1 files changed, 329 insertions, 63 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index e21c073158e5..f76fe406937a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -74,6 +74,8 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
 
 int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
+	if (unlikely(nfs_current_task_exiting()))
+		return -EINTR;
 	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;
@@ -106,7 +108,7 @@ u64 nfs_compat_user_ino64(u64 fileid)
 
 int nfs_drop_inode(struct inode *inode)
 {
-	return NFS_STALE(inode) || generic_drop_inode(inode);
+	return NFS_STALE(inode) || inode_generic_drop(inode);
 }
 EXPORT_SYMBOL_GPL(nfs_drop_inode);
 
@@ -190,12 +192,12 @@ static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi)
 void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
-	bool have_delegation = NFS_PROTO(inode)->have_delegation(inode, FMODE_READ);
 
-	if (have_delegation) {
+	if (nfs_have_delegated_attributes(inode)) {
 		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);
 	}
@@ -206,12 +208,15 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 		nfs_fscache_invalidate(inode, 0);
 	flags &= ~NFS_INO_REVAL_FORCED;
 
-	nfsi->cache_validity |= flags;
+	flags |= nfsi->cache_validity;
+	if (inode->i_mapping->nrpages == 0)
+		flags &= ~NFS_INO_INVALID_DATA;
 
-	if (inode->i_mapping->nrpages == 0) {
-		nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
-		nfs_ooo_clear(nfsi);
-	} else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
+	/* pairs with nfs_clear_invalid_mapping()'s smp_load_acquire() */
+	smp_store_release(&nfsi->cache_validity, flags);
+
+	if (inode->i_mapping->nrpages == 0 ||
+	    nfsi->cache_validity & NFS_INO_INVALID_DATA) {
 		nfs_ooo_clear(nfsi);
 	}
 	trace_nfs_set_cache_invalid(inode, 0);
@@ -276,6 +281,8 @@ EXPORT_SYMBOL_GPL(nfs_zap_acl_cache);
 
 void nfs_invalidate_atime(struct inode *inode)
 {
+	if (nfs_have_delegated_atime(inode))
+		return;
 	spin_lock(&inode->i_lock);
 	nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
 	spin_unlock(&inode->i_lock);
@@ -468,7 +475,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		goto out_no_inode;
 	}
 
-	if (inode->i_state & I_NEW) {
+	if (inode_state_read_once(inode) & I_NEW) {
 		struct nfs_inode *nfsi = NFS_I(inode);
 		unsigned long now = jiffies;
 
@@ -491,6 +498,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
 			nfs_inode_init_regular(nfsi);
+			mapping_set_large_folios(inode->i_mapping);
 		} else if (S_ISDIR(inode->i_mode)) {
 			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
@@ -512,9 +520,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		} else
 			init_special_inode(inode, inode->i_mode, fattr->rdev);
 
-		memset(&inode->i_atime, 0, sizeof(inode->i_atime));
-		memset(&inode->i_mtime, 0, sizeof(inode->i_mtime));
+		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);
@@ -527,17 +536,21 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		nfsi->read_cache_jiffies = fattr->time_start;
 		nfsi->attr_gencount = fattr->gencount;
 		if (fattr->valid & NFS_ATTR_FATTR_ATIME)
-			inode->i_atime = fattr->atime;
+			inode_set_atime_to_ts(inode, fattr->atime);
 		else if (fattr_supported & NFS_ATTR_FATTR_ATIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
 		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
-			inode->i_mtime = fattr->mtime;
+			inode_set_mtime_to_ts(inode, fattr->mtime);
 		else if (fattr_supported & NFS_ATTR_FATTR_MTIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
 			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
@@ -550,6 +563,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 		else if (fattr_supported & NFS_ATTR_FATTR_NLINK)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK);
+		else
+			set_nlink(inode, 1);
 		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
 			inode->i_uid = fattr->uid;
 		else if (fattr_supported & NFS_ATTR_FATTR_OWNER)
@@ -593,7 +608,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode->i_sb->s_id,
 		(unsigned long long)NFS_FILEID(inode),
 		nfs_display_fhandle_hash(fh),
-		atomic_read(&inode->i_count));
+		icount_read(inode));
 
 out:
 	return inode;
@@ -604,6 +619,95 @@ out_no_inode:
 }
 EXPORT_SYMBOL_GPL(nfs_fhget);
 
+static void
+nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr)
+{
+	unsigned long cache_validity = NFS_I(inode)->cache_validity;
+
+	if (nfs_have_delegated_mtime(inode)) {
+		if (!(cache_validity & NFS_INO_INVALID_CTIME))
+			fattr->valid &= ~(NFS_ATTR_FATTR_PRECTIME |
+					  NFS_ATTR_FATTR_CTIME);
+
+		if (!(cache_validity & NFS_INO_INVALID_MTIME))
+			fattr->valid &= ~(NFS_ATTR_FATTR_PREMTIME |
+					  NFS_ATTR_FATTR_MTIME);
+
+		if (!(cache_validity & NFS_INO_INVALID_ATIME))
+			fattr->valid &= ~NFS_ATTR_FATTR_ATIME;
+	} else if (nfs_have_delegated_atime(inode)) {
+		if (!(cache_validity & NFS_INO_INVALID_ATIME))
+			fattr->valid &= ~NFS_ATTR_FATTR_ATIME;
+	}
+}
+
+static void nfs_set_timestamps_to_ts(struct inode *inode, struct iattr *attr)
+{
+	unsigned int cache_flags = 0;
+
+	if (attr->ia_valid & ATTR_MTIME_SET) {
+		struct timespec64 ctime = inode_get_ctime(inode);
+		struct timespec64 mtime = inode_get_mtime(inode);
+		struct timespec64 now;
+		int updated = 0;
+
+		now = inode_set_ctime_current(inode);
+		if (!timespec64_equal(&now, &ctime))
+			updated |= S_CTIME;
+
+		inode_set_mtime_to_ts(inode, attr->ia_mtime);
+		if (!timespec64_equal(&now, &mtime))
+			updated |= S_MTIME;
+
+		inode_maybe_inc_iversion(inode, updated);
+		cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
+	}
+	if (attr->ia_valid & ATTR_ATIME_SET) {
+		inode_set_atime_to_ts(inode, attr->ia_atime);
+		cache_flags |= NFS_INO_INVALID_ATIME;
+	}
+	NFS_I(inode)->cache_validity &= ~cache_flags;
+}
+
+static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid)
+{
+	enum file_time_flags time_flags = 0;
+	unsigned int cache_flags = 0;
+
+	if (ia_valid & ATTR_MTIME) {
+		time_flags |= S_MTIME | S_CTIME;
+		cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
+	}
+	if (ia_valid & ATTR_ATIME) {
+		time_flags |= S_ATIME;
+		cache_flags |= NFS_INO_INVALID_ATIME;
+	}
+	inode_update_timestamps(inode, time_flags);
+	NFS_I(inode)->cache_validity &= ~cache_flags;
+}
+
+void nfs_update_delegated_atime(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	if (nfs_have_delegated_atime(inode))
+		nfs_update_timestamps(inode, ATTR_ATIME);
+	spin_unlock(&inode->i_lock);
+}
+
+void nfs_update_delegated_mtime_locked(struct inode *inode)
+{
+	if (nfs_have_delegated_mtime(inode))
+		nfs_update_timestamps(inode, ATTR_MTIME);
+}
+
+void nfs_update_delegated_mtime(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	nfs_update_delegated_mtime_locked(inode);
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_update_delegated_mtime);
+
 #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN)
 
 int
@@ -612,7 +716,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 {
 	struct inode *inode = d_inode(dentry);
 	struct nfs_fattr *fattr;
+	loff_t oldsize = i_size_read(inode);
 	int error = 0;
+	kuid_t task_uid = current_fsuid();
+	kuid_t owner_uid = inode->i_uid;
 
 	nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
 
@@ -627,10 +734,39 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		if (error)
 			return error;
 
-		if (attr->ia_size == i_size_read(inode))
+		if (attr->ia_size == oldsize)
 			attr->ia_valid &= ~ATTR_SIZE;
 	}
 
+	if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) {
+		spin_lock(&inode->i_lock);
+		if (attr->ia_valid & ATTR_MTIME_SET) {
+			if (uid_eq(task_uid, owner_uid)) {
+				nfs_set_timestamps_to_ts(inode, attr);
+				attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
+						ATTR_ATIME|ATTR_ATIME_SET);
+			}
+		} else {
+			nfs_update_timestamps(inode, attr->ia_valid);
+			attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME);
+		}
+		spin_unlock(&inode->i_lock);
+	} else if (nfs_have_delegated_atime(inode) &&
+		   attr->ia_valid & ATTR_ATIME &&
+		   !(attr->ia_valid & ATTR_MTIME)) {
+		if (attr->ia_valid & ATTR_ATIME_SET) {
+			if (uid_eq(task_uid, owner_uid)) {
+				spin_lock(&inode->i_lock);
+				nfs_set_timestamps_to_ts(inode, attr);
+				spin_unlock(&inode->i_lock);
+				attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+			}
+		} else {
+			nfs_update_delegated_atime(inode);
+			attr->ia_valid &= ~ATTR_ATIME;
+		}
+	}
+
 	/* Optimization: if the end result is no change, don't RPC */
 	if (((attr->ia_valid & NFS_VALID_ATTRS) & ~(ATTR_FILE|ATTR_OPEN)) == 0)
 		return 0;
@@ -638,8 +774,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	trace_nfs_setattr_enter(inode);
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode))
+	if (S_ISREG(inode->i_mode)) {
+		nfs_file_block_o_direct(NFS_I(inode));
 		nfs_sync_inode(inode);
+	}
 
 	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
 	if (fattr == NULL) {
@@ -648,8 +786,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	}
 
 	error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
-	if (error == 0)
+	if (error == 0) {
+		if (attr->ia_valid & ATTR_SIZE)
+			nfs_truncate_last_folio(inode->i_mapping, oldsize,
+						attr->ia_size);
 		error = nfs_refresh_inode(inode, fattr);
+	}
 	nfs_free_fattr(fattr);
 out:
 	trace_nfs_setattr_exit(inode, error);
@@ -686,6 +828,7 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 
 	spin_unlock(&inode->i_lock);
 	truncate_pagecache(inode, offset);
+	nfs_update_delegated_mtime_locked(inode);
 	spin_lock(&inode->i_lock);
 out:
 	return err;
@@ -709,8 +852,9 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
 	spin_lock(&inode->i_lock);
 	NFS_I(inode)->attr_gencount = fattr->gencount;
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
-		nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME |
-						     NFS_INO_INVALID_BLOCKS);
+		if (!nfs_have_delegated_mtime(inode))
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
 		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
@@ -742,9 +886,9 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
 		NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME
 				| NFS_INO_INVALID_CTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_ATIME)
-			inode->i_atime = fattr->atime;
+			inode_set_atime_to_ts(inode, fattr->atime);
 		else if (attr->ia_valid & ATTR_ATIME_SET)
-			inode->i_atime = attr->ia_atime;
+			inode_set_atime_to_ts(inode, attr->ia_atime);
 		else
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
 
@@ -758,9 +902,9 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
 		NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME
 				| NFS_INO_INVALID_CTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
-			inode->i_mtime = fattr->mtime;
+			inode_set_mtime_to_ts(inode, fattr->mtime);
 		else if (attr->ia_valid & ATTR_MTIME_SET)
-			inode->i_mtime = attr->ia_mtime;
+			inode_set_mtime_to_ts(inode, attr->ia_mtime);
 		else
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
 
@@ -806,6 +950,7 @@ 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;
 
@@ -825,6 +970,9 @@ 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;
@@ -835,6 +983,7 @@ 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;
@@ -845,9 +994,12 @@ 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);
@@ -856,8 +1008,12 @@ int nfs_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 	/* Flush out writes to the server in order to update c/mtime/version.  */
 	if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_CHANGE_COOKIE)) &&
-	    S_ISREG(inode->i_mode))
-		filemap_write_and_wait(inode->i_mapping);
+	    S_ISREG(inode->i_mode)) {
+		if (nfs_have_delegated_mtime(inode))
+			filemap_fdatawrite(inode->i_mapping);
+		else
+			filemap_write_and_wait(inode->i_mapping);
+	}
 
 	/*
 	 * We may force a getattr if the user cares about atime.
@@ -875,7 +1031,7 @@ 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;
 
@@ -899,6 +1055,8 @@ 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)
@@ -920,6 +1078,22 @@ 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;
+
+	/* Special handling for STATX_DIOALIGN and STATX_DIO_READ_ALIGN
+	 * - NFS doesn't have DIO alignment constraints, avoid getting
+	 *   these DIO attrs from remote and just respond with most
+	 *   accommodating limits (so client will issue supported DIO).
+	 * - this is unintuitive, but the most coarse-grained
+	 *   dio_offset_align is the most accommodating.
+	 */
+	if ((request_mask & (STATX_DIOALIGN | STATX_DIO_READ_ALIGN)) &&
+	    S_ISREG(inode->i_mode)) {
+		stat->result_mask |= STATX_DIOALIGN | STATX_DIO_READ_ALIGN;
+		stat->dio_mem_align = 4; /* 4-byte alignment */
+		stat->dio_offset_align = PAGE_SIZE;
+		stat->dio_read_offset_align = stat->dio_offset_align;
+	}
 out:
 	trace_nfs_getattr_exit(inode, err);
 	return err;
@@ -1012,7 +1186,7 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
 	if (!is_sync)
 		return;
 	inode = d_inode(ctx->dentry);
-	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
+	if (nfs_have_read_or_write_delegation(inode))
 		return;
 	nfsi = NFS_I(inode);
 	if (inode->i_mapping->nrpages == 0)
@@ -1053,6 +1227,8 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
 	ctx->lock_context.open_context = ctx;
 	INIT_LIST_HEAD(&ctx->list);
 	ctx->mdsthreshold = NULL;
+	nfs_localio_file_init(&ctx->nfl);
+
 	return ctx;
 }
 EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
@@ -1084,6 +1260,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	nfs_sb_deactive(sb);
 	put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1));
 	kfree(ctx->mdsthreshold);
+	nfs_close_local_fh(&ctx->nfl);
 	kfree_rcu(ctx, rcu_head);
 }
 
@@ -1340,6 +1517,13 @@ int nfs_clear_invalid_mapping(struct address_space *mapping)
 					 TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 		if (ret)
 			goto out;
+		smp_rmb(); /* pairs with smp_wmb() below */
+		if (test_bit(NFS_INO_INVALIDATING, bitlock))
+			continue;
+		/* pairs with nfs_set_cache_invalid()'s smp_store_release() */
+		if (!(smp_load_acquire(&nfsi->cache_validity) & NFS_INO_INVALID_DATA))
+			goto out;
+		/* Slow-path that double-checks with spinlock held */
 		spin_lock(&inode->i_lock);
 		if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
 			spin_unlock(&inode->i_lock);
@@ -1451,11 +1635,11 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		inode_set_ctime_to_ts(inode, fattr->ctime);
 	}
 
-	ts = inode->i_mtime;
+	ts = inode_get_mtime(inode);
 	if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
 			&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
 			&& timespec64_equal(&ts, &fattr->pre_mtime)) {
-		inode->i_mtime = fattr->mtime;
+		inode_set_mtime_to_ts(inode, fattr->mtime);
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
 			&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
@@ -1482,7 +1666,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	unsigned long invalid = 0;
 	struct timespec64 ts;
 
-	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
+	if (nfs_have_delegated_attributes(inode))
 		return 0;
 
 	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
@@ -1506,7 +1690,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr))
 			invalid |= NFS_INO_INVALID_CHANGE;
 
-		ts = inode->i_mtime;
+		ts = inode_get_mtime(inode);
 		if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime))
 			invalid |= NFS_INO_INVALID_MTIME;
 
@@ -1534,7 +1718,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
 		invalid |= NFS_INO_INVALID_NLINK;
 
-	ts = inode->i_atime;
+	ts = inode_get_atime(inode);
 	if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime))
 		invalid |= NFS_INO_INVALID_ATIME;
 
@@ -1565,6 +1749,7 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 	fattr->gencount = nfs_inc_attr_generation_counter();
 	fattr->owner_name = NULL;
 	fattr->group_name = NULL;
+	fattr->mdsthreshold = NULL;
 }
 EXPORT_SYMBOL_GPL(nfs_fattr_init);
 
@@ -1803,7 +1988,7 @@ 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;
 
@@ -2002,7 +2187,7 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 &&
 			(fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) {
-		fattr->pre_mtime = inode->i_mtime;
+		fattr->pre_mtime = inode_get_mtime(inode);
 		fattr->valid |= NFS_ATTR_FATTR_PREMTIME;
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 &&
@@ -2069,10 +2254,10 @@ 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);
+			icount_read(inode), fattr->valid);
 
 	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
 		/* Only a mounted-on-fileid? Just exit */
@@ -2118,6 +2303,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	 */
 	nfsi->read_cache_jiffies = fattr->time_start;
 
+	/* Fix up any delegated attributes in the struct nfs_fattr */
+	nfs_fattr_fixup_delegated(inode, fattr);
+
 	save_cache_validity = nfsi->cache_validity;
 	nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
 			| NFS_INO_INVALID_ATIME
@@ -2161,7 +2349,8 @@ 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;
@@ -2184,7 +2373,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME)
-		inode->i_mtime = fattr->mtime;
+		inode_set_mtime_to_ts(inode, fattr->mtime);
 	else if (fattr_supported & NFS_ATTR_FATTR_MTIME)
 		nfsi->cache_validity |=
 			save_cache_validity & NFS_INO_INVALID_MTIME;
@@ -2195,6 +2384,12 @@ 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);
@@ -2220,7 +2415,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			save_cache_validity & NFS_INO_INVALID_SIZE;
 
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
-		inode->i_atime = fattr->atime;
+		inode_set_atime_to_ts(inode, fattr->atime);
 	else if (fattr_supported & NFS_ATTR_FATTR_ATIME)
 		nfsi->cache_validity |=
 			save_cache_validity & NFS_INO_INVALID_ATIME;
@@ -2372,7 +2567,7 @@ static int __init nfs_init_inodecache(void)
 	nfs_inode_cachep = kmem_cache_create("nfs_inode_cache",
 					     sizeof(struct nfs_inode),
 					     0, (SLAB_RECLAIM_ACCOUNT|
-						SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+						SLAB_ACCOUNT),
 					     init_once);
 	if (nfs_inode_cachep == NULL)
 		return -ENOMEM;
@@ -2390,35 +2585,54 @@ static void nfs_destroy_inodecache(void)
 	kmem_cache_destroy(nfs_inode_cachep);
 }
 
+struct workqueue_struct *nfslocaliod_workqueue;
 struct workqueue_struct *nfsiod_workqueue;
 EXPORT_SYMBOL_GPL(nfsiod_workqueue);
 
 /*
- * start up the nfsiod workqueue
+ * Destroy the nfsiod workqueues
  */
-static int nfsiod_start(void)
+static void nfsiod_stop(void)
 {
 	struct workqueue_struct *wq;
-	dprintk("RPC:       creating workqueue nfsiod\n");
-	wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
-	if (wq == NULL)
-		return -ENOMEM;
-	nfsiod_workqueue = wq;
-	return 0;
+
+	wq = nfsiod_workqueue;
+	if (wq != NULL) {
+		nfsiod_workqueue = NULL;
+		destroy_workqueue(wq);
+	}
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	wq = nfslocaliod_workqueue;
+	if (wq != NULL) {
+		nfslocaliod_workqueue = NULL;
+		destroy_workqueue(wq);
+	}
+#endif /* CONFIG_NFS_LOCALIO */
 }
 
 /*
- * Destroy the nfsiod workqueue
+ * Start the nfsiod workqueues
  */
-static void nfsiod_stop(void)
+static int nfsiod_start(void)
 {
-	struct workqueue_struct *wq;
-
-	wq = nfsiod_workqueue;
-	if (wq == NULL)
-		return;
-	nfsiod_workqueue = NULL;
-	destroy_workqueue(wq);
+	dprintk("RPC:       creating workqueue nfsiod\n");
+	nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
+	if (nfsiod_workqueue == NULL)
+		return -ENOMEM;
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	/*
+	 * localio writes need to use a normal (non-memreclaim) workqueue.
+	 * When we start getting low on space, XFS goes and calls flush_work() on
+	 * a non-memreclaim work queue, which causes a priority inversion problem.
+	 */
+	dprintk("RPC:       creating workqueue nfslocaliod\n");
+	nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0);
+	if (unlikely(nfslocaliod_workqueue == NULL)) {
+		nfsiod_stop();
+		return -ENOMEM;
+	}
+#endif /* CONFIG_NFS_LOCALIO */
+	return 0;
 }
 
 unsigned int nfs_net_id;
@@ -2426,12 +2640,32 @@ EXPORT_SYMBOL_GPL(nfs_net_id);
 
 static int nfs_net_init(struct net *net)
 {
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	int err;
+
 	nfs_clients_init(net);
-	return nfs_fs_proc_net_init(net);
+
+	if (!rpc_proc_register(net, &nn->rpcstats)) {
+		err = -ENOMEM;
+		goto err_proc_rpc;
+	}
+
+	err = nfs_fs_proc_net_init(net);
+	if (err)
+		goto err_proc_nfs;
+
+	return 0;
+
+err_proc_nfs:
+	rpc_proc_unregister(net, "nfs");
+err_proc_rpc:
+	nfs_clients_exit(net);
+	return err;
 }
 
 static void nfs_net_exit(struct net *net)
 {
+	rpc_proc_unregister(net, "nfs");
 	nfs_fs_proc_net_exit(net);
 	nfs_clients_exit(net);
 }
@@ -2443,6 +2677,35 @@ 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
  */
@@ -2450,6 +2713,10 @@ 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;
@@ -2486,15 +2753,12 @@ static int __init init_nfs_fs(void)
 	if (err)
 		goto out1;
 
-	rpc_proc_register(&init_net, &nfs_rpcstat);
-
 	err = register_nfs_fs();
 	if (err)
 		goto out0;
 
 	return 0;
 out0:
-	rpc_proc_unregister(&init_net, "nfs");
 	nfs_destroy_directcache();
 out1:
 	nfs_destroy_writepagecache();
@@ -2513,6 +2777,7 @@ out7:
 out9:
 	nfs_sysfs_exit();
 out10:
+	nfs_exit_keyring();
 	return err;
 }
 
@@ -2524,15 +2789,16 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
 	unregister_pernet_subsys(&nfs_net_ops);
-	rpc_proc_unregister(&init_net, "nfs");
 	unregister_nfs_fs();
 	nfs_fs_proc_exit();
 	nfsiod_stop();
 	nfs_sysfs_exit();
+	nfs_exit_keyring();
 }
 
 /* Not quite true; I just maintain it */
 MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
+MODULE_DESCRIPTION("NFS client support");
 MODULE_LICENSE("GPL");
 module_param(enable_ino64, bool, 0644);