Merge tag 'nfsd-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "This release completes the SunRPC thread scheduler work that was begun
  in v6.6. The scheduler can now find an svc thread to wake in constant
  time and without a list walk. Thanks again to Neil Brown for this
  overhaul.

  Lorenzo Bianconi contributed infrastructure for a netlink-based NFSD
  control plane. The long-term plan is to provide the same functionality
  as found in /proc/fs/nfsd, plus some interesting additions, and then
  migrate the NFSD user space utilities to netlink.

  A long series to overhaul NFSD's NFSv4 operation encoding was applied
  in this release. The goals are to bring this family of encoding
  functions in line with the matching NFSv4 decoding functions and with
  the NFSv2 and NFSv3 XDR functions, preparing the way for better memory
  safety and maintainability.

  A further improvement to NFSD's write delegation support was
  contributed by Dai Ngo. This adds a CB_GETATTR callback, enabling the
  server to retrieve cached size and mtime data from clients holding
  write delegations. If the server can retrieve this information, it
  does not have to recall the delegation in some cases.

  The usual panoply of bug fixes and minor improvements round out this
  release. As always I am grateful to all contributors, reviewers, and
  testers"

* tag 'nfsd-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (127 commits)
  svcrdma: Fix tracepoint printk format
  svcrdma: Drop connection after an RDMA Read error
  NFSD: clean up alloc_init_deleg()
  NFSD: Fix frame size warning in svc_export_parse()
  NFSD: Rewrite synopsis of nfsd_percpu_counters_init()
  nfsd: Clean up errors in nfs3proc.c
  nfsd: Clean up errors in nfs4state.c
  NFSD: Clean up errors in stats.c
  NFSD: simplify error paths in nfsd_svc()
  NFSD: Clean up nfsd4_encode_seek()
  NFSD: Clean up nfsd4_encode_offset_status()
  NFSD: Clean up nfsd4_encode_copy_notify()
  NFSD: Clean up nfsd4_encode_copy()
  NFSD: Clean up nfsd4_encode_test_stateid()
  NFSD: Clean up nfsd4_encode_exchange_id()
  NFSD: Clean up nfsd4_do_encode_secinfo()
  NFSD: Clean up nfsd4_encode_access()
  NFSD: Clean up nfsd4_encode_readdir()
  NFSD: Clean up nfsd4_encode_entry4()
  NFSD: Add an nfsd4_encode_nfs_cookie4() helper
  ...

12 files changed, 459 insertions, 91 deletions

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 11fbd0ee1370..6dd993240fcc 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -224,9 +224,23 @@ struct export_operations {
 						  atomic attribute updates
 						*/
 #define EXPORT_OP_FLUSH_ON_CLOSE	(0x20) /* fs flushes file data on close */
+#define EXPORT_OP_ASYNC_LOCK		(0x40) /* fs can do async lock request */
 	unsigned long	flags;
 };
 
+/**
+ * exportfs_lock_op_is_async() - export op supports async lock operation
+ * @export_ops:	the nfs export operations to check
+ *
+ * Returns true if the nfs export_operations structure has
+ * EXPORT_OP_ASYNC_LOCK in their flags set
+ */
+static inline bool
+exportfs_lock_op_is_async(const struct export_operations *export_ops)
+{
+	return export_ops->flags & EXPORT_OP_ASYNC_LOCK;
+}
+
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
 				    int *max_len, struct inode *parent,
 				    int flags);
diff --git a/include/linux/iversion.h b/include/linux/iversion.h
index f174ff1b59ee..8f972eaca2ed 100644
--- a/include/linux/iversion.h
+++ b/include/linux/iversion.h
@@ -256,7 +256,7 @@ inode_peek_iversion(const struct inode *inode)
  * For filesystems without any sort of change attribute, the best we can
  * do is fake one up from the ctime:
  */
-static inline u64 time_to_chattr(struct timespec64 *t)
+static inline u64 time_to_chattr(const struct timespec64 *t)
 {
 	u64 chattr = t->tv_sec;
 
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 85bda2d02d65..2c982ff7475a 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -74,6 +74,33 @@ static inline void init_llist_head(struct llist_head *list)
 }
 
 /**
+ * init_llist_node - initialize lock-less list node
+ * @node:	the node to be initialised
+ *
+ * In cases where there is a need to test if a node is on
+ * a list or not, this initialises the node to clearly
+ * not be on any list.
+ */
+static inline void init_llist_node(struct llist_node *node)
+{
+	node->next = node;
+}
+
+/**
+ * llist_on_list - test if a lock-list list node is on a list
+ * @node:	the node to test
+ *
+ * When a node is on a list the ->next pointer will be NULL or
+ * some other node.  It can never point to itself.  We use that
+ * in init_llist_node() to record that a node is not on any list,
+ * and here to test whether it is on any list.
+ */
+static inline bool llist_on_list(const struct llist_node *node)
+{
+	return node->next != node;
+}
+
+/**
  * llist_entry - get the struct of this entry
  * @ptr:	the &struct llist_node pointer.
  * @type:	the type of the struct this is embedded in.
@@ -249,6 +276,25 @@ static inline struct llist_node *__llist_del_all(struct llist_head *head)
 
 extern struct llist_node *llist_del_first(struct llist_head *head);
 
+/**
+ * llist_del_first_init - delete first entry from lock-list and mark is as being off-list
+ * @head:	the head of lock-less list to delete from.
+ *
+ * This behave the same as llist_del_first() except that llist_init_node() is called
+ * on the returned node so that llist_on_list() will report false for the node.
+ */
+static inline struct llist_node *llist_del_first_init(struct llist_head *head)
+{
+	struct llist_node *n = llist_del_first(head);
+
+	if (n)
+		init_llist_node(n);
+	return n;
+}
+
+extern bool llist_del_first_this(struct llist_head *head,
+				 struct llist_node *this);
+
 struct llist_node *llist_reverse_order(struct llist_node *head);
 
 #endif /* LLIST_H */
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 0f016d69c996..9f565416d186 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -282,7 +282,7 @@ __be32		  nlmsvc_testlock(struct svc_rqst *, struct nlm_file *,
 			struct nlm_host *, struct nlm_lock *,
 			struct nlm_lock *, struct nlm_cookie *);
 __be32		  nlmsvc_cancel_blocked(struct net *net, struct nlm_file *, struct nlm_lock *);
-void		  nlmsvc_retry_blocked(void);
+void		  nlmsvc_retry_blocked(struct svc_rqst *rqstp);
 void		  nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *,
 					nlm_host_match_fn_t match);
 void		  nlmsvc_grant_reply(struct nlm_cookie *, __be32);
diff --git a/include/linux/lwq.h b/include/linux/lwq.h
new file mode 100644
index 000000000000..d081d5cf8e33
--- /dev/null
+++ b/include/linux/lwq.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef LWQ_H
+#define LWQ_H
+/*
+ * Light-weight single-linked queue built from llist
+ *
+ * Entries can be enqueued from any context with no locking.
+ * Entries can be dequeued from process context with integrated locking.
+ *
+ * This is particularly suitable when work items are queued in
+ * BH or IRQ context, and where work items are handled one at a time
+ * by dedicated threads.
+ */
+#include <linux/container_of.h>
+#include <linux/spinlock.h>
+#include <linux/llist.h>
+
+struct lwq_node {
+	struct llist_node node;
+};
+
+struct lwq {
+	spinlock_t		lock;
+	struct llist_node	*ready;		/* entries to be dequeued */
+	struct llist_head	new;		/* entries being enqueued */
+};
+
+/**
+ * lwq_init - initialise a lwq
+ * @q:	the lwq object
+ */
+static inline void lwq_init(struct lwq *q)
+{
+	spin_lock_init(&q->lock);
+	q->ready = NULL;
+	init_llist_head(&q->new);
+}
+
+/**
+ * lwq_empty - test if lwq contains any entry
+ * @q:	the lwq object
+ *
+ * This empty test contains an acquire barrier so that if a wakeup
+ * is sent when lwq_dequeue returns true, it is safe to go to sleep after
+ * a test on lwq_empty().
+ */
+static inline bool lwq_empty(struct lwq *q)
+{
+	/* acquire ensures ordering wrt lwq_enqueue() */
+	return smp_load_acquire(&q->ready) == NULL && llist_empty(&q->new);
+}
+
+struct llist_node *__lwq_dequeue(struct lwq *q);
+/**
+ * lwq_dequeue - dequeue first (oldest) entry from lwq
+ * @q:		the queue to dequeue from
+ * @type:	the type of object to return
+ * @member:	them member in returned object which is an lwq_node.
+ *
+ * Remove a single object from the lwq and return it.  This will take
+ * a spinlock and so must always be called in the same context, typcially
+ * process contet.
+ */
+#define lwq_dequeue(q, type, member)					\
+	({ struct llist_node *_n = __lwq_dequeue(q);			\
+	  _n ? container_of(_n, type, member.node) : NULL; })
+
+struct llist_node *lwq_dequeue_all(struct lwq *q);
+
+/**
+ * lwq_for_each_safe - iterate over detached queue allowing deletion
+ * @_n:		iterator variable
+ * @_t1:	temporary struct llist_node **
+ * @_t2:	temporary struct llist_node *
+ * @_l:		address of llist_node pointer from lwq_dequeue_all()
+ * @_member:	member in _n where lwq_node is found.
+ *
+ * Iterate over members in a dequeued list.  If the iterator variable
+ * is set to NULL, the iterator removes that entry from the queue.
+ */
+#define lwq_for_each_safe(_n, _t1, _t2, _l, _member)			\
+	for (_t1 = (_l);						\
+	     *(_t1) ? (_n = container_of(*(_t1), typeof(*(_n)), _member.node),\
+		       _t2 = ((*_t1)->next),				\
+		       true)						\
+	     : false;							\
+	     (_n) ? (_t1 = &(_n)->_member.node.next, 0)			\
+	     : ((*(_t1) = (_t2)),  0))
+
+/**
+ * lwq_enqueue - add a new item to the end of the queue
+ * @n	- the lwq_node embedded in the item to be added
+ * @q	- the lwq to append to.
+ *
+ * No locking is needed to append to the queue so this can
+ * be called from any context.
+ * Return %true is the list may have previously been empty.
+ */
+static inline bool lwq_enqueue(struct lwq_node *n, struct lwq *q)
+{
+	/* acquire enqures ordering wrt lwq_dequeue */
+	return llist_add(&n->node, &q->new) &&
+		smp_load_acquire(&q->ready) == NULL;
+}
+
+/**
+ * lwq_enqueue_batch - add a list of new items to the end of the queue
+ * @n	- the lwq_node embedded in the first item to be added
+ * @q	- the lwq to append to.
+ *
+ * No locking is needed to append to the queue so this can
+ * be called from any context.
+ * Return %true is the list may have previously been empty.
+ */
+static inline bool lwq_enqueue_batch(struct llist_node *n, struct lwq *q)
+{
+	struct llist_node *e = n;
+
+	/* acquire enqures ordering wrt lwq_dequeue */
+	return llist_add_batch(llist_reverse_order(n), e, &q->new) &&
+		smp_load_acquire(&q->ready) == NULL;
+}
+#endif /* LWQ_H */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 730003c4f4af..c11c4db34639 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -150,7 +150,7 @@ enum nfs_opnum4 {
 	OP_WRITE_SAME = 70,
 	OP_CLONE = 71,
 
-	/* xattr support (RFC8726) */
+	/* xattr support (RFC8276) */
 	OP_GETXATTR                = 72,
 	OP_SETXATTR                = 73,
 	OP_LISTXATTRS              = 74,
@@ -389,79 +389,203 @@ enum lock_type4 {
 	NFS4_WRITEW_LT = 4
 };
 
+/*
+ * Symbol names and values are from RFC 7531 Section 2.
+ * "XDR Description of NFSv4.0"
+ */
+enum {
+	FATTR4_SUPPORTED_ATTRS		= 0,
+	FATTR4_TYPE			= 1,
+	FATTR4_FH_EXPIRE_TYPE		= 2,
+	FATTR4_CHANGE			= 3,
+	FATTR4_SIZE			= 4,
+	FATTR4_LINK_SUPPORT		= 5,
+	FATTR4_SYMLINK_SUPPORT		= 6,
+	FATTR4_NAMED_ATTR		= 7,
+	FATTR4_FSID			= 8,
+	FATTR4_UNIQUE_HANDLES		= 9,
+	FATTR4_LEASE_TIME		= 10,
+	FATTR4_RDATTR_ERROR		= 11,
+	FATTR4_ACL			= 12,
+	FATTR4_ACLSUPPORT		= 13,
+	FATTR4_ARCHIVE			= 14,
+	FATTR4_CANSETTIME		= 15,
+	FATTR4_CASE_INSENSITIVE		= 16,
+	FATTR4_CASE_PRESERVING		= 17,
+	FATTR4_CHOWN_RESTRICTED		= 18,
+	FATTR4_FILEHANDLE		= 19,
+	FATTR4_FILEID			= 20,
+	FATTR4_FILES_AVAIL		= 21,
+	FATTR4_FILES_FREE		= 22,
+	FATTR4_FILES_TOTAL		= 23,
+	FATTR4_FS_LOCATIONS		= 24,
+	FATTR4_HIDDEN			= 25,
+	FATTR4_HOMOGENEOUS		= 26,
+	FATTR4_MAXFILESIZE		= 27,
+	FATTR4_MAXLINK			= 28,
+	FATTR4_MAXNAME			= 29,
+	FATTR4_MAXREAD			= 30,
+	FATTR4_MAXWRITE			= 31,
+	FATTR4_MIMETYPE			= 32,
+	FATTR4_MODE			= 33,
+	FATTR4_NO_TRUNC			= 34,
+	FATTR4_NUMLINKS			= 35,
+	FATTR4_OWNER			= 36,
+	FATTR4_OWNER_GROUP		= 37,
+	FATTR4_QUOTA_AVAIL_HARD		= 38,
+	FATTR4_QUOTA_AVAIL_SOFT		= 39,
+	FATTR4_QUOTA_USED		= 40,
+	FATTR4_RAWDEV			= 41,
+	FATTR4_SPACE_AVAIL		= 42,
+	FATTR4_SPACE_FREE		= 43,
+	FATTR4_SPACE_TOTAL		= 44,
+	FATTR4_SPACE_USED		= 45,
+	FATTR4_SYSTEM			= 46,
+	FATTR4_TIME_ACCESS		= 47,
+	FATTR4_TIME_ACCESS_SET		= 48,
+	FATTR4_TIME_BACKUP		= 49,
+	FATTR4_TIME_CREATE		= 50,
+	FATTR4_TIME_DELTA		= 51,
+	FATTR4_TIME_METADATA		= 52,
+	FATTR4_TIME_MODIFY		= 53,
+	FATTR4_TIME_MODIFY_SET		= 54,
+	FATTR4_MOUNTED_ON_FILEID	= 55,
+};
+
+/*
+ * Symbol names and values are from RFC 5662 Section 2.
+ * "XDR Description of NFSv4.1"
+ */
+enum {
+	FATTR4_DIR_NOTIF_DELAY		= 56,
+	FATTR4_DIRENT_NOTIF_DELAY	= 57,
+	FATTR4_DACL			= 58,
+	FATTR4_SACL			= 59,
+	FATTR4_CHANGE_POLICY		= 60,
+	FATTR4_FS_STATUS		= 61,
+	FATTR4_FS_LAYOUT_TYPES		= 62,
+	FATTR4_LAYOUT_HINT		= 63,
+	FATTR4_LAYOUT_TYPES		= 64,
+	FATTR4_LAYOUT_BLKSIZE		= 65,
+	FATTR4_LAYOUT_ALIGNMENT		= 66,
+	FATTR4_FS_LOCATIONS_INFO	= 67,
+	FATTR4_MDSTHRESHOLD		= 68,
+	FATTR4_RETENTION_GET		= 69,
+	FATTR4_RETENTION_SET		= 70,
+	FATTR4_RETENTEVT_GET		= 71,
+	FATTR4_RETENTEVT_SET		= 72,
+	FATTR4_RETENTION_HOLD		= 73,
+	FATTR4_MODE_SET_MASKED		= 74,
+	FATTR4_SUPPATTR_EXCLCREAT	= 75,
+	FATTR4_FS_CHARSET_CAP		= 76,
+};
+
+/*
+ * Symbol names and values are from RFC 7863 Section 2.
+ * "XDR Description of NFSv4.2"
+ */
+enum {
+	FATTR4_CLONE_BLKSIZE		= 77,
+	FATTR4_SPACE_FREED		= 78,
+	FATTR4_CHANGE_ATTR_TYPE		= 79,
+	FATTR4_SEC_LABEL		= 80,
+};
+
+/*
+ * Symbol names and values are from RFC 8275 Section 5.
+ * "The mode_umask Attribute"
+ */
+enum {
+	FATTR4_MODE_UMASK		= 81,
+};
+
+/*
+ * Symbol names and values are from RFC 8276 Section 8.6.
+ * "Numeric Values Assigned to Protocol Extensions"
+ */
+enum {
+	FATTR4_XATTR_SUPPORT		= 82,
+};
+
+/*
+ * The following internal definitions enable processing the above
+ * attribute bits within 32-bit word boundaries.
+ */
 
 /* Mandatory Attributes */
-#define FATTR4_WORD0_SUPPORTED_ATTRS    (1UL << 0)
-#define FATTR4_WORD0_TYPE               (1UL << 1)
-#define FATTR4_WORD0_FH_EXPIRE_TYPE     (1UL << 2)
-#define FATTR4_WORD0_CHANGE             (1UL << 3)
-#define FATTR4_WORD0_SIZE               (1UL << 4)
-#define FATTR4_WORD0_LINK_SUPPORT       (1UL << 5)
-#define FATTR4_WORD0_SYMLINK_SUPPORT    (1UL << 6)
-#define FATTR4_WORD0_NAMED_ATTR         (1UL << 7)
-#define FATTR4_WORD0_FSID               (1UL << 8)
-#define FATTR4_WORD0_UNIQUE_HANDLES     (1UL << 9)
-#define FATTR4_WORD0_LEASE_TIME         (1UL << 10)
-#define FATTR4_WORD0_RDATTR_ERROR       (1UL << 11)
+#define FATTR4_WORD0_SUPPORTED_ATTRS    BIT(FATTR4_SUPPORTED_ATTRS)
+#define FATTR4_WORD0_TYPE               BIT(FATTR4_TYPE)
+#define FATTR4_WORD0_FH_EXPIRE_TYPE     BIT(FATTR4_FH_EXPIRE_TYPE)
+#define FATTR4_WORD0_CHANGE             BIT(FATTR4_CHANGE)
+#define FATTR4_WORD0_SIZE               BIT(FATTR4_SIZE)
+#define FATTR4_WORD0_LINK_SUPPORT       BIT(FATTR4_LINK_SUPPORT)
+#define FATTR4_WORD0_SYMLINK_SUPPORT    BIT(FATTR4_SYMLINK_SUPPORT)
+#define FATTR4_WORD0_NAMED_ATTR         BIT(FATTR4_NAMED_ATTR)
+#define FATTR4_WORD0_FSID               BIT(FATTR4_FSID)
+#define FATTR4_WORD0_UNIQUE_HANDLES     BIT(FATTR4_UNIQUE_HANDLES)
+#define FATTR4_WORD0_LEASE_TIME         BIT(FATTR4_LEASE_TIME)
+#define FATTR4_WORD0_RDATTR_ERROR       BIT(FATTR4_RDATTR_ERROR)
 /* Mandatory in NFSv4.1 */
-#define FATTR4_WORD2_SUPPATTR_EXCLCREAT (1UL << 11)
+#define FATTR4_WORD2_SUPPATTR_EXCLCREAT BIT(FATTR4_SUPPATTR_EXCLCREAT - 64)
 
 /* Recommended Attributes */
-#define FATTR4_WORD0_ACL                (1UL << 12)
-#define FATTR4_WORD0_ACLSUPPORT         (1UL << 13)
-#define FATTR4_WORD0_ARCHIVE            (1UL << 14)
-#define FATTR4_WORD0_CANSETTIME         (1UL << 15)
-#define FATTR4_WORD0_CASE_INSENSITIVE   (1UL << 16)
-#define FATTR4_WORD0_CASE_PRESERVING    (1UL << 17)
-#define FATTR4_WORD0_CHOWN_RESTRICTED   (1UL << 18)
-#define FATTR4_WORD0_FILEHANDLE         (1UL << 19)
-#define FATTR4_WORD0_FILEID             (1UL << 20)
-#define FATTR4_WORD0_FILES_AVAIL        (1UL << 21)
-#define FATTR4_WORD0_FILES_FREE         (1UL << 22)
-#define FATTR4_WORD0_FILES_TOTAL        (1UL << 23)
-#define FATTR4_WORD0_FS_LOCATIONS       (1UL << 24)
-#define FATTR4_WORD0_HIDDEN             (1UL << 25)
-#define FATTR4_WORD0_HOMOGENEOUS        (1UL << 26)
-#define FATTR4_WORD0_MAXFILESIZE        (1UL << 27)
-#define FATTR4_WORD0_MAXLINK            (1UL << 28)
-#define FATTR4_WORD0_MAXNAME            (1UL << 29)
-#define FATTR4_WORD0_MAXREAD            (1UL << 30)
-#define FATTR4_WORD0_MAXWRITE           (1UL << 31)
-#define FATTR4_WORD1_MIMETYPE           (1UL << 0)
-#define FATTR4_WORD1_MODE               (1UL << 1)
-#define FATTR4_WORD1_NO_TRUNC           (1UL << 2)
-#define FATTR4_WORD1_NUMLINKS           (1UL << 3)
-#define FATTR4_WORD1_OWNER              (1UL << 4)
-#define FATTR4_WORD1_OWNER_GROUP        (1UL << 5)
-#define FATTR4_WORD1_QUOTA_HARD         (1UL << 6)
-#define FATTR4_WORD1_QUOTA_SOFT         (1UL << 7)
-#define FATTR4_WORD1_QUOTA_USED         (1UL << 8)
-#define FATTR4_WORD1_RAWDEV             (1UL << 9)
-#define FATTR4_WORD1_SPACE_AVAIL        (1UL << 10)
-#define FATTR4_WORD1_SPACE_FREE         (1UL << 11)
-#define FATTR4_WORD1_SPACE_TOTAL        (1UL << 12)
-#define FATTR4_WORD1_SPACE_USED         (1UL << 13)
-#define FATTR4_WORD1_SYSTEM             (1UL << 14)
-#define FATTR4_WORD1_TIME_ACCESS        (1UL << 15)
-#define FATTR4_WORD1_TIME_ACCESS_SET    (1UL << 16)
-#define FATTR4_WORD1_TIME_BACKUP        (1UL << 17)
-#define FATTR4_WORD1_TIME_CREATE        (1UL << 18)
-#define FATTR4_WORD1_TIME_DELTA         (1UL << 19)
-#define FATTR4_WORD1_TIME_METADATA      (1UL << 20)
-#define FATTR4_WORD1_TIME_MODIFY        (1UL << 21)
-#define FATTR4_WORD1_TIME_MODIFY_SET    (1UL << 22)
-#define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
-#define FATTR4_WORD1_DACL               (1UL << 26)
-#define FATTR4_WORD1_SACL               (1UL << 27)
-#define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
-#define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
-#define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
-#define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
-#define FATTR4_WORD2_CLONE_BLKSIZE	(1UL << 13)
-#define FATTR4_WORD2_CHANGE_ATTR_TYPE	(1UL << 15)
-#define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
-#define FATTR4_WORD2_MODE_UMASK		(1UL << 17)
-#define FATTR4_WORD2_XATTR_SUPPORT	(1UL << 18)
+#define FATTR4_WORD0_ACL                BIT(FATTR4_ACL)
+#define FATTR4_WORD0_ACLSUPPORT         BIT(FATTR4_ACLSUPPORT)
+#define FATTR4_WORD0_ARCHIVE            BIT(FATTR4_ARCHIVE)
+#define FATTR4_WORD0_CANSETTIME         BIT(FATTR4_CANSETTIME)
+#define FATTR4_WORD0_CASE_INSENSITIVE   BIT(FATTR4_CASE_INSENSITIVE)
+#define FATTR4_WORD0_CASE_PRESERVING    BIT(FATTR4_CASE_PRESERVING)
+#define FATTR4_WORD0_CHOWN_RESTRICTED   BIT(FATTR4_CHOWN_RESTRICTED)
+#define FATTR4_WORD0_FILEHANDLE         BIT(FATTR4_FILEHANDLE)
+#define FATTR4_WORD0_FILEID             BIT(FATTR4_FILEID)
+#define FATTR4_WORD0_FILES_AVAIL        BIT(FATTR4_FILES_AVAIL)
+#define FATTR4_WORD0_FILES_FREE         BIT(FATTR4_FILES_FREE)
+#define FATTR4_WORD0_FILES_TOTAL        BIT(FATTR4_FILES_TOTAL)
+#define FATTR4_WORD0_FS_LOCATIONS       BIT(FATTR4_FS_LOCATIONS)
+#define FATTR4_WORD0_HIDDEN             BIT(FATTR4_HIDDEN)
+#define FATTR4_WORD0_HOMOGENEOUS        BIT(FATTR4_HOMOGENEOUS)
+#define FATTR4_WORD0_MAXFILESIZE        BIT(FATTR4_MAXFILESIZE)
+#define FATTR4_WORD0_MAXLINK            BIT(FATTR4_MAXLINK)
+#define FATTR4_WORD0_MAXNAME            BIT(FATTR4_MAXNAME)
+#define FATTR4_WORD0_MAXREAD            BIT(FATTR4_MAXREAD)
+#define FATTR4_WORD0_MAXWRITE           BIT(FATTR4_MAXWRITE)
+
+#define FATTR4_WORD1_MIMETYPE           BIT(FATTR4_MIMETYPE - 32)
+#define FATTR4_WORD1_MODE               BIT(FATTR4_MODE	- 32)
+#define FATTR4_WORD1_NO_TRUNC           BIT(FATTR4_NO_TRUNC - 32)
+#define FATTR4_WORD1_NUMLINKS           BIT(FATTR4_NUMLINKS - 32)
+#define FATTR4_WORD1_OWNER              BIT(FATTR4_OWNER - 32)
+#define FATTR4_WORD1_OWNER_GROUP        BIT(FATTR4_OWNER_GROUP - 32)
+#define FATTR4_WORD1_QUOTA_HARD         BIT(FATTR4_QUOTA_AVAIL_HARD - 32)
+#define FATTR4_WORD1_QUOTA_SOFT         BIT(FATTR4_QUOTA_AVAIL_SOFT - 32)
+#define FATTR4_WORD1_QUOTA_USED         BIT(FATTR4_QUOTA_USED - 32)
+#define FATTR4_WORD1_RAWDEV             BIT(FATTR4_RAWDEV - 32)
+#define FATTR4_WORD1_SPACE_AVAIL        BIT(FATTR4_SPACE_AVAIL - 32)
+#define FATTR4_WORD1_SPACE_FREE         BIT(FATTR4_SPACE_FREE - 32)
+#define FATTR4_WORD1_SPACE_TOTAL        BIT(FATTR4_SPACE_TOTAL - 32)
+#define FATTR4_WORD1_SPACE_USED         BIT(FATTR4_SPACE_USED - 32)
+#define FATTR4_WORD1_SYSTEM             BIT(FATTR4_SYSTEM - 32)
+#define FATTR4_WORD1_TIME_ACCESS        BIT(FATTR4_TIME_ACCESS - 32)
+#define FATTR4_WORD1_TIME_ACCESS_SET    BIT(FATTR4_TIME_ACCESS_SET - 32)
+#define FATTR4_WORD1_TIME_BACKUP        BIT(FATTR4_TIME_BACKUP - 32)
+#define FATTR4_WORD1_TIME_CREATE        BIT(FATTR4_TIME_CREATE - 32)
+#define FATTR4_WORD1_TIME_DELTA         BIT(FATTR4_TIME_DELTA - 32)
+#define FATTR4_WORD1_TIME_METADATA      BIT(FATTR4_TIME_METADATA - 32)
+#define FATTR4_WORD1_TIME_MODIFY        BIT(FATTR4_TIME_MODIFY - 32)
+#define FATTR4_WORD1_TIME_MODIFY_SET    BIT(FATTR4_TIME_MODIFY_SET - 32)
+#define FATTR4_WORD1_MOUNTED_ON_FILEID  BIT(FATTR4_MOUNTED_ON_FILEID - 32)
+#define FATTR4_WORD1_DACL               BIT(FATTR4_DACL	- 32)
+#define FATTR4_WORD1_SACL               BIT(FATTR4_SACL	- 32)
+#define FATTR4_WORD1_FS_LAYOUT_TYPES    BIT(FATTR4_FS_LAYOUT_TYPES - 32)
+
+#define FATTR4_WORD2_LAYOUT_TYPES       BIT(FATTR4_LAYOUT_TYPES - 64)
+#define FATTR4_WORD2_LAYOUT_BLKSIZE     BIT(FATTR4_LAYOUT_BLKSIZE - 64)
+#define FATTR4_WORD2_MDSTHRESHOLD       BIT(FATTR4_MDSTHRESHOLD	- 64)
+#define FATTR4_WORD2_CLONE_BLKSIZE	BIT(FATTR4_CLONE_BLKSIZE - 64)
+#define FATTR4_WORD2_CHANGE_ATTR_TYPE	BIT(FATTR4_CHANGE_ATTR_TYPE - 64)
+#define FATTR4_WORD2_SECURITY_LABEL     BIT(FATTR4_SEC_LABEL - 64)
+#define FATTR4_WORD2_MODE_UMASK		BIT(FATTR4_MODE_UMASK - 64)
+#define FATTR4_WORD2_XATTR_SUPPORT	BIT(FATTR4_XATTR_SUPPORT - 64)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index dbf5b21feafe..b10f987509cc 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -17,6 +17,7 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/auth.h>
 #include <linux/sunrpc/svcauth.h>
+#include <linux/lwq.h>
 #include <linux/wait.h>
 #include <linux/mm.h>
 #include <linux/pagevec.h>
@@ -33,10 +34,10 @@
  */
 struct svc_pool {
 	unsigned int		sp_id;	    	/* pool id; also node id on NUMA */
-	spinlock_t		sp_lock;	/* protects all fields */
-	struct list_head	sp_sockets;	/* pending sockets */
-	unsigned int		sp_nrthreads;	/* # of threads in pool */
+	struct lwq		sp_xprts;	/* pending transports */
+	atomic_t		sp_nrthreads;	/* # of threads in pool */
 	struct list_head	sp_all_threads;	/* all server threads */
+	struct llist_head	sp_idle_threads; /* idle server threads */
 
 	/* statistics on pool operation */
 	struct percpu_counter	sp_messages_arrived;
@@ -49,7 +50,8 @@ struct svc_pool {
 /* bits for sp_flags */
 enum {
 	SP_TASK_PENDING,	/* still work to do even if no xprt is queued */
-	SP_CONGESTED,		/* all threads are busy, none idle */
+	SP_NEED_VICTIM,		/* One thread needs to agree to exit */
+	SP_VICTIM_REMAINS,	/* One thread needs to actually exit */
 };
 
 
@@ -88,12 +90,9 @@ struct svc_serv {
 	int			(*sv_threadfn)(void *data);
 
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
-	struct list_head	sv_cb_list;	/* queue for callback requests
+	struct lwq		sv_cb_list;	/* queue for callback requests
 						 * that arrive over the same
 						 * connection */
-	spinlock_t		sv_cb_lock;	/* protects the svc_cb_list */
-	wait_queue_head_t	sv_cb_waitq;	/* sleep here if there are no
-						 * entries in the svc_cb_list */
 	bool			sv_bc_enabled;	/* service uses backchannel */
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };
@@ -186,6 +185,7 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp);
  */
 struct svc_rqst {
 	struct list_head	rq_all;		/* all threads list */
+	struct llist_node	rq_idle;	/* On the idle list */
 	struct rcu_head		rq_rcu_head;	/* for RCU deferred kfree */
 	struct svc_xprt *	rq_xprt;	/* transport ptr */
 
@@ -251,6 +251,7 @@ struct svc_rqst {
 						 * net namespace
 						 */
 	void **			rq_lease_breaker; /* The v4 client breaking a lease */
+	unsigned int		rq_status_counter; /* RPC processing counter */
 };
 
 /* bits for rq_flags */
@@ -261,8 +262,7 @@ enum {
 	RQ_DROPME,		/* drop current reply */
 	RQ_SPLICE_OK,		/* turned off in gss privacy to prevent
 				 * encrypting page cache pages */
-	RQ_VICTIM,		/* about to be shut down */
-	RQ_BUSY,		/* request is busy */
+	RQ_VICTIM,		/* Have agreed to shut down */
 	RQ_DATA,		/* request has data */
 };
 
@@ -301,6 +301,28 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst)
 	return (struct sockaddr *) &rqst->rq_daddr;
 }
 
+/**
+ * svc_thread_should_stop - check if this thread should stop
+ * @rqstp: the thread that might need to stop
+ *
+ * To stop an svc thread, the pool flags SP_NEED_VICTIM and SP_VICTIM_REMAINS
+ * are set.  The first thread which sees SP_NEED_VICTIM clears it, becoming
+ * the victim using this function.  It should then promptly call
+ * svc_exit_thread() to complete the process, clearing SP_VICTIM_REMAINS
+ * so the task waiting for a thread to exit can wake and continue.
+ *
+ * Return values:
+ *   %true: caller should invoke svc_exit_thread()
+ *   %false: caller should do nothing
+ */
+static inline bool svc_thread_should_stop(struct svc_rqst *rqstp)
+{
+	if (test_and_clear_bit(SP_NEED_VICTIM, &rqstp->rq_pool->sp_flags))
+		set_bit(RQ_VICTIM, &rqstp->rq_flags);
+
+	return test_bit(RQ_VICTIM, &rqstp->rq_flags);
+}
+
 struct svc_deferred_req {
 	u32			prot;	/* protocol (UDP or TCP) */
 	struct svc_xprt		*xprt;
@@ -413,8 +435,7 @@ struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
 void		   svc_process(struct svc_rqst *rqstp);
-int		   bc_svc_process(struct svc_serv *, struct rpc_rqst *,
-			struct svc_rqst *);
+void		   svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp);
 int		   svc_register(const struct svc_serv *, struct net *, const int,
 				const unsigned short, const unsigned short);
 
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index fa55d12dc765..8e20cd60e2e7 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -54,7 +54,7 @@ struct svc_xprt {
 	const struct svc_xprt_ops *xpt_ops;
 	struct kref		xpt_ref;
 	struct list_head	xpt_list;
-	struct list_head	xpt_ready;
+	struct lwq_node		xpt_ready;
 	unsigned long		xpt_flags;
 
 	struct svc_serv		*xpt_server;	/* service for transport */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 4ecc89301eb7..f85d3a0daca2 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -57,6 +57,7 @@ struct xprt_class;
 struct seq_file;
 struct svc_serv;
 struct net;
+#include <linux/lwq.h>
 
 /*
  * This describes a complete RPC request
@@ -121,7 +122,7 @@ struct rpc_rqst {
 	int			rq_ntrans;
 
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
-	struct list_head	rq_bc_list;	/* Callback service list */
+	struct lwq_node		rq_bc_list;	/* Callback service list */
 	unsigned long		rq_bc_pa_state;	/* Backchannel prealloc state */
 	struct list_head	rq_bc_pa_list;	/* Backchannel prealloc list */
 #endif /* CONFIG_SUNRPC_BACKCHANEL */
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index f8069ef2ee0f..718df1d9b834 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1667,7 +1667,7 @@ TRACE_EVENT(svcrdma_encode_wseg,
 		__entry->offset = offset;
 	),
 
-	TP_printk("cq_id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
+	TP_printk("cq.id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
 		__entry->cq_id, __entry->completion_id,
 		__entry->segno, __entry->length,
 		(unsigned long long)__entry->offset, __entry->handle
@@ -1703,7 +1703,7 @@ TRACE_EVENT(svcrdma_decode_rseg,
 		__entry->offset = segment->rs_offset;
 	),
 
-	TP_printk("cq_id=%u cid=%d segno=%u position=%u %u@0x%016llx:0x%08x",
+	TP_printk("cq.id=%u cid=%d segno=%u position=%u %u@0x%016llx:0x%08x",
 		__entry->cq_id, __entry->completion_id,
 		__entry->segno, __entry->position, __entry->length,
 		(unsigned long long)__entry->offset, __entry->handle
@@ -1740,7 +1740,7 @@ TRACE_EVENT(svcrdma_decode_wseg,
 		__entry->offset = segment->rs_offset;
 	),
 
-	TP_printk("cq_id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
+	TP_printk("cq.id=%u cid=%d segno=%u %u@0x%016llx:0x%08x",
 		__entry->cq_id, __entry->completion_id,
 		__entry->segno, __entry->length,
 		(unsigned long long)__entry->offset, __entry->handle
@@ -1959,7 +1959,7 @@ TRACE_EVENT(svcrdma_send_pullup,
 		__entry->msglen = msglen;
 	),
 
-	TP_printk("cq_id=%u cid=%d hdr=%u msg=%u (total %u)",
+	TP_printk("cq.id=%u cid=%d hdr=%u msg=%u (total %u)",
 		__entry->cq_id, __entry->completion_id,
 		__entry->hdrlen, __entry->msglen,
 		__entry->hdrlen + __entry->msglen)
@@ -2014,7 +2014,7 @@ TRACE_EVENT(svcrdma_post_send,
 					wr->ex.invalidate_rkey : 0;
 	),
 
-	TP_printk("cq_id=%u cid=%d num_sge=%u inv_rkey=0x%08x",
+	TP_printk("cq.id=%u cid=%d num_sge=%u inv_rkey=0x%08x",
 		__entry->cq_id, __entry->completion_id,
 		__entry->num_sge, __entry->inv_rkey
 	)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 6beb38c1dcb5..337c90787fb1 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1677,7 +1677,6 @@ DEFINE_SVCXDRBUF_EVENT(sendto);
 	svc_rqst_flag(DROPME)						\
 	svc_rqst_flag(SPLICE_OK)					\
 	svc_rqst_flag(VICTIM)						\
-	svc_rqst_flag(BUSY)						\
 	svc_rqst_flag_end(DATA)
 
 #undef svc_rqst_flag
diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h
new file mode 100644
index 000000000000..c8ae72466ee6
--- /dev/null
+++ b/include/uapi/linux/nfsd_netlink.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/nfsd.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NFSD_H
+#define _UAPI_LINUX_NFSD_H
+
+#define NFSD_FAMILY_NAME	"nfsd"
+#define NFSD_FAMILY_VERSION	1
+
+enum {
+	NFSD_A_RPC_STATUS_XID = 1,
+	NFSD_A_RPC_STATUS_FLAGS,
+	NFSD_A_RPC_STATUS_PROG,
+	NFSD_A_RPC_STATUS_VERSION,
+	NFSD_A_RPC_STATUS_PROC,
+	NFSD_A_RPC_STATUS_SERVICE_TIME,
+	NFSD_A_RPC_STATUS_PAD,
+	NFSD_A_RPC_STATUS_SADDR4,
+	NFSD_A_RPC_STATUS_DADDR4,
+	NFSD_A_RPC_STATUS_SADDR6,
+	NFSD_A_RPC_STATUS_DADDR6,
+	NFSD_A_RPC_STATUS_SPORT,
+	NFSD_A_RPC_STATUS_DPORT,
+	NFSD_A_RPC_STATUS_COMPOUND_OPS,
+
+	__NFSD_A_RPC_STATUS_MAX,
+	NFSD_A_RPC_STATUS_MAX = (__NFSD_A_RPC_STATUS_MAX - 1)
+};
+
+enum {
+	NFSD_CMD_RPC_STATUS_GET = 1,
+
+	__NFSD_CMD_MAX,
+	NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1)
+};
+
+#endif /* _UAPI_LINUX_NFSD_H */