }, \
-		{ NFS_ATTR_FATTR_GROUP_NAME, "GROUP_NAME" })
+		{ NFS_ATTR_FATTR_GROUP_NAME, "GROUP_NAME" }, \
+		{ NFS_ATTR_FATTR_BTIME, "BTIME" })
 
 DECLARE_EVENT_CLASS(nfs4_clientid_event,
 		TP_PROTO(
@@ -273,6 +276,32 @@ TRACE_EVENT(nfs4_cb_offload,
 			show_nfs_stable_how(__entry->cb_how)
 		)
 );
+
+TRACE_EVENT(pnfs_ds_connect,
+		TP_PROTO(
+			char *ds_remotestr,
+			int status
+		),
+
+		TP_ARGS(ds_remotestr, status),
+
+		TP_STRUCT__entry(
+			__string(ds_ips, ds_remotestr)
+			__field(int, status)
+		),
+
+		TP_fast_assign(
+			__assign_str(ds_ips);
+			__entry->status = status;
+		),
+
+		TP_printk(
+			"ds_ips=%s, status=%d",
+			__get_str(ds_ips),
+			__entry->status
+                )
+);
+
 #endif /* CONFIG_NFS_V4_1 */
 
 TRACE_EVENT(nfs4_setup_sequence,
@@ -956,6 +985,52 @@ DECLARE_EVENT_CLASS(nfs4_set_delegation_event,
 			TP_ARGS(inode, fmode))
 DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_set_delegation);
 DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_reclaim_delegation);
+DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_detach_delegation);
+
+#define show_delegation_flags(flags) \
+	__print_flags(flags, "|", \
+		{ BIT(NFS_DELEGATION_NEED_RECLAIM), "NEED_RECLAIM" }, \
+		{ BIT(NFS_DELEGATION_RETURN), "RETURN" }, \
+		{ BIT(NFS_DELEGATION_RETURN_IF_CLOSED), "RETURN_IF_CLOSED" }, \
+		{ BIT(NFS_DELEGATION_REFERENCED), "REFERENCED" }, \
+		{ BIT(NFS_DELEGATION_RETURNING), "RETURNING" }, \
+		{ BIT(NFS_DELEGATION_REVOKED), "REVOKED" }, \
+		{ BIT(NFS_DELEGATION_TEST_EXPIRED), "TEST_EXPIRED" }, \
+		{ BIT(NFS_DELEGATION_INODE_FREEING), "INODE_FREEING" }, \
+		{ BIT(NFS_DELEGATION_RETURN_DELAYED), "RETURN_DELAYED" })
+
+DECLARE_EVENT_CLASS(nfs4_delegation_event,
+		TP_PROTO(
+			const struct nfs_delegation *delegation
+		),
+
+		TP_ARGS(delegation),
+
+		TP_STRUCT__entry(
+			__field(u32, fhandle)
+			__field(unsigned int, fmode)
+			__field(unsigned long, flags)
+		),
+
+		TP_fast_assign(
+			__entry->fhandle = nfs_fhandle_hash(NFS_FH(delegation->inode));
+			__entry->fmode = delegation->type;
+			__entry->flags = delegation->flags;
+		),
+
+		TP_printk(
+			"fhandle=0x%08x fmode=%s flags=%s",
+			__entry->fhandle, show_fs_fmode_flags(__entry->fmode),
+			show_delegation_flags(__entry->flags)
+		)
+);
+#define DEFINE_NFS4_DELEGATION_EVENT(name) \
+	DEFINE_EVENT(nfs4_delegation_event, name, \
+			TP_PROTO( \
+				const struct nfs_delegation *delegation \
+			), \
+			TP_ARGS(delegation))
+DEFINE_NFS4_DELEGATION_EVENT(nfs_delegation_need_return);
 
 TRACE_EVENT(nfs4_delegreturn_exit,
 		TP_PROTO(
@@ -1449,6 +1524,63 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event,
 DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_recall);
 DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_layoutrecall_file);
 
+#define show_stateid_type(type) \
+	__print_symbolic(type, \
+		{ NFS4_INVALID_STATEID_TYPE,	"INVALID" }, \
+		{ NFS4_SPECIAL_STATEID_TYPE,	"SPECIAL" }, \
+		{ NFS4_OPEN_STATEID_TYPE,	"OPEN" }, \
+		{ NFS4_LOCK_STATEID_TYPE,	"LOCK" }, \
+		{ NFS4_DELEGATION_STATEID_TYPE,	"DELEGATION" }, \
+		{ NFS4_LAYOUT_STATEID_TYPE,	"LAYOUT" },	\
+		{ NFS4_PNFS_DS_STATEID_TYPE,	"PNFS_DS" }, \
+		{ NFS4_REVOKED_STATEID_TYPE,	"REVOKED" }, \
+		{ NFS4_FREED_STATEID_TYPE,	"FREED" })
+
+DECLARE_EVENT_CLASS(nfs4_match_stateid_event,
+		TP_PROTO(
+			const nfs4_stateid *s1,
+			const nfs4_stateid *s2
+		),
+
+		TP_ARGS(s1, s2),
+
+		TP_STRUCT__entry(
+			__field(int, s1_seq)
+			__field(int, s2_seq)
+			__field(u32, s1_hash)
+			__field(u32, s2_hash)
+			__field(int, s1_type)
+			__field(int, s2_type)
+		),
+
+		TP_fast_assign(
+			__entry->s1_seq = s1->seqid;
+			__entry->s1_hash = nfs_stateid_hash(s1);
+			__entry->s1_type = s1->type;
+			__entry->s2_seq = s2->seqid;
+			__entry->s2_hash = nfs_stateid_hash(s2);
+			__entry->s2_type = s2->type;
+		),
+
+		TP_printk(
+			"s1=%s:%x:%u s2=%s:%x:%u",
+			show_stateid_type(__entry->s1_type),
+			__entry->s1_hash, __entry->s1_seq,
+			show_stateid_type(__entry->s2_type),
+			__entry->s2_hash, __entry->s2_seq
+		)
+);
+
+#define DEFINE_NFS4_MATCH_STATEID_EVENT(name) \
+	DEFINE_EVENT(nfs4_match_stateid_event, name, \
+			TP_PROTO( \
+				const nfs4_stateid *s1, \
+				const nfs4_stateid *s2 \
+			), \
+			TP_ARGS(s1, s2))
+DEFINE_NFS4_MATCH_STATEID_EVENT(nfs41_match_stateid);
+DEFINE_NFS4_MATCH_STATEID_EVENT(nfs4_match_stateid);
+
 DECLARE_EVENT_CLASS(nfs4_idmap_event,
 		TP_PROTO(
 			const char *name,
@@ -2163,6 +2295,40 @@ TRACE_EVENT(ff_layout_commit_error,
 		)
 );
 
+TRACE_EVENT(bl_ext_tree_prepare_commit,
+		TP_PROTO(
+			int ret,
+			size_t count,
+			u64 lwb,
+			bool not_all_ranges
+		),
+
+		TP_ARGS(ret, count, lwb, not_all_ranges),
+
+		TP_STRUCT__entry(
+			__field(int, ret)
+			__field(size_t, count)
+			__field(u64, lwb)
+			__field(bool, not_all_ranges)
+		),
+
+		TP_fast_assign(
+			__entry->ret = ret;
+			__entry->count = count;
+			__entry->lwb = lwb;
+			__entry->not_all_ranges = not_all_ranges;
+		),
+
+		TP_printk(
+			"ret=%d, found %zu ranges, lwb=%llu%s",
+			__entry->ret,
+			__entry->count,
+			__entry->lwb,
+			__entry->not_all_ranges ? ", not all ranges encoded" :
+						  ""
+		)
+);
+
 DECLARE_EVENT_CLASS(pnfs_bl_pr_key_class,
 	TP_PROTO(
 		const struct block_device *bdev,

fs/nfs/nfs4xdr.c

@@ -1623,6 +1623,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 			| FATTR4_WORD1_RAWDEV
 			| FATTR4_WORD1_SPACE_USED
 			| FATTR4_WORD1_TIME_ACCESS
+			| FATTR4_WORD1_TIME_CREATE
 			| FATTR4_WORD1_TIME_METADATA
 			| FATTR4_WORD1_TIME_MODIFY;
 		attrs[2] |= FATTR4_WORD2_SECURITY_LABEL;
@@ -4207,6 +4208,24 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str
 	return status;
 }
 
+static int decode_attr_time_create(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time)
+{
+	int status = 0;
+
+	time->tv_sec = 0;
+	time->tv_nsec = 0;
+	if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_CREATE - 1U)))
+		return -EIO;
+	if (likely(bitmap[1] & FATTR4_WORD1_TIME_CREATE)) {
+		status = decode_attr_time(xdr, time);
+		if (status == 0)
+			status = NFS_ATTR_FATTR_BTIME;
+		bitmap[1] &= ~FATTR4_WORD1_TIME_CREATE;
+	}
+	dprintk("%s: btime=%lld\n", __func__, time->tv_sec);
+	return status;
+}
+
 static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time)
 {
 	int status = 0;
@@ -4781,6 +4800,11 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		goto xdr_error;
 	fattr->valid |= status;
 
+	status = decode_attr_time_create(xdr, bitmap, &fattr->btime);
+	if (status < 0)
+		goto xdr_error;
+	fattr->valid |= status;
+
 	status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime);
 	if (status < 0)
 		goto xdr_error;

fs/nfs/nfstrace.h

@@ -32,7 +32,8 @@
 			{ NFS_INO_INVALID_BLOCKS, "INVALID_BLOCKS" }, \
 			{ NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \
 			{ NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \
-			{ NFS_INO_INVALID_MODE, "INVALID_MODE" })
+			{ NFS_INO_INVALID_MODE, "INVALID_MODE" }, \
+			{ NFS_INO_INVALID_BTIME, "INVALID_BTIME" })
 
 #define nfs_show_nfsi_flags(v) \
 	__print_flags(v, "|", \
@@ -56,6 +57,7 @@ DECLARE_EVENT_CLASS(nfs_inode_event,
 			__field(u32, fhandle)
 			__field(u64, fileid)
 			__field(u64, version)
+			__field(unsigned long, cache_validity)
 		),
 
 		TP_fast_assign(
@@ -64,14 +66,17 @@ DECLARE_EVENT_CLASS(nfs_inode_event,
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
 			__entry->version = inode_peek_iversion_raw(inode);
+			__entry->cache_validity = nfsi->cache_validity;
 		),
 
 		TP_printk(
-			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu ",
+			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu cache_validity=0x%lx (%s)",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
-			(unsigned long long)__entry->version
+			(unsigned long long)__entry->version,
+			__entry->cache_validity,
+			nfs_show_cache_validity(__entry->cache_validity)
 		)
 );
 

fs/nfs/pnfs.c

@@ -306,7 +306,6 @@ void
 pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	struct inode *inode;
-	unsigned long i_state;
 
 	if (!lo)
 		return;
@@ -317,12 +316,11 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 		if (!list_empty(&lo->plh_segs))
 			WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
 		pnfs_detach_layout_hdr(lo);
-		i_state = inode->i_state;
+		/* Notify pnfs_destroy_layout_final() that we're done */
+		if (inode->i_state & (I_FREEING | I_CLEAR))
+			wake_up_var_locked(lo, &inode->i_lock);
 		spin_unlock(&inode->i_lock);
 		pnfs_free_layout_hdr(lo);
-		/* Notify pnfs_destroy_layout_final() that we're done */
-		if (i_state & (I_FREEING | I_CLEAR))
-			wake_up_var(lo);
 	}
 }
 
@@ -809,23 +807,17 @@ void pnfs_destroy_layout(struct nfs_inode *nfsi)
 }
 EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
 
-static bool pnfs_layout_removed(struct nfs_inode *nfsi,
-				struct pnfs_layout_hdr *lo)
-{
-	bool ret;
-
-	spin_lock(&nfsi->vfs_inode.i_lock);
-	ret = nfsi->layout != lo;
-	spin_unlock(&nfsi->vfs_inode.i_lock);
-	return ret;
-}
-
 void pnfs_destroy_layout_final(struct nfs_inode *nfsi)
 {
 	struct pnfs_layout_hdr *lo = __pnfs_destroy_layout(nfsi);
+	struct inode *inode = &nfsi->vfs_inode;
 
-	if (lo)
+	if (lo) {
-		wait_var_event(lo, pnfs_layout_removed(nfsi, lo));
+		spin_lock(&inode->i_lock);
+		wait_var_event_spinlock(lo, nfsi->layout != lo,
+					&inode->i_lock);
+		spin_unlock(&inode->i_lock);
+	}
 }
 
 static bool
@@ -3340,6 +3332,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	loff_t end_pos;
 	int status;
+	bool mark_as_dirty = false;
 
 	if (!pnfs_layoutcommit_outstanding(inode))
 		return 0;
@@ -3391,19 +3384,23 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	if (ld->prepare_layoutcommit) {
 		status = ld->prepare_layoutcommit(&data->args);
 		if (status) {
-			put_cred(data->cred);
+			if (status != -ENOSPC)
+				put_cred(data->cred);
 			spin_lock(&inode->i_lock);
 			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
 			if (end_pos > nfsi->layout->plh_lwb)
 				nfsi->layout->plh_lwb = end_pos;
-			goto out_unlock;
+			if (status != -ENOSPC)
+				goto out_unlock;
+			spin_unlock(&inode->i_lock);
+			mark_as_dirty = true;
 		}
 	}
 
 
 	status = nfs4_proc_layoutcommit(data, sync);
 out:
-	if (status)
+	if (status || mark_as_dirty)
 		mark_inode_dirty_sync(inode);
 	dprintk("<-- %s status %d\n", __func__, status);
 	return status;

fs/nfs/pnfs_nfs.c

@@ -17,6 +17,7 @@
 #include "internal.h"
 #include "pnfs.h"
 #include "netns.h"
+#include "nfs4trace.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
 
@@ -1007,8 +1008,10 @@ int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 		err = nfs4_wait_ds_connect(ds);
 		if (err || ds->ds_clp)
 			goto out;
-		if (nfs4_test_deviceid_unavailable(devid))
+		if (nfs4_test_deviceid_unavailable(devid)) {
-			return -ENODEV;
+			err = -ENODEV;
+			goto out;
+		}
 	} while (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) != 0);
 
 	if (ds->ds_clp)
@@ -1038,11 +1041,12 @@ out:
 		if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) {
 			WARN_ON_ONCE(ds->ds_clp ||
 				!nfs4_test_deviceid_unavailable(devid));
-			return -EINVAL;
+			err = -EINVAL;
-		}
+		} else
-		err = nfs_client_init_status(ds->ds_clp);
+			err = nfs_client_init_status(ds->ds_clp);
 	}
 
+	trace_pnfs_ds_connect(ds->ds_remotestr, err);
 	return err;
 }
 EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);

fs/nfs/write.c

@@ -2113,8 +2113,12 @@ int nfs_migrate_folio(struct address_space *mapping, struct folio *dst,
 	 *        that we can safely release the inode reference while holding
 	 *        the folio lock.
 	 */
-	if (folio_test_private(src))
+	if (folio_test_private(src)) {
-		return -EBUSY;
+		if (mode == MIGRATE_SYNC)
+			nfs_wb_folio(src->mapping->host, src);
+		if (folio_test_private(src))
+			return -EBUSY;
+	}
 
 	if (folio_test_private_2(src)) { /* [DEPRECATED] */
 		if (mode == MIGRATE_ASYNC)

fs/nfs_common/nfslocalio.c

@@ -177,7 +177,7 @@ static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid)
 			/* nfs_close_local_fh() is doing the
 			 * close and we must wait. until it unlinks
 			 */
-			wait_var_event_spinlock(nfl,
+			wait_var_event_spinlock(nfs_uuid,
 						list_first_entry_or_null(
 							&nfs_uuid->files,
 							struct nfs_file_localio,
@@ -198,8 +198,7 @@ static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid)
 		/* Now we can allow racing nfs_close_local_fh() to
 		 * skip the locking.
 		 */
-		RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
+		store_release_wake_up(&nfl->nfs_uuid, RCU_INITIALIZER(NULL));
-		wake_up_var_locked(&nfl->nfs_uuid, &nfs_uuid->lock);
 	}
 
 	/* Remove client from nn->local_clients */
@@ -243,15 +242,20 @@ void nfs_localio_invalidate_clients(struct list_head *nn_local_clients,
 }
 EXPORT_SYMBOL_GPL(nfs_localio_invalidate_clients);
 
-static void nfs_uuid_add_file(nfs_uuid_t *nfs_uuid, struct nfs_file_localio *nfl)
+static int nfs_uuid_add_file(nfs_uuid_t *nfs_uuid, struct nfs_file_localio *nfl)
 {
+	int ret = 0;
+
 	/* Add nfl to nfs_uuid->files if it isn't already */
 	spin_lock(&nfs_uuid->lock);
-	if (list_empty(&nfl->list)) {
+	if (rcu_access_pointer(nfs_uuid->net) == NULL) {
+		ret = -ENXIO;
+	} else if (list_empty(&nfl->list)) {
 		rcu_assign_pointer(nfl->nfs_uuid, nfs_uuid);
 		list_add_tail(&nfl->list, &nfs_uuid->files);
 	}
 	spin_unlock(&nfs_uuid->lock);
+	return ret;
 }
 
 /*
@@ -285,11 +289,13 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 	}
 	rcu_read_unlock();
 	/* We have an implied reference to net thanks to nfsd_net_try_get */
-	localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt,
+	localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt, cred,
-					     cred, nfs_fh, pnf, fmode);
+					     nfs_fh, pnf, fmode);
+	if (!IS_ERR(localio) && nfs_uuid_add_file(uuid, nfl) < 0) {
+		/* Delete the cached file when racing with nfs_uuid_put() */
+		nfs_to_nfsd_file_put_local(pnf);
+	}
 	nfs_to_nfsd_net_put(net);
-	if (!IS_ERR(localio))
-		nfs_uuid_add_file(uuid, nfl);
 
 	return localio;
 }
@@ -314,7 +320,7 @@ void nfs_close_local_fh(struct nfs_file_localio *nfl)
 		rcu_read_unlock();
 		return;
 	}
-	if (list_empty(&nfs_uuid->files)) {
+	if (list_empty(&nfl->list)) {
 		/* nfs_uuid_put() has started closing files, wait for it
 		 * to finished
 		 */
@@ -338,7 +344,7 @@ void nfs_close_local_fh(struct nfs_file_localio *nfl)
 	 */
 	spin_lock(&nfs_uuid->lock);
 	list_del_init(&nfl->list);
-	wake_up_var_locked(&nfl->nfs_uuid, &nfs_uuid->lock);
+	wake_up_var_locked(nfs_uuid, &nfs_uuid->lock);
 	spin_unlock(&nfs_uuid->lock);
 }
 EXPORT_SYMBOL_GPL(nfs_close_local_fh);

include/linux/nfs_fs.h

@@ -160,6 +160,12 @@ struct nfs_inode {
 	unsigned long		flags;			/* atomic bit ops */
 	unsigned long		cache_validity;		/* bit mask */
 
+	/*
+	 * NFS Attributes not included in struct inode
+	 */
+
+	struct timespec64	btime;
+
 	/*
 	 * read_cache_jiffies is when we started read-caching this inode.
 	 * attrtimeo is for how long the cached information is assumed
@@ -316,10 +322,12 @@ struct nfs4_copy_state {
 #define NFS_INO_INVALID_XATTR	BIT(15)		/* xattrs are invalid */
 #define NFS_INO_INVALID_NLINK	BIT(16)		/* cached nlinks is invalid */
 #define NFS_INO_INVALID_MODE	BIT(17)		/* cached mode is invalid */
+#define NFS_INO_INVALID_BTIME	BIT(18)		/* cached btime is invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
 		| NFS_INO_INVALID_MTIME \
+		| NFS_INO_INVALID_BTIME \
 		| NFS_INO_INVALID_SIZE \
 		| NFS_INO_INVALID_NLINK \
 		| NFS_INO_INVALID_MODE \

include/linux/nfs_fs_sb.h

@@ -172,12 +172,11 @@ struct nfs_server {
 #define NFS_MOUNT_FORCE_RDIRPLUS	0x20000000
 #define NFS_MOUNT_NETUNREACH_FATAL	0x40000000
 
-	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
+	__u64			fattr_valid;	/* Valid attributes */
 	unsigned int		rsize;		/* read size */
 	unsigned int		rpages;		/* read size (in pages) */
 	unsigned int		wsize;		/* write size */
-	unsigned int		wpages;		/* write size (in pages) */
 	unsigned int		wtmult;		/* server disk block size */
 	unsigned int		dtsize;		/* readdir size */
 	unsigned short		port;		/* "port=" setting */
@@ -203,7 +202,6 @@ struct nfs_server {
 	struct nfs_fsid		fsid;
 	int			s_sysfs_id;	/* sysfs dentry index */
 	__u64			maxfilesize;	/* maximum file size */
-	struct timespec64	time_delta;	/* smallest time granularity */
 	unsigned long		mount_time;	/* when this fs was mounted */
 	struct super_block	*super;		/* VFS super block */
 	dev_t			s_dev;		/* superblock dev numbers */
@@ -248,7 +246,6 @@ struct nfs_server {
 						   filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
-	void			*pnfs_ld_data;	/* per mount point data */
 
 	/* the following fields are protected by nfs_client->cl_lock */
 	struct rb_root		state_owners;
@@ -257,6 +254,9 @@ struct nfs_server {
 	struct list_head	state_owners_lru;
 	struct list_head	layouts;
 	struct list_head	delegations;
+	atomic_long_t		nr_active_delegations;
+	unsigned int		delegation_hash_mask;
+	struct hlist_head	*delegation_hash_table;
 	struct list_head	ss_copies;
 	struct list_head	ss_src_copies;
 

include/linux/nfs_xdr.h

@@ -45,7 +45,7 @@ struct nfs4_threshold {
 };
 
 struct nfs_fattr {
-	unsigned int		valid;		/* which fields are valid */
+	__u64			valid;		/* which fields are valid */
 	umode_t			mode;
 	__u32			nlink;
 	kuid_t			uid;
@@ -67,6 +67,7 @@ struct nfs_fattr {
 	struct timespec64	atime;
 	struct timespec64	mtime;
 	struct timespec64	ctime;
+	struct timespec64	btime;
 	__u64			change_attr;	/* NFSv4 change attribute */
 	__u64			pre_change_attr;/* pre-op NFSv4 change attribute */
 	__u64			pre_size;	/* pre_op_attr.size	  */
@@ -80,32 +81,33 @@ struct nfs_fattr {
 	struct nfs4_label	*label;
 };
 
-#define NFS_ATTR_FATTR_TYPE		(1U << 0)
+#define NFS_ATTR_FATTR_TYPE		BIT_ULL(0)
-#define NFS_ATTR_FATTR_MODE		(1U << 1)
+#define NFS_ATTR_FATTR_MODE		BIT_ULL(1)
-#define NFS_ATTR_FATTR_NLINK		(1U << 2)
+#define NFS_ATTR_FATTR_NLINK		BIT_ULL(2)
-#define NFS_ATTR_FATTR_OWNER		(1U << 3)
+#define NFS_ATTR_FATTR_OWNER		BIT_ULL(3)
-#define NFS_ATTR_FATTR_GROUP		(1U << 4)
+#define NFS_ATTR_FATTR_GROUP		BIT_ULL(4)
-#define NFS_ATTR_FATTR_RDEV		(1U << 5)
+#define NFS_ATTR_FATTR_RDEV		BIT_ULL(5)
-#define NFS_ATTR_FATTR_SIZE		(1U << 6)
+#define NFS_ATTR_FATTR_SIZE		BIT_ULL(6)
-#define NFS_ATTR_FATTR_PRESIZE		(1U << 7)
+#define NFS_ATTR_FATTR_PRESIZE		BIT_ULL(7)
-#define NFS_ATTR_FATTR_BLOCKS_USED	(1U << 8)
+#define NFS_ATTR_FATTR_BLOCKS_USED	BIT_ULL(8)
-#define NFS_ATTR_FATTR_SPACE_USED	(1U << 9)
+#define NFS_ATTR_FATTR_SPACE_USED	BIT_ULL(9)
-#define NFS_ATTR_FATTR_FSID		(1U << 10)
+#define NFS_ATTR_FATTR_FSID		BIT_ULL(10)
-#define NFS_ATTR_FATTR_FILEID		(1U << 11)
+#define NFS_ATTR_FATTR_FILEID		BIT_ULL(11)
-#define NFS_ATTR_FATTR_ATIME		(1U << 12)
+#define NFS_ATTR_FATTR_ATIME		BIT_ULL(12)
-#define NFS_ATTR_FATTR_MTIME		(1U << 13)
+#define NFS_ATTR_FATTR_MTIME		BIT_ULL(13)
-#define NFS_ATTR_FATTR_CTIME		(1U << 14)
+#define NFS_ATTR_FATTR_CTIME		BIT_ULL(14)
-#define NFS_ATTR_FATTR_PREMTIME		(1U << 15)
+#define NFS_ATTR_FATTR_PREMTIME		BIT_ULL(15)
-#define NFS_ATTR_FATTR_PRECTIME		(1U << 16)
+#define NFS_ATTR_FATTR_PRECTIME		BIT_ULL(16)
-#define NFS_ATTR_FATTR_CHANGE		(1U << 17)
+#define NFS_ATTR_FATTR_CHANGE		BIT_ULL(17)
-#define NFS_ATTR_FATTR_PRECHANGE	(1U << 18)
+#define NFS_ATTR_FATTR_PRECHANGE	BIT_ULL(18)
-#define NFS_ATTR_FATTR_V4_LOCATIONS	(1U << 19)
+#define NFS_ATTR_FATTR_V4_LOCATIONS	BIT_ULL(19)
-#define NFS_ATTR_FATTR_V4_REFERRAL	(1U << 20)
+#define NFS_ATTR_FATTR_V4_REFERRAL	BIT_ULL(20)
-#define NFS_ATTR_FATTR_MOUNTPOINT	(1U << 21)
+#define NFS_ATTR_FATTR_MOUNTPOINT	BIT_ULL(21)
-#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID (1U << 22)
+#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID BIT_ULL(22)
-#define NFS_ATTR_FATTR_OWNER_NAME	(1U << 23)
+#define NFS_ATTR_FATTR_OWNER_NAME	BIT_ULL(23)
-#define NFS_ATTR_FATTR_GROUP_NAME	(1U << 24)
+#define NFS_ATTR_FATTR_GROUP_NAME	BIT_ULL(24)
-#define NFS_ATTR_FATTR_V4_SECURITY_LABEL (1U << 25)
+#define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25)
+#define NFS_ATTR_FATTR_BTIME		BIT_ULL(26)
 
 #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \
 		| NFS_ATTR_FATTR_MODE \
@@ -126,6 +128,7 @@ struct nfs_fattr {
 		| NFS_ATTR_FATTR_SPACE_USED)
 #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \
 		| NFS_ATTR_FATTR_SPACE_USED \
+		| NFS_ATTR_FATTR_BTIME \
 		| NFS_ATTR_FATTR_V4_SECURITY_LABEL)
 
 /*

include/linux/sunrpc/xdr.h

@@ -130,10 +130,7 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 __be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int len);
 __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int len);
 __be32 *xdr_encode_string(__be32 *p, const char *s);
-__be32 *xdr_decode_string_inplace(__be32 *p, char **sp, unsigned int *lenp,
-			unsigned int maxlen);
 __be32 *xdr_encode_netobj(__be32 *p, const struct xdr_netobj *);
-__be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *);
 
 void	xdr_inline_pages(struct xdr_buf *, unsigned int,
 			 struct page **, unsigned int, unsigned int);
@@ -342,12 +339,6 @@ xdr_stream_remaining(const struct xdr_stream *xdr)
 	return xdr->nwords << 2;
 }
 
-ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr,
-		size_t size);
-ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr,
-		size_t maxlen, gfp_t gfp_flags);
-ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str,
-		size_t size);
 ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str,
 		size_t maxlen, gfp_t gfp_flags);
 ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor,

net/sunrpc/auth_gss/gss_krb5_crypto.c

@@ -875,8 +875,8 @@ out_err:
  * krb5_etm_decrypt - Decrypt using the RFC 8009 rules
  * @kctx: Kerberos context
  * @offset: starting offset of the ciphertext, in bytes
- * @len:
+ * @len: size of ciphertext to unwrap
- * @buf:
+ * @buf: ciphertext to unwrap
  * @headskip: OUT: the enctype's confounder length, in octets
  * @tailskip: OUT: the enctype's HMAC length, in octets
  *

net/sunrpc/xdr.c

@@ -37,19 +37,6 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj)
 }
 EXPORT_SYMBOL_GPL(xdr_encode_netobj);
 
-__be32 *
-xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj)
-{
-	unsigned int	len;
-
-	if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ)
-		return NULL;
-	obj->len  = len;
-	obj->data = (u8 *) p;
-	return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_netobj);
-
 /**
  * xdr_encode_opaque_fixed - Encode fixed length opaque data
  * @p: pointer to current position in XDR buffer.
@@ -102,21 +89,6 @@ xdr_encode_string(__be32 *p, const char *string)
 }
 EXPORT_SYMBOL_GPL(xdr_encode_string);
 
-__be32 *
-xdr_decode_string_inplace(__be32 *p, char **sp,
-			  unsigned int *lenp, unsigned int maxlen)
-{
-	u32 len;
-
-	len = be32_to_cpu(*p++);
-	if (len > maxlen)
-		return NULL;
-	*lenp = len;
-	*sp = (char *) p;
-	return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
-
 /**
  * xdr_terminate_string - '\0'-terminate a string residing in an xdr_buf
  * @buf: XDR buffer where string resides
@@ -2244,88 +2216,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(xdr_process_buf);
 
-/**
- * xdr_stream_decode_opaque - Decode variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store opaque data
- * @size: size of storage buffer @ptr
- *
- * Return values:
- *   On success, returns size of object stored in *@ptr
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE on overflow of storage buffer @ptr
- */
-ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, size_t size)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
-	if (ret <= 0)
-		return ret;
-	memcpy(ptr, p, ret);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque);
-
-/**
- * xdr_stream_decode_opaque_dup - Decode and duplicate variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store pointer to opaque data
- * @maxlen: maximum acceptable object size
- * @gfp_flags: GFP mask to use
- *
- * Return values:
- *   On success, returns size of object stored in *@ptr
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE if the size of the object would exceed @maxlen
- *   %-ENOMEM on memory allocation failure
- */
-ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr,
-		size_t maxlen, gfp_t gfp_flags)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen);
-	if (ret > 0) {
-		*ptr = kmemdup(p, ret, gfp_flags);
-		if (*ptr != NULL)
-			return ret;
-		ret = -ENOMEM;
-	}
-	*ptr = NULL;
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_dup);
-
-/**
- * xdr_stream_decode_string - Decode variable length string
- * @xdr: pointer to xdr_stream
- * @str: location to store string
- * @size: size of storage buffer @str
- *
- * Return values:
- *   On success, returns length of NUL-terminated string stored in *@str
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE on overflow of storage buffer @str
- */
-ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
-	if (ret > 0) {
-		memcpy(str, p, ret);
-		str[ret] = '\0';
-		return strlen(str);
-	}
-	*str = '\0';
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_string);
-
 /**
  * xdr_stream_decode_string_dup - Decode and duplicate variable length string
  * @xdr: pointer to xdr_stream

net/sunrpc/xprtsock.c

@@ -358,7 +358,7 @@ xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp)
 
 static int
 xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
-		     struct cmsghdr *cmsg, int ret)
+		     unsigned int *msg_flags, struct cmsghdr *cmsg, int ret)
 {
 	u8 content_type = tls_get_record_type(sock->sk, cmsg);
 	u8 level, description;
@@ -371,7 +371,7 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 		 * record, even though there might be more frames
 		 * waiting to be decrypted.
 		 */
-		msg->msg_flags &= ~MSG_EOR;
+		*msg_flags &= ~MSG_EOR;
 		break;
 	case TLS_RECORD_TYPE_ALERT:
 		tls_alert_recv(sock->sk, msg, &level, &description);
@@ -386,19 +386,33 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 }
 
 static int
-xs_sock_recv_cmsg(struct socket *sock, struct msghdr *msg, int flags)
+xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags)
 {
 	union {
 		struct cmsghdr	cmsg;
 		u8		buf[CMSG_SPACE(sizeof(u8))];
 	} u;
+	u8 alert[2];
+	struct kvec alert_kvec = {
+		.iov_base = alert,
+		.iov_len = sizeof(alert),
+	};
+	struct msghdr msg = {
+		.msg_flags = *msg_flags,
+		.msg_control = &u,
+		.msg_controllen = sizeof(u),
+	};
 	int ret;
 
-	msg->msg_control = &u;
+	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
-	msg->msg_controllen = sizeof(u);
+		      alert_kvec.iov_len);
-	ret = sock_recvmsg(sock, msg, flags);
+	ret = sock_recvmsg(sock, &msg, flags);
-	if (msg->msg_controllen != sizeof(u))
+	if (ret > 0 &&
-		ret = xs_sock_process_cmsg(sock, msg, &u.cmsg, ret);
+	    tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
+		iov_iter_revert(&msg.msg_iter, ret);
+		ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg,
+					   -EAGAIN);
+	}
 	return ret;
 }
 
@@ -408,7 +422,13 @@ xs_sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags, size_t seek)
 	ssize_t ret;
 	if (seek != 0)
 		iov_iter_advance(&msg->msg_iter, seek);
-	ret = xs_sock_recv_cmsg(sock, msg, flags);
+	ret = sock_recvmsg(sock, msg, flags);
+	/* Handle TLS inband control message lazily */
+	if (msg->msg_flags & MSG_CTRUNC) {
+		msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
+		if (ret == 0 || ret == -EIO)
+			ret = xs_sock_recv_cmsg(sock, &msg->msg_flags, flags);
+	}
 	return ret > 0 ? ret + seek : ret;
 }
 
@@ -434,7 +454,7 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags,
 		size_t count)
 {
 	iov_iter_discard(&msg->msg_iter, ITER_DEST, count);
-	return xs_sock_recv_cmsg(sock, msg, flags);
+	return xs_sock_recvmsg(sock, msg, flags, 0);
 }
 
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE