Merge tag 'nfsd-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux

Pull nfsd updates from Chuck Lever:
 "This release introduces support for the CB_RECALL_ANY operation. NFSD
  can send this operation to request that clients return any delegations
  they choose. The server uses this operation to handle low memory
  scenarios or indicate to a client when that client has reached the
  maximum number of delegations the server supports.

  The NFSv4.2 READ_PLUS operation has been simplified temporarily whilst
  support for sparse files in local filesystems and the VFS is improved.

  Two major data structure fixes appear in this release:

   - The nfs4_file hash table is replaced with a resizable hash table to
     reduce the latency of NFSv4 OPEN operations.

   - Reference counting in the NFSD filecache has been hardened against
     races.

  In furtherance of removing support for NFSv2 in a subsequent kernel
  release, a new Kconfig option enables server-side support for NFSv2 to
  be left out of a kernel build.

  MAINTAINERS has been updated to indicate that changes to fs/exportfs
  should go through the NFSD tree"

* tag 'nfsd-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (49 commits)
  NFSD: Avoid clashing function prototypes
  SUNRPC: Fix crasher in unwrap_integ_data()
  SUNRPC: Make the svc_authenticate tracepoint conditional
  NFSD: Use only RQ_DROPME to signal the need to drop a reply
  SUNRPC: Clean up xdr_write_pages()
  SUNRPC: Don't leak netobj memory when gss_read_proxy_verf() fails
  NFSD: add CB_RECALL_ANY tracepoints
  NFSD: add delegation reaper to react to low memory condition
  NFSD: add support for sending CB_RECALL_ANY
  NFSD: refactoring courtesy_client_reaper to a generic low memory shrinker
  trace: Relocate event helper files
  NFSD: pass range end to vfs_fsync_range() instead of count
  lockd: fix file selection in nlmsvc_cancel_blocked
  lockd: ensure we use the correct file descriptor when unlocking
  lockd: set missing fl_flags field when retrieving args
  NFSD: Use struct_size() helper in alloc_session()
  nfsd: return error if nfs4_setacl fails
  lockd: set other missing fields when unlocking files
  NFSD: Add an nfsd_file_fsync tracepoint
  sunrpc: svc: Remove an unused static function svc_ungetu32()
  ...

MAINTAINERS

@@ -10082,6 +10082,7 @@ F:	drivers/infiniband/
 F:	include/rdma/
 F:	include/trace/events/ib_mad.h
 F:	include/trace/events/ib_umad.h
+F:	include/trace/misc/rdma.h
 F:	include/uapi/linux/if_infiniband.h
 F:	include/uapi/rdma/
 F:	samples/bpf/ibumad_kern.c
@@ -11168,11 +11169,18 @@ L:	linux-nfs@vger.kernel.org
 S:	Supported
 W:	http://nfs.sourceforge.net/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux.git
+F:	fs/exportfs/
 F:	fs/lockd/
 F:	fs/nfs_common/
 F:	fs/nfsd/
 F:	include/linux/lockd/
 F:	include/linux/sunrpc/
+F:	include/trace/events/rpcgss.h
+F:	include/trace/events/rpcrdma.h
+F:	include/trace/events/sunrpc.h
+F:	include/trace/misc/fs.h
+F:	include/trace/misc/nfs.h
+F:	include/trace/misc/sunrpc.h
 F:	include/uapi/linux/nfsd/
 F:	include/uapi/linux/sunrpc/
 F:	net/sunrpc/

drivers/infiniband/core/cm_trace.h

@@ -16,7 +16,7 @@
 
 #include <linux/tracepoint.h>
 #include <rdma/ib_cm.h>
-#include <trace/events/rdma.h>
+#include <trace/misc/rdma.h>
 
 /*
  * enum ib_cm_state, from include/rdma/ib_cm.h

drivers/infiniband/core/cma_trace.h

@@ -15,7 +15,7 @@
 #define _TRACE_RDMA_CMA_H
 
 #include <linux/tracepoint.h>
-#include <trace/events/rdma.h>
+#include <trace/misc/rdma.h>
 
 
 DECLARE_EVENT_CLASS(cma_fsm_class,

fs/exportfs/expfs.c

@@ -18,7 +18,7 @@
 #include <linux/sched.h>
 #include <linux/cred.h>
 
-#define dprintk(fmt, args...) do{}while(0)
+#define dprintk(fmt, args...) pr_debug(fmt, ##args)
 
 
 static int get_name(const struct path *path, char *name, struct dentry *child);
@@ -132,8 +132,8 @@ static struct dentry *reconnect_one(struct vfsmount *mnt,
 	inode_unlock(dentry->d_inode);
 
 	if (IS_ERR(parent)) {
-		dprintk("%s: get_parent of %ld failed, err %d\n",
+		dprintk("get_parent of %lu failed, err %ld\n",
-			__func__, dentry->d_inode->i_ino, PTR_ERR(parent));
+			dentry->d_inode->i_ino, PTR_ERR(parent));
 		return parent;
 	}
 
@@ -147,7 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt,
 	dprintk("%s: found name: %s\n", __func__, nbuf);
 	tmp = lookup_one_unlocked(mnt_user_ns(mnt), nbuf, parent, strlen(nbuf));
 	if (IS_ERR(tmp)) {
-		dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
+		dprintk("lookup failed: %ld\n", PTR_ERR(tmp));
 		err = PTR_ERR(tmp);
 		goto out_err;
 	}

fs/lockd/svc4proc.c

@@ -52,6 +52,7 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 		*filp = file;
 
 		/* Set up the missing parts of the file_lock structure */
+		lock->fl.fl_flags = FL_POSIX;
 		lock->fl.fl_file  = file->f_file[mode];
 		lock->fl.fl_pid = current->tgid;
 		lock->fl.fl_start = (loff_t)lock->lock_start;

fs/lockd/svclock.c

@@ -659,11 +659,13 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock)
 	nlmsvc_cancel_blocked(net, file, lock);
 
 	lock->fl.fl_type = F_UNLCK;
-	if (file->f_file[O_RDONLY])
+	lock->fl.fl_file = file->f_file[O_RDONLY];
-		error = vfs_lock_file(file->f_file[O_RDONLY], F_SETLK,
+	if (lock->fl.fl_file)
+		error = vfs_lock_file(lock->fl.fl_file, F_SETLK,
 					&lock->fl, NULL);
-	if (file->f_file[O_WRONLY])
+	lock->fl.fl_file = file->f_file[O_WRONLY];
-		error = vfs_lock_file(file->f_file[O_WRONLY], F_SETLK,
+	if (lock->fl.fl_file)
+		error |= vfs_lock_file(lock->fl.fl_file, F_SETLK,
 					&lock->fl, NULL);
 
 	return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
@@ -697,9 +699,10 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l
 	block = nlmsvc_lookup_block(file, lock);
 	mutex_unlock(&file->f_mutex);
 	if (block != NULL) {
-		mode = lock_to_openmode(&lock->fl);
+		struct file_lock *fl = &block->b_call->a_args.lock.fl;
-		vfs_cancel_lock(block->b_file->f_file[mode],
+
-				&block->b_call->a_args.lock.fl);
+		mode = lock_to_openmode(fl);
+		vfs_cancel_lock(block->b_file->f_file[mode], fl);
 		status = nlmsvc_unlink_block(block);
 		nlmsvc_release_block(block);
 	}

fs/lockd/svcproc.c

@@ -77,6 +77,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 		/* Set up the missing parts of the file_lock structure */
 		mode = lock_to_openmode(&lock->fl);
+		lock->fl.fl_flags = FL_POSIX;
 		lock->fl.fl_file  = file->f_file[mode];
 		lock->fl.fl_pid = current->tgid;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;

fs/lockd/svcsubs.c

@@ -176,7 +176,7 @@ nlm_delete_file(struct nlm_file *file)
 	}
 }
 
-static int nlm_unlock_files(struct nlm_file *file, fl_owner_t owner)
+static int nlm_unlock_files(struct nlm_file *file, const struct file_lock *fl)
 {
 	struct file_lock lock;
 
@@ -184,12 +184,15 @@ static int nlm_unlock_files(struct nlm_file *file, fl_owner_t owner)
 	lock.fl_type  = F_UNLCK;
 	lock.fl_start = 0;
 	lock.fl_end   = OFFSET_MAX;
-	lock.fl_owner = owner;
+	lock.fl_owner = fl->fl_owner;
-	if (file->f_file[O_RDONLY] &&
+	lock.fl_pid   = fl->fl_pid;
-	    vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, &lock, NULL))
+	lock.fl_flags = FL_POSIX;
+
+	lock.fl_file = file->f_file[O_RDONLY];
+	if (lock.fl_file && vfs_lock_file(lock.fl_file, F_SETLK, &lock, NULL))
 		goto out_err;
-	if (file->f_file[O_WRONLY] &&
+	lock.fl_file = file->f_file[O_WRONLY];
-	    vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, &lock, NULL))
+	if (lock.fl_file && vfs_lock_file(lock.fl_file, F_SETLK, &lock, NULL))
 		goto out_err;
 	return 0;
 out_err:
@@ -226,7 +229,7 @@ again:
 		if (match(lockhost, host)) {
 
 			spin_unlock(&flctx->flc_lock);
-			if (nlm_unlock_files(file, fl->fl_owner))
+			if (nlm_unlock_files(file, fl))
 				return 1;
 			goto again;
 		}

fs/nfs/nfs4trace.h

@@ -9,10 +9,10 @@
 #define _TRACE_NFS4_H
 
 #include <linux/tracepoint.h>
-#include <trace/events/sunrpc_base.h>
+#include <trace/misc/sunrpc.h>
 
-#include <trace/events/fs.h>
+#include <trace/misc/fs.h>
-#include <trace/events/nfs.h>
+#include <trace/misc/nfs.h>
 
 #define show_nfs_fattr_flags(valid) \
 	__print_flags((unsigned long)valid, "|", \

fs/nfs/nfstrace.h

@@ -11,9 +11,9 @@
 #include <linux/tracepoint.h>
 #include <linux/iversion.h>
 
-#include <trace/events/fs.h>
+#include <trace/misc/fs.h>
-#include <trace/events/nfs.h>
+#include <trace/misc/nfs.h>
-#include <trace/events/sunrpc_base.h>
+#include <trace/misc/sunrpc.h>
 
 #define nfs_show_cache_validity(v) \
 	__print_flags(v, "|", \

fs/nfsd/Kconfig

@@ -8,6 +8,7 @@ config NFSD
 	select SUNRPC
 	select EXPORTFS
 	select NFS_ACL_SUPPORT if NFSD_V2_ACL
+	select NFS_ACL_SUPPORT if NFSD_V3_ACL
 	depends on MULTIUSER
 	help
 	  Choose Y here if you want to allow other computers to access
@@ -26,19 +27,29 @@ config NFSD
 
 	  Below you can choose which versions of the NFS protocol are
 	  available to clients mounting the NFS server on this system.
-	  Support for NFS version 2 (RFC 1094) is always available when
+	  Support for NFS version 3 (RFC 1813) is always available when
 	  CONFIG_NFSD is selected.
 
 	  If unsure, say N.
 
-config NFSD_V2_ACL
+config NFSD_V2
-	bool
+	bool "NFS server support for NFS version 2 (DEPRECATED)"
 	depends on NFSD
+	default n
+	help
+	  NFSv2 (RFC 1094) was the first publicly-released version of NFS.
+	  Unless you are hosting ancient (1990's era) NFS clients, you don't
+	  need this.
+
+	  If unsure, say N.
+
+config NFSD_V2_ACL
+	bool "NFS server support for the NFSv2 ACL protocol extension"
+	depends on NFSD_V2
 
 config NFSD_V3_ACL
 	bool "NFS server support for the NFSv3 ACL protocol extension"
 	depends on NFSD
-	select NFSD_V2_ACL
 	help
 	  Solaris NFS servers support an auxiliary NFSv3 ACL protocol that
 	  never became an official part of the NFS version 3 protocol.

fs/nfsd/Makefile

@@ -10,9 +10,10 @@ obj-$(CONFIG_NFSD)	+= nfsd.o
 # this one should be compiled first, as the tracing macros can easily blow up
 nfsd-y			+= trace.o
 
-nfsd-y 			+= nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \
+nfsd-y 			+= nfssvc.o nfsctl.o nfsfh.o vfs.o \
-			   export.o auth.o lockd.o nfscache.o nfsxdr.o \
+			   export.o auth.o lockd.o nfscache.o \
 			   stats.o filecache.o nfs3proc.o nfs3xdr.o
+nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \

fs/nfsd/blocklayout.c

@@ -12,6 +12,7 @@
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
 #include "filecache.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_PNFS
 

fs/nfsd/blocklayoutxdr.c

@@ -9,6 +9,7 @@
 
 #include "nfsd.h"
 #include "blocklayoutxdr.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_PNFS
 

fs/nfsd/export.h

@@ -115,7 +115,6 @@ struct svc_export *	rqst_find_fsidzero_export(struct svc_rqst *);
 int			exp_rootfh(struct net *, struct auth_domain *,
 					char *path, struct knfsd_fh *, int maxsize);
 __be32			exp_pseudoroot(struct svc_rqst *, struct svc_fh *);
-__be32			nfserrno(int errno);
 
 static inline void exp_put(struct svc_export *exp)
 {

fs/nfsd/filecache.c

@@ -1,7 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * Open file cache.
+ * The NFSD open file cache.
  *
  * (c) 2015 - Jeff Layton <jeff.layton@primarydata.com>
+ *
+ * An nfsd_file object is a per-file collection of open state that binds
+ * together:
+ *   - a struct file *
+ *   - a user credential
+ *   - a network namespace
+ *   - a read-ahead context
+ *   - monitoring for writeback errors
+ *
+ * nfsd_file objects are reference-counted. Consumers acquire a new
+ * object via the nfsd_file_acquire API. They manage their interest in
+ * the acquired object, and hence the object's reference count, via
+ * nfsd_file_get and nfsd_file_put. There are two varieties of nfsd_file
+ * object:
+ *
+ *  * non-garbage-collected: When a consumer wants to precisely control
+ *    the lifetime of a file's open state, it acquires a non-garbage-
+ *    collected nfsd_file. The final nfsd_file_put releases the open
+ *    state immediately.
+ *
+ *  * garbage-collected: When a consumer does not control the lifetime
+ *    of open state, it acquires a garbage-collected nfsd_file. The
+ *    final nfsd_file_put allows the open state to linger for a period
+ *    during which it may be re-used.
  */
 
 #include <linux/hash.h>
@@ -33,7 +58,6 @@ static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_releases);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age);
-static DEFINE_PER_CPU(unsigned long, nfsd_file_pages_flushed);
 static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions);
 
 struct nfsd_fcache_disposal {
@@ -63,6 +87,7 @@ struct nfsd_file_lookup_key {
 	struct net			*net;
 	const struct cred		*cred;
 	unsigned char			need;
+	bool				gc;
 	enum nfsd_file_lookup_type	type;
 };
 
@@ -162,6 +187,8 @@ static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg,
 			return 1;
 		if (!nfsd_match_cred(nf->nf_cred, key->cred))
 			return 1;
+		if (!!test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc)
+			return 1;
 		if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0)
 			return 1;
 		break;
@@ -184,12 +211,9 @@ static const struct rhashtable_params nfsd_file_rhash_params = {
 static void
 nfsd_file_schedule_laundrette(void)
 {
-	if ((atomic_read(&nfsd_file_rhash_tbl.nelems) == 0) ||
+	if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags))
-	    test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0)
+		queue_delayed_work(system_wq, &nfsd_filecache_laundrette,
-		return;
+				   NFSD_LAUNDRETTE_DELAY);
-
-	queue_delayed_work(system_wq, &nfsd_filecache_laundrette,
-			NFSD_LAUNDRETTE_DELAY);
 }
 
 static void
@@ -297,6 +321,8 @@ nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may)
 		nf->nf_flags = 0;
 		__set_bit(NFSD_FILE_HASHED, &nf->nf_flags);
 		__set_bit(NFSD_FILE_PENDING, &nf->nf_flags);
+		if (key->gc)
+			__set_bit(NFSD_FILE_GC, &nf->nf_flags);
 		nf->nf_inode = key->inode;
 		/* nf_ref is pre-incremented for hash table */
 		refcount_set(&nf->nf_ref, 2);
@@ -306,16 +332,62 @@ nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may)
 	return nf;
 }
 
+static void
+nfsd_file_fsync(struct nfsd_file *nf)
+{
+	struct file *file = nf->nf_file;
+	int ret;
+
+	if (!file || !(file->f_mode & FMODE_WRITE))
+		return;
+	ret = vfs_fsync(file, 1);
+	trace_nfsd_file_fsync(nf, ret);
+	if (ret)
+		nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id));
+}
+
+static int
+nfsd_file_check_write_error(struct nfsd_file *nf)
+{
+	struct file *file = nf->nf_file;
+
+	if (!file || !(file->f_mode & FMODE_WRITE))
+		return 0;
+	return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err));
+}
+
+static void
+nfsd_file_hash_remove(struct nfsd_file *nf)
+{
+	trace_nfsd_file_unhash(nf);
+
+	if (nfsd_file_check_write_error(nf))
+		nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id));
+	rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash,
+			       nfsd_file_rhash_params);
+}
+
+static bool
+nfsd_file_unhash(struct nfsd_file *nf)
+{
+	if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+		nfsd_file_hash_remove(nf);
+		return true;
+	}
+	return false;
+}
+
 static bool
 nfsd_file_free(struct nfsd_file *nf)
 {
 	s64 age = ktime_to_ms(ktime_sub(ktime_get(), nf->nf_birthtime));
 	bool flush = false;
 
+	trace_nfsd_file_free(nf);
+
 	this_cpu_inc(nfsd_file_releases);
 	this_cpu_add(nfsd_file_total_age, age);
 
-	trace_nfsd_file_put_final(nf);
 	if (nf->nf_mark)
 		nfsd_file_mark_put(nf->nf_mark);
 	if (nf->nf_file) {
@@ -349,28 +421,6 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
 		mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
 }
 
-static int
-nfsd_file_check_write_error(struct nfsd_file *nf)
-{
-	struct file *file = nf->nf_file;
-
-	if (!file || !(file->f_mode & FMODE_WRITE))
-		return 0;
-	return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err));
-}
-
-static void
-nfsd_file_flush(struct nfsd_file *nf)
-{
-	struct file *file = nf->nf_file;
-
-	if (!file || !(file->f_mode & FMODE_WRITE))
-		return;
-	this_cpu_add(nfsd_file_pages_flushed, file->f_mapping->nrpages);
-	if (vfs_fsync(file, 1) != 0)
-		nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id));
-}
-
 static void nfsd_file_lru_add(struct nfsd_file *nf)
 {
 	set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
@@ -384,31 +434,18 @@ static void nfsd_file_lru_remove(struct nfsd_file *nf)
 		trace_nfsd_file_lru_del(nf);
 }
 
-static void
+struct nfsd_file *
-nfsd_file_hash_remove(struct nfsd_file *nf)
+nfsd_file_get(struct nfsd_file *nf)
 {
-	trace_nfsd_file_unhash(nf);
+	if (likely(refcount_inc_not_zero(&nf->nf_ref)))
-
+		return nf;
-	if (nfsd_file_check_write_error(nf))
+	return NULL;
-		nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id));
-	rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash,
-			       nfsd_file_rhash_params);
-}
-
-static bool
-nfsd_file_unhash(struct nfsd_file *nf)
-{
-	if (test_and_clear_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
-		nfsd_file_hash_remove(nf);
-		return true;
-	}
-	return false;
 }
 
 static void
-nfsd_file_unhash_and_dispose(struct nfsd_file *nf, struct list_head *dispose)
+nfsd_file_unhash_and_queue(struct nfsd_file *nf, struct list_head *dispose)
 {
-	trace_nfsd_file_unhash_and_dispose(nf);
+	trace_nfsd_file_unhash_and_queue(nf);
 	if (nfsd_file_unhash(nf)) {
 		/* caller must call nfsd_file_dispose_list() later */
 		nfsd_file_lru_remove(nf);
@@ -428,48 +465,33 @@ nfsd_file_put_noref(struct nfsd_file *nf)
 	}
 }
 
+static void
+nfsd_file_unhash_and_put(struct nfsd_file *nf)
+{
+	if (nfsd_file_unhash(nf))
+		nfsd_file_put_noref(nf);
+}
+
 void
 nfsd_file_put(struct nfsd_file *nf)
 {
 	might_sleep();
 
-	nfsd_file_lru_add(nf);
+	if (test_bit(NFSD_FILE_GC, &nf->nf_flags))
-	if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) {
+		nfsd_file_lru_add(nf);
-		nfsd_file_flush(nf);
+	else if (refcount_read(&nf->nf_ref) == 2)
+		nfsd_file_unhash_and_put(nf);
+
+	if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
+		nfsd_file_fsync(nf);
 		nfsd_file_put_noref(nf);
-	} else if (nf->nf_file) {
+	} else if (nf->nf_file && test_bit(NFSD_FILE_GC, &nf->nf_flags)) {
 		nfsd_file_put_noref(nf);
 		nfsd_file_schedule_laundrette();
 	} else
 		nfsd_file_put_noref(nf);
 }
 
-/**
- * nfsd_file_close - Close an nfsd_file
- * @nf: nfsd_file to close
- *
- * If this is the final reference for @nf, free it immediately.
- * This reflects an on-the-wire CLOSE or DELEGRETURN into the
- * VFS and exported filesystem.
- */
-void nfsd_file_close(struct nfsd_file *nf)
-{
-	nfsd_file_put(nf);
-	if (refcount_dec_if_one(&nf->nf_ref)) {
-		nfsd_file_unhash(nf);
-		nfsd_file_lru_remove(nf);
-		nfsd_file_free(nf);
-	}
-}
-
-struct nfsd_file *
-nfsd_file_get(struct nfsd_file *nf)
-{
-	if (likely(refcount_inc_not_zero(&nf->nf_ref)))
-		return nf;
-	return NULL;
-}
-
 static void
 nfsd_file_dispose_list(struct list_head *dispose)
 {
@@ -478,7 +500,7 @@ nfsd_file_dispose_list(struct list_head *dispose)
 	while(!list_empty(dispose)) {
 		nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
 		list_del_init(&nf->nf_lru);
-		nfsd_file_flush(nf);
+		nfsd_file_fsync(nf);
 		nfsd_file_put_noref(nf);
 	}
 }
@@ -492,7 +514,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose)
 	while(!list_empty(dispose)) {
 		nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
 		list_del_init(&nf->nf_lru);
-		nfsd_file_flush(nf);
+		nfsd_file_fsync(nf);
 		if (!refcount_dec_and_test(&nf->nf_ref))
 			continue;
 		if (nfsd_file_free(nf))
@@ -644,7 +666,8 @@ static void
 nfsd_file_gc_worker(struct work_struct *work)
 {
 	nfsd_file_gc();
-	nfsd_file_schedule_laundrette();
+	if (list_lru_count(&nfsd_file_lru))
+		nfsd_file_schedule_laundrette();
 }
 
 static unsigned long
@@ -692,7 +715,7 @@ __nfsd_file_close_inode(struct inode *inode, struct list_head *dispose)
 				       nfsd_file_rhash_params);
 		if (!nf)
 			break;
-		nfsd_file_unhash_and_dispose(nf, dispose);
+		nfsd_file_unhash_and_queue(nf, dispose);
 		count++;
 	} while (1);
 	rcu_read_unlock();
@@ -894,7 +917,7 @@ __nfsd_file_cache_purge(struct net *net)
 		nf = rhashtable_walk_next(&iter);
 		while (!IS_ERR_OR_NULL(nf)) {
 			if (!net || nf->nf_net == net)
-				nfsd_file_unhash_and_dispose(nf, &dispose);
+				nfsd_file_unhash_and_queue(nf, &dispose);
 			nf = rhashtable_walk_next(&iter);
 		}
 
@@ -1000,7 +1023,6 @@ nfsd_file_cache_shutdown(void)
 		per_cpu(nfsd_file_acquisitions, i) = 0;
 		per_cpu(nfsd_file_releases, i) = 0;
 		per_cpu(nfsd_file_total_age, i) = 0;
-		per_cpu(nfsd_file_pages_flushed, i) = 0;
 		per_cpu(nfsd_file_evictions, i) = 0;
 	}
 }
@@ -1034,12 +1056,14 @@ nfsd_file_is_cached(struct inode *inode)
 
 static __be32
 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
-		     unsigned int may_flags, struct nfsd_file **pnf, bool open)
+		     unsigned int may_flags, struct nfsd_file **pnf,
+		     bool open, bool want_gc)
 {
 	struct nfsd_file_lookup_key key = {
 		.type	= NFSD_FILE_KEY_FULL,
 		.need	= may_flags & NFSD_FILE_MAY_MASK,
 		.net	= SVC_NET(rqstp),
+		.gc	= want_gc,
 	};
 	bool open_retry = true;
 	struct nfsd_file *nf;
@@ -1135,14 +1159,35 @@ open_file:
 	 * then unhash.
 	 */
 	if (status != nfs_ok || key.inode->i_nlink == 0)
-		if (nfsd_file_unhash(nf))
+		nfsd_file_unhash_and_put(nf);
-			nfsd_file_put_noref(nf);
 	clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags);
 	smp_mb__after_atomic();
 	wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING);
 	goto out;
 }
 
+/**
+ * nfsd_file_acquire_gc - Get a struct nfsd_file with an open file
+ * @rqstp: the RPC transaction being executed
+ * @fhp: the NFS filehandle of the file to be opened
+ * @may_flags: NFSD_MAY_ settings for the file
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * The nfsd_file object returned by this API is reference-counted
+ * and garbage-collected. The object is retained for a few
+ * seconds after the final nfsd_file_put() in case the caller
+ * wants to re-use it.
+ *
+ * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
+ * network byte order is returned.
+ */
+__be32
+nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		     unsigned int may_flags, struct nfsd_file **pnf)
+{
+	return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true);
+}
+
 /**
  * nfsd_file_acquire - Get a struct nfsd_file with an open file
  * @rqstp: the RPC transaction being executed
@@ -1150,6 +1195,10 @@ open_file:
  * @may_flags: NFSD_MAY_ settings for the file
  * @pnf: OUT: new or found "struct nfsd_file" object
  *
+ * The nfsd_file_object returned by this API is reference-counted
+ * but not garbage-collected. The object is unhashed after the
+ * final nfsd_file_put().
+ *
  * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
  * network byte order is returned.
  */
@@ -1157,7 +1206,7 @@ __be32
 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **pnf)
 {
-	return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true);
+	return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false);
 }
 
 /**
@@ -1167,6 +1216,10 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * @may_flags: NFSD_MAY_ settings for the file
  * @pnf: OUT: new or found "struct nfsd_file" object
  *
+ * The nfsd_file_object returned by this API is reference-counted
+ * but not garbage-collected. The object is released immediately
+ * one RCU grace period after the final nfsd_file_put().
+ *
  * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
  * network byte order is returned.
  */
@@ -1174,7 +1227,7 @@ __be32
 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		 unsigned int may_flags, struct nfsd_file **pnf)
 {
-	return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false);
+	return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false);
 }
 
 /*
@@ -1184,7 +1237,7 @@ nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
  */
 int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 {
-	unsigned long releases = 0, pages_flushed = 0, evictions = 0;
+	unsigned long releases = 0, evictions = 0;
 	unsigned long hits = 0, acquisitions = 0;
 	unsigned int i, count = 0, buckets = 0;
 	unsigned long lru = 0, total_age = 0;
@@ -1212,7 +1265,6 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 		releases += per_cpu(nfsd_file_releases, i);
 		total_age += per_cpu(nfsd_file_total_age, i);
 		evictions += per_cpu(nfsd_file_evictions, i);
-		pages_flushed += per_cpu(nfsd_file_pages_flushed, i);
 	}
 
 	seq_printf(m, "total entries: %u\n", count);
@@ -1226,6 +1278,5 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 		seq_printf(m, "mean age (ms): %ld\n", total_age / releases);
 	else
 		seq_printf(m, "mean age (ms): -\n");
-	seq_printf(m, "pages flushed: %lu\n", pages_flushed);
 	return 0;
 }

fs/nfsd/filecache.h

@@ -38,6 +38,7 @@ struct nfsd_file {
 #define NFSD_FILE_HASHED	(0)
 #define NFSD_FILE_PENDING	(1)
 #define NFSD_FILE_REFERENCED	(2)
+#define NFSD_FILE_GC		(3)
 	unsigned long		nf_flags;
 	struct inode		*nf_inode;	/* don't deref */
 	refcount_t		nf_ref;
@@ -52,10 +53,11 @@ void nfsd_file_cache_shutdown(void);
 int nfsd_file_cache_start_net(struct net *net);
 void nfsd_file_cache_shutdown_net(struct net *net);
 void nfsd_file_put(struct nfsd_file *nf);
-void nfsd_file_close(struct nfsd_file *nf);
 struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
 void nfsd_file_close_inode_sync(struct inode *inode);
 bool nfsd_file_is_cached(struct inode *inode);
+__be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **nfp);
 __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **nfp);
 __be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,

fs/nfsd/flexfilelayout.c

@@ -15,6 +15,7 @@
 
 #include "flexfilelayoutxdr.h"
 #include "pnfs.h"
+#include "vfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_PNFS
 

fs/nfsd/nfs2acl.c

@@ -246,7 +246,6 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 	struct inode *inode;
-	int w;
 
 	if (!svcxdr_encode_stat(xdr, resp->status))
 		return false;
@@ -260,15 +259,6 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 	if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
 		return false;
 
-	rqstp->rq_res.page_len = w = nfsacl_size(
-		(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
-		(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
-	while (w > 0) {
-		if (!*(rqstp->rq_next_page++))
-			return true;
-		w -= PAGE_SIZE;
-	}
-
 	if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access,
 				   resp->mask & NFS_ACL, 0))
 		return false;

fs/nfsd/nfs3acl.c

@@ -171,11 +171,7 @@ nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 {
 	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
-	struct kvec *head = rqstp->rq_res.head;
 	struct inode *inode;
-	unsigned int base;
-	int n;
-	int w;
 
 	if (!svcxdr_encode_nfsstat3(xdr, resp->status))
 		return false;
@@ -187,26 +183,12 @@ nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 		if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
 			return false;
 
-		base = (char *)xdr->p - (char *)head->iov_base;
+		if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access,
-
+					   resp->mask & NFS_ACL, 0))
-		rqstp->rq_res.page_len = w = nfsacl_size(
+			return false;
-			(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
+		if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default,
-			(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
+					   resp->mask & NFS_DFACL,
-		while (w > 0) {
+					   NFS_ACL_DEFAULT))
-			if (!*(rqstp->rq_next_page++))
-				return false;
-			w -= PAGE_SIZE;
-		}
-
-		n = nfsacl_encode(&rqstp->rq_res, base, inode,
-				  resp->acl_access,
-				  resp->mask & NFS_ACL, 0);
-		if (n > 0)
-			n = nfsacl_encode(&rqstp->rq_res, base + n, inode,
-					  resp->acl_default,
-					  resp->mask & NFS_DFACL,
-					  NFS_ACL_DEFAULT);
-		if (n <= 0)
 			return false;
 		break;
 	default:

fs/nfsd/nfs3proc.c

@@ -13,6 +13,7 @@
 #include "cache.h"
 #include "xdr3.h"
 #include "vfs.h"
+#include "filecache.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 
@@ -763,6 +764,7 @@ nfsd3_proc_commit(struct svc_rqst *rqstp)
 {
 	struct nfsd3_commitargs *argp = rqstp->rq_argp;
 	struct nfsd3_commitres *resp = rqstp->rq_resp;
+	struct nfsd_file *nf;
 
 	dprintk("nfsd: COMMIT(3)   %s %u@%Lu\n",
 				SVCFH_fmt(&argp->fh),
@@ -770,8 +772,14 @@ nfsd3_proc_commit(struct svc_rqst *rqstp)
 				(unsigned long long) argp->offset);
 
 	fh_copy(&resp->fh, &argp->fh);
-	resp->status = nfsd_commit(rqstp, &resp->fh, argp->offset,
+	resp->status = nfsd_file_acquire_gc(rqstp, &resp->fh, NFSD_MAY_WRITE |
+					    NFSD_MAY_NOT_BREAK_LEASE, &nf);
+	if (resp->status)
+		goto out;
+	resp->status = nfsd_commit(rqstp, &resp->fh, nf, argp->offset,
 				   argp->count, resp->verf);
+	nfsd_file_put(nf);
+out:
 	return rpc_success;
 }
 

fs/nfsd/nfs4callback.c

@@ -76,6 +76,17 @@ static __be32 *xdr_encode_empty_array(__be32 *p)
  * 1 Protocol"
  */
 
+static void encode_uint32(struct xdr_stream *xdr, u32 n)
+{
+	WARN_ON_ONCE(xdr_stream_encode_u32(xdr, n) < 0);
+}
+
+static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
+			   size_t len)
+{
+	WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
+}
+
 /*
  *	nfs_cb_opnum4
  *
@@ -328,6 +339,24 @@ static void encode_cb_recall4args(struct xdr_stream *xdr,
 	hdr->nops++;
 }
 
+/*
+ * CB_RECALLANY4args
+ *
+ *	struct CB_RECALLANY4args {
+ *		uint32_t	craa_objects_to_keep;
+ *		bitmap4		craa_type_mask;
+ *	};
+ */
+static void
+encode_cb_recallany4args(struct xdr_stream *xdr,
+	struct nfs4_cb_compound_hdr *hdr, struct nfsd4_cb_recall_any *ra)
+{
+	encode_nfs_cb_opnum4(xdr, OP_CB_RECALL_ANY);
+	encode_uint32(xdr, ra->ra_keep);
+	encode_bitmap4(xdr, ra->ra_bmval, ARRAY_SIZE(ra->ra_bmval));
+	hdr->nops++;
+}
+
 /*
  * CB_SEQUENCE4args
  *
@@ -482,6 +511,26 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_cb_nops(&hdr);
 }
 
+/*
+ * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects
+ */
+static void
+nfs4_xdr_enc_cb_recall_any(struct rpc_rqst *req,
+		struct xdr_stream *xdr, const void *data)
+{
+	const struct nfsd4_callback *cb = data;
+	struct nfsd4_cb_recall_any *ra;
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = cb->cb_clp->cl_cb_ident,
+		.minorversion = cb->cb_clp->cl_minorversion,
+	};
+
+	ra = container_of(cb, struct nfsd4_cb_recall_any, ra_cb);
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+	encode_cb_recallany4args(xdr, &hdr, ra);
+	encode_cb_nops(&hdr);
+}
 
 /*
  * NFSv4.0 and NFSv4.1 XDR decode functions
@@ -520,6 +569,28 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 	return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status);
 }
 
+/*
+ * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects
+ */
+static int
+nfs4_xdr_dec_cb_recall_any(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfsd4_callback *cb = data;
+	struct nfs4_cb_compound_hdr hdr;
+	int status;
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		return status;
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
+	status =  decode_cb_op_status(xdr, OP_CB_RECALL_ANY, &cb->cb_status);
+	return status;
+}
+
 #ifdef CONFIG_NFSD_PNFS
 /*
  * CB_LAYOUTRECALL4args
@@ -783,6 +854,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
 #endif
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 	PROC(CB_OFFLOAD,	COMPOUND,	cb_offload,	cb_offload),
+	PROC(CB_RECALL_ANY,	COMPOUND,	cb_recall_any,	cb_recall_any),
 };
 
 static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];

fs/nfsd/nfs4idmap.c

@@ -41,6 +41,7 @@
 #include "idmap.h"
 #include "nfsd.h"
 #include "netns.h"
+#include "vfs.h"
 
 /*
  * Turn off idmapping when using AUTH_SYS.

fs/nfsd/nfs4proc.c

@@ -731,10 +731,19 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	     union nfsd4_op_u *u)
 {
 	struct nfsd4_commit *commit = &u->commit;
+	struct nfsd_file *nf;
+	__be32 status;
 
-	return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
+	status = nfsd_file_acquire(rqstp, &cstate->current_fh, NFSD_MAY_WRITE |
+				   NFSD_MAY_NOT_BREAK_LEASE, &nf);
+	if (status != nfs_ok)
+		return status;
+
+	status = nfsd_commit(rqstp, &cstate->current_fh, nf, commit->co_offset,
 			     commit->co_count,
 			     (__be32 *)commit->co_verf.data);
+	nfsd_file_put(nf);
+	return status;
 }
 
 static __be32
@@ -934,12 +943,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					&read->rd_stateid, RD_STATE,
 					&read->rd_nf, NULL);
-	if (status) {
+
-		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
-		goto out;
-	}
-	status = nfs_ok;
-out:
 	read->rd_rqstp = rqstp;
 	read->rd_fhp = &cstate->current_fh;
 	return status;
@@ -1108,10 +1112,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfs4_preprocess_stateid_op(rqstp, cstate,
 				&cstate->current_fh, &setattr->sa_stateid,
 				WR_STATE, NULL, NULL);
-		if (status) {
+		if (status)
-			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
-		}
 	}
 	err = fh_want_write(&cstate->current_fh);
 	if (err)
@@ -1133,6 +1135,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				0, (time64_t)0);
 	if (!status)
 		status = nfserrno(attrs.na_labelerr);
+	if (!status)
+		status = nfserrno(attrs.na_aclerr);
 out:
 	nfsd_attrs_free(&attrs);
 	fh_drop_write(&cstate->current_fh);
@@ -1159,10 +1163,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			       write->wr_offset, cnt);
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 						stateid, WR_STATE, &nf, NULL);
-	if (status) {
+	if (status)
-		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
-	}
 
 	write->wr_how_written = write->wr_stable_how;
 
@@ -1193,17 +1195,13 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
 					    src_stateid, RD_STATE, src, NULL);
-	if (status) {
+	if (status)
-		dprintk("NFSD: %s: couldn't process src stateid!\n", __func__);
 		goto out;
-	}
 
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    dst_stateid, WR_STATE, dst, NULL);
-	if (status) {
+	if (status)
-		dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__);
 		goto out_put_src;
-	}
 
 	/* fix up for NFS-specific error code */
 	if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) ||
@@ -1644,6 +1642,7 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy,
 	u64 src_pos = copy->cp_src_pos;
 	u64 dst_pos = copy->cp_dst_pos;
 	int status;
+	loff_t end;
 
 	/* See RFC 7862 p.67: */
 	if (bytes_total == 0)
@@ -1663,8 +1662,8 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy,
 	/* for a non-zero asynchronous copy do a commit of data */
 	if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) {
 		since = READ_ONCE(dst->f_wb_err);
-		status = vfs_fsync_range(dst, copy->cp_dst_pos,
+		end = copy->cp_dst_pos + copy->cp_res.wr_bytes_written - 1;
-					 copy->cp_res.wr_bytes_written, 0);
+		status = vfs_fsync_range(dst, copy->cp_dst_pos, end, 0);
 		if (!status)
 			status = filemap_check_wb_err(dst->f_mapping, since);
 		if (!status)
@@ -1948,10 +1947,8 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &fallocate->falloc_stateid,
 					    WR_STATE, &nf, NULL);
-	if (status != nfs_ok) {
+	if (status != nfs_ok)
-		dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n");
 		return status;
-	}
 
 	status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file,
 				     fallocate->falloc_offset,
@@ -2007,10 +2004,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
 					    &seek->seek_stateid,
 					    RD_STATE, &nf, NULL);
-	if (status) {
+	if (status)
-		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
 		return status;
-	}
 
 	switch (seek->seek_whence) {
 	case NFS4_CONTENT_DATA:

fs/nfsd/nfs4state.c

@@ -44,7 +44,9 @@
 #include <linux/jhash.h>
 #include <linux/string_helpers.h>
 #include <linux/fsnotify.h>
+#include <linux/rhashtable.h>
 #include <linux/nfs_ssc.h>
+
 #include "xdr4.h"
 #include "xdr4cb.h"
 #include "vfs.h"
@@ -84,6 +86,7 @@ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
 void nfsd4_end_grace(struct nfsd_net *nn);
 static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps);
+static void nfsd4_file_hash_remove(struct nfs4_file *fi);
 
 /* Locking: */
 
@@ -588,11 +591,8 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu)
 void
 put_nfs4_file(struct nfs4_file *fi)
 {
-	might_lock(&state_lock);
+	if (refcount_dec_and_test(&fi->fi_ref)) {
-
+		nfsd4_file_hash_remove(fi);
-	if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) {
-		hlist_del_rcu(&fi->fi_hash);
-		spin_unlock(&state_lock);
 		WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate));
 		WARN_ON_ONCE(!list_empty(&fi->fi_delegations));
 		call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu);
@@ -675,15 +675,26 @@ find_any_file(struct nfs4_file *f)
 	return ret;
 }
 
-static struct nfsd_file *find_deleg_file(struct nfs4_file *f)
+static struct nfsd_file *find_any_file_locked(struct nfs4_file *f)
 {
-	struct nfsd_file *ret = NULL;
+	lockdep_assert_held(&f->fi_lock);
+
+	if (f->fi_fds[O_RDWR])
+		return f->fi_fds[O_RDWR];
+	if (f->fi_fds[O_WRONLY])
+		return f->fi_fds[O_WRONLY];
+	if (f->fi_fds[O_RDONLY])
+		return f->fi_fds[O_RDONLY];
+	return NULL;
+}
+
+static struct nfsd_file *find_deleg_file_locked(struct nfs4_file *f)
+{
+	lockdep_assert_held(&f->fi_lock);
 
-	spin_lock(&f->fi_lock);
 	if (f->fi_deleg_file)
-		ret = nfsd_file_get(f->fi_deleg_file);
+		return f->fi_deleg_file;
-	spin_unlock(&f->fi_lock);
+	return NULL;
-	return ret;
 }
 
 static atomic_long_t num_delegations;
@@ -706,19 +717,20 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername)
 	return ret & OWNER_HASH_MASK;
 }
 
-/* hash table for nfs4_file */
+static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp;
-#define FILE_HASH_BITS                   8
-#define FILE_HASH_SIZE                  (1 << FILE_HASH_BITS)
 
-static unsigned int file_hashval(struct svc_fh *fh)
+static const struct rhashtable_params nfs4_file_rhash_params = {
-{
+	.key_len		= sizeof_field(struct nfs4_file, fi_inode),
-	struct inode *inode = d_inode(fh->fh_dentry);
+	.key_offset		= offsetof(struct nfs4_file, fi_inode),
+	.head_offset		= offsetof(struct nfs4_file, fi_rlist),
 
-	/* XXX: why not (here & in file cache) use inode? */
+	/*
-	return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS);
+	 * Start with a single page hash table to reduce resizing churn
-}
+	 * on light workloads.
-
+	 */
-static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
+	.min_size		= 256,
+	.automatic_shrinking	= true,
+};
 
 /*
  * Check if courtesy clients have conflicting access and resolve it if possible
@@ -831,9 +843,9 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 			swap(f2, fp->fi_fds[O_RDWR]);
 		spin_unlock(&fp->fi_lock);
 		if (f1)
-			nfsd_file_close(f1);
+			nfsd_file_put(f1);
 		if (f2)
-			nfsd_file_close(f2);
+			nfsd_file_put(f2);
 	}
 }
 
@@ -1355,6 +1367,8 @@ static void revoke_delegation(struct nfs4_delegation *dp)
 
 	WARN_ON(!list_empty(&dp->dl_recall_lru));
 
+	trace_nfsd_stid_revoke(&dp->dl_stid);
+
 	if (clp->cl_minorversion) {
 		dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID;
 		refcount_inc(&dp->dl_stid.sc_count);
@@ -1819,13 +1833,12 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
 	int numslots = fattrs->maxreqs;
 	int slotsize = slot_bytes(fattrs);
 	struct nfsd4_session *new;
-	int mem, i;
+	int i;
 
-	BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *)
+	BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION)
-			+ sizeof(struct nfsd4_session) > PAGE_SIZE);
+		     > PAGE_SIZE);
-	mem = numslots * sizeof(struct nfsd4_slot *);
 
-	new = kzalloc(sizeof(*new) + mem, GFP_KERNEL);
+	new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL);
 	if (!new)
 		return NULL;
 	/* allocate each struct nfsd4_slot and data cache in one piece */
@@ -2131,6 +2144,7 @@ static void __free_client(struct kref *k)
 	kfree(clp->cl_nii_domain.data);
 	kfree(clp->cl_nii_name.data);
 	idr_destroy(&clp->cl_stateids);
+	kfree(clp->cl_ra);
 	kmem_cache_free(client_slab, clp);
 }
 
@@ -2613,9 +2627,11 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
 	ols = openlockstateid(st);
 	oo = ols->st_stateowner;
 	nf = st->sc_file;
-	file = find_any_file(nf);
+
+	spin_lock(&nf->fi_lock);
+	file = find_any_file_locked(nf);
 	if (!file)
-		return 0;
+		goto out;
 
 	seq_printf(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
@@ -2637,8 +2653,8 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
 	seq_printf(s, ", ");
 	nfs4_show_owner(s, oo);
 	seq_printf(s, " }\n");
-	nfsd_file_put(file);
+out:
-
+	spin_unlock(&nf->fi_lock);
 	return 0;
 }
 
@@ -2652,9 +2668,10 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st)
 	ols = openlockstateid(st);
 	oo = ols->st_stateowner;
 	nf = st->sc_file;
-	file = find_any_file(nf);
+	spin_lock(&nf->fi_lock);
+	file = find_any_file_locked(nf);
 	if (!file)
-		return 0;
+		goto out;
 
 	seq_printf(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
@@ -2674,8 +2691,8 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st)
 	seq_printf(s, ", ");
 	nfs4_show_owner(s, oo);
 	seq_printf(s, " }\n");
-	nfsd_file_put(file);
+out:
-
+	spin_unlock(&nf->fi_lock);
 	return 0;
 }
 
@@ -2687,9 +2704,10 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 
 	ds = delegstateid(st);
 	nf = st->sc_file;
-	file = find_deleg_file(nf);
+	spin_lock(&nf->fi_lock);
+	file = find_deleg_file_locked(nf);
 	if (!file)
-		return 0;
+		goto out;
 
 	seq_printf(s, "- ");
 	nfs4_show_stateid(s, &st->sc_stateid);
@@ -2705,8 +2723,8 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 	seq_printf(s, ", ");
 	nfs4_show_fname(s, file);
 	seq_printf(s, " }\n");
-	nfsd_file_put(file);
+out:
-
+	spin_unlock(&nf->fi_lock);
 	return 0;
 }
 
@@ -2854,6 +2872,37 @@ static const struct tree_descr client_files[] = {
 	[3] = {""},
 };
 
+static int
+nfsd4_cb_recall_any_done(struct nfsd4_callback *cb,
+				struct rpc_task *task)
+{
+	trace_nfsd_cb_recall_any_done(cb, task);
+	switch (task->tk_status) {
+	case -NFS4ERR_DELAY:
+		rpc_delay(task, 2 * HZ);
+		return 0;
+	default:
+		return 1;
+	}
+}
+
+static void
+nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_client *clp = cb->cb_clp;
+	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+	spin_lock(&nn->client_lock);
+	clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
+	put_client_renew_locked(clp);
+	spin_unlock(&nn->client_lock);
+}
+
+static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
+	.done		= nfsd4_cb_recall_any_done,
+	.release	= nfsd4_cb_recall_any_release,
+};
+
 static struct nfs4_client *create_client(struct xdr_netobj name,
 		struct svc_rqst *rqstp, nfs4_verifier *verf)
 {
@@ -2891,6 +2940,14 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 		free_client(clp);
 		return NULL;
 	}
+	clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL);
+	if (!clp->cl_ra) {
+		free_client(clp);
+		return NULL;
+	}
+	clp->cl_ra_time = 0;
+	nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops,
+			NFSPROC4_CLNT_CB_RECALL_ANY);
 	return clp;
 }
 
@@ -4260,11 +4317,9 @@ static struct nfs4_file *nfsd4_alloc_file(void)
 }
 
 /* OPEN Share state helper functions */
-static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval,
-				struct nfs4_file *fp)
-{
-	lockdep_assert_held(&state_lock);
 
+static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp)
+{
 	refcount_set(&fp->fi_ref, 1);
 	spin_lock_init(&fp->fi_lock);
 	INIT_LIST_HEAD(&fp->fi_stateids);
@@ -4282,7 +4337,6 @@ static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval,
 	INIT_LIST_HEAD(&fp->fi_lo_states);
 	atomic_set(&fp->fi_lo_recalls, 0);
 #endif
-	hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
 }
 
 void
@@ -4347,20 +4401,22 @@ out:
 }
 
 static unsigned long
-nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc)
+nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	int cnt;
+	int count;
 	struct nfsd_net *nn = container_of(shrink,
 			struct nfsd_net, nfsd_client_shrinker);
 
-	cnt = atomic_read(&nn->nfsd_courtesy_clients);
+	count = atomic_read(&nn->nfsd_courtesy_clients);
-	if (cnt > 0)
+	if (!count)
+		count = atomic_long_read(&num_delegations);
+	if (count)
 		mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
-	return (unsigned long)cnt;
+	return (unsigned long)count;
 }
 
 static unsigned long
-nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc)
+nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
 	return SHRINK_STOP;
 }
@@ -4387,8 +4443,8 @@ nfsd4_init_leases_net(struct nfsd_net *nn)
 	nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
 
 	atomic_set(&nn->nfsd_courtesy_clients, 0);
-	nn->nfsd_client_shrinker.scan_objects = nfsd_courtesy_client_scan;
+	nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
-	nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_count;
+	nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
 	nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
 	return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
 }
@@ -4667,71 +4723,80 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
 		nfs4_put_stid(&last->st_stid);
 }
 
-/* search file_hashtbl[] for file */
+static noinline_for_stack struct nfs4_file *
-static struct nfs4_file *
+nfsd4_file_hash_lookup(const struct svc_fh *fhp)
-find_file_locked(struct svc_fh *fh, unsigned int hashval)
 {
-	struct nfs4_file *fp;
+	struct inode *inode = d_inode(fhp->fh_dentry);
+	struct rhlist_head *tmp, *list;
+	struct nfs4_file *fi;
 
-	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash,
+	rcu_read_lock();
-				lockdep_is_held(&state_lock)) {
+	list = rhltable_lookup(&nfs4_file_rhltable, &inode,
-		if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) {
+			       nfs4_file_rhash_params);
-			if (refcount_inc_not_zero(&fp->fi_ref))
+	rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) {
-				return fp;
+		if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) {
+			if (refcount_inc_not_zero(&fi->fi_ref)) {
+				rcu_read_unlock();
+				return fi;
+			}
 		}
 	}
+	rcu_read_unlock();
 	return NULL;
 }
 
-static struct nfs4_file *insert_file(struct nfs4_file *new, struct svc_fh *fh,
+/*
-				     unsigned int hashval)
+ * On hash insertion, identify entries with the same inode but
+ * distinct filehandles. They will all be on the list returned
+ * by rhltable_lookup().
+ *
+ * inode->i_lock prevents racing insertions from adding an entry
+ * for the same inode/fhp pair twice.
+ */
+static noinline_for_stack struct nfs4_file *
+nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp)
 {
-	struct nfs4_file *fp;
+	struct inode *inode = d_inode(fhp->fh_dentry);
+	struct rhlist_head *tmp, *list;
 	struct nfs4_file *ret = NULL;
 	bool alias_found = false;
+	struct nfs4_file *fi;
+	int err;
 
-	spin_lock(&state_lock);
+	rcu_read_lock();
-	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash,
+	spin_lock(&inode->i_lock);
-				 lockdep_is_held(&state_lock)) {
+
-		if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) {
+	list = rhltable_lookup(&nfs4_file_rhltable, &inode,
-			if (refcount_inc_not_zero(&fp->fi_ref))
+			       nfs4_file_rhash_params);
-				ret = fp;
+	rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) {
-		} else if (d_inode(fh->fh_dentry) == fp->fi_inode)
+		if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) {
-			fp->fi_aliased = alias_found = true;
+			if (refcount_inc_not_zero(&fi->fi_ref))
+				ret = fi;
+		} else
+			fi->fi_aliased = alias_found = true;
 	}
-	if (likely(ret == NULL)) {
+	if (ret)
-		nfsd4_init_file(fh, hashval, new);
+		goto out_unlock;
-		new->fi_aliased = alias_found;
+
-		ret = new;
+	nfsd4_file_init(fhp, new);
-	}
+	err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist,
-	spin_unlock(&state_lock);
+			      nfs4_file_rhash_params);
+	if (err)
+		goto out_unlock;
+
+	new->fi_aliased = alias_found;
+	ret = new;
+
+out_unlock:
+	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 	return ret;
 }
 
-static struct nfs4_file * find_file(struct svc_fh *fh)
+static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi)
 {
-	struct nfs4_file *fp;
+	rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist,
-	unsigned int hashval = file_hashval(fh);
+			nfs4_file_rhash_params);
-
-	rcu_read_lock();
-	fp = find_file_locked(fh, hashval);
-	rcu_read_unlock();
-	return fp;
-}
-
-static struct nfs4_file *
-find_or_add_file(struct nfs4_file *new, struct svc_fh *fh)
-{
-	struct nfs4_file *fp;
-	unsigned int hashval = file_hashval(fh);
-
-	rcu_read_lock();
-	fp = find_file_locked(fh, hashval);
-	rcu_read_unlock();
-	if (fp)
-		return fp;
-
-	return insert_file(new, fh, hashval);
 }
 
 /*
@@ -4744,9 +4809,10 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
 	struct nfs4_file *fp;
 	__be32 ret = nfs_ok;
 
-	fp = find_file(current_fh);
+	fp = nfsd4_file_hash_lookup(current_fh);
 	if (!fp)
 		return ret;
+
 	/* Check for conflicting share reservations */
 	spin_lock(&fp->fi_lock);
 	if (fp->fi_share_deny & deny_type)
@@ -5620,7 +5686,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	 * and check for delegations in the process of being recalled.
 	 * If not found, create the nfs4_file struct
 	 */
-	fp = find_or_add_file(open->op_file, current_fh);
+	fp = nfsd4_file_hash_insert(open->op_file, current_fh);
+	if (unlikely(!fp))
+		return nfserr_jukebox;
 	if (fp != open->op_file) {
 		status = nfs4_check_deleg(cl, open, &dp);
 		if (status)
@@ -6125,17 +6193,64 @@ laundromat_main(struct work_struct *laundry)
 }
 
 static void
-courtesy_client_reaper(struct work_struct *reaper)
+courtesy_client_reaper(struct nfsd_net *nn)
 {
 	struct list_head reaplist;
-	struct delayed_work *dwork = to_delayed_work(reaper);
-	struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
-					nfsd_shrinker_work);
 
 	nfs4_get_courtesy_client_reaplist(nn, &reaplist);
 	nfs4_process_client_reaplist(&reaplist);
 }
 
+static void
+deleg_reaper(struct nfsd_net *nn)
+{
+	struct list_head *pos, *next;
+	struct nfs4_client *clp;
+	struct list_head cblist;
+
+	INIT_LIST_HEAD(&cblist);
+	spin_lock(&nn->client_lock);
+	list_for_each_safe(pos, next, &nn->client_lru) {
+		clp = list_entry(pos, struct nfs4_client, cl_lru);
+		if (clp->cl_state != NFSD4_ACTIVE ||
+			list_empty(&clp->cl_delegations) ||
+			atomic_read(&clp->cl_delegs_in_recall) ||
+			test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) ||
+			(ktime_get_boottime_seconds() -
+				clp->cl_ra_time < 5)) {
+			continue;
+		}
+		list_add(&clp->cl_ra_cblist, &cblist);
+
+		/* release in nfsd4_cb_recall_any_release */
+		atomic_inc(&clp->cl_rpc_users);
+		set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
+		clp->cl_ra_time = ktime_get_boottime_seconds();
+	}
+	spin_unlock(&nn->client_lock);
+
+	while (!list_empty(&cblist)) {
+		clp = list_first_entry(&cblist, struct nfs4_client,
+					cl_ra_cblist);
+		list_del_init(&clp->cl_ra_cblist);
+		clp->cl_ra->ra_keep = 0;
+		clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG);
+		trace_nfsd_cb_recall_any(clp->cl_ra);
+		nfsd4_run_cb(&clp->cl_ra->ra_cb);
+	}
+}
+
+static void
+nfsd4_state_shrinker_worker(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+				nfsd_shrinker_work);
+
+	courtesy_client_reaper(nn);
+	deleg_reaper(nn);
+}
+
 static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 {
 	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
@@ -6902,6 +7017,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto put_stateid;
 
+	trace_nfsd_deleg_return(stateid);
 	wake_up_var(d_inode(cstate->current_fh.fh_dentry));
 	destroy_delegation(dp);
 put_stateid:
@@ -7958,7 +8074,7 @@ static int nfs4_state_create_net(struct net *net)
 	INIT_LIST_HEAD(&nn->blocked_locks_lru);
 
 	INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
-	INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, courtesy_client_reaper);
+	INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
 	get_net(net);
 
 	return 0;
@@ -8034,10 +8150,16 @@ nfs4_state_start(void)
 {
 	int ret;
 
-	ret = nfsd4_create_callback_queue();
+	ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params);
 	if (ret)
 		return ret;
 
+	ret = nfsd4_create_callback_queue();
+	if (ret) {
+		rhltable_destroy(&nfs4_file_rhltable);
+		return ret;
+	}
+
 	set_max_delegations();
 	return 0;
 }
@@ -8068,6 +8190,7 @@ nfs4_state_shutdown_net(struct net *net)
 
 	nfsd4_client_tracking_exit(net);
 	nfs4_state_destroy_net(net);
+	rhltable_destroy(&nfs4_file_rhltable);
 #ifdef CONFIG_NFSD_V4_2_INTER_SSC
 	nfsd4_ssc_shutdown_umount(nn);
 #endif

fs/nfsd/nfsctl.c

@@ -581,7 +581,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 
 			cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET;
 			switch(num) {
+#ifdef CONFIG_NFSD_V2
 			case 2:
+#endif
 			case 3:
 				nfsd_vers(nn, num, cmd);
 				break;
@@ -601,7 +603,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 				}
 				break;
 			default:
-				return -EINVAL;
+				/* Ignore requests to disable non-existent versions */
+				if (cmd == NFSD_SET)
+					return -EINVAL;
 			}
 			vers += len + 1;
 		} while ((len = qword_get(&mesg, vers, size)) > 0);

fs/nfsd/nfsd.h

@@ -64,8 +64,7 @@ struct readdir_cd {
 
 
 extern struct svc_program	nfsd_program;
-extern const struct svc_version	nfsd_version2, nfsd_version3,
+extern const struct svc_version	nfsd_version2, nfsd_version3, nfsd_version4;
-				nfsd_version4;
 extern struct mutex		nfsd_mutex;
 extern spinlock_t		nfsd_drc_lock;
 extern unsigned long		nfsd_drc_max_mem;

fs/nfsd/nfsfh.h

@@ -220,7 +220,7 @@ __be32	fh_update(struct svc_fh *);
 void	fh_put(struct svc_fh *);
 
 static __inline__ struct svc_fh *
-fh_copy(struct svc_fh *dst, struct svc_fh *src)
+fh_copy(struct svc_fh *dst, const struct svc_fh *src)
 {
 	WARN_ON(src->fh_dentry);
 
@@ -229,7 +229,7 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src)
 }
 
 static inline void
-fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src)
+fh_copy_shallow(struct knfsd_fh *dst, const struct knfsd_fh *src)
 {
 	dst->fh_size = src->fh_size;
 	memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size);
@@ -243,7 +243,8 @@ fh_init(struct svc_fh *fhp, int maxsize)
 	return fhp;
 }
 
-static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+static inline bool fh_match(const struct knfsd_fh *fh1,
+			    const struct knfsd_fh *fh2)
 {
 	if (fh1->fh_size != fh2->fh_size)
 		return false;
@@ -252,7 +253,8 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
 	return true;
 }
 
-static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2)
+static inline bool fh_fsid_match(const struct knfsd_fh *fh1,
+				 const struct knfsd_fh *fh2)
 {
 	if (fh1->fh_fsid_type != fh2->fh_fsid_type)
 		return false;

fs/nfsd/nfsproc.c

@@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
 	if (resp->status == nfs_ok)
 		resp->status = fh_getattr(&resp->fh, &resp->stat);
 	else if (resp->status == nfserr_jukebox)
-		return rpc_drop_reply;
+		__set_bit(RQ_DROPME, &rqstp->rq_flags);
 	return rpc_success;
 }
 
@@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp)
 	if (resp->status == nfs_ok)
 		resp->status = fh_getattr(&resp->fh, &resp->stat);
 	else if (resp->status == nfserr_jukebox)
-		return rpc_drop_reply;
+		__set_bit(RQ_DROPME, &rqstp->rq_flags);
 	return rpc_success;
 }
 
@@ -848,65 +848,3 @@ const struct svc_version nfsd_version2 = {
 	.vs_dispatch	= nfsd_dispatch,
 	.vs_xdrsize	= NFS2_SVC_XDRSIZE,
 };
-
-/*
- * Map errnos to NFS errnos.
- */
-__be32
-nfserrno (int errno)
-{
-	static struct {
-		__be32	nfserr;
-		int	syserr;
-	} nfs_errtbl[] = {
-		{ nfs_ok, 0 },
-		{ nfserr_perm, -EPERM },
-		{ nfserr_noent, -ENOENT },
-		{ nfserr_io, -EIO },
-		{ nfserr_nxio, -ENXIO },
-		{ nfserr_fbig, -E2BIG },
-		{ nfserr_stale, -EBADF },
-		{ nfserr_acces, -EACCES },
-		{ nfserr_exist, -EEXIST },
-		{ nfserr_xdev, -EXDEV },
-		{ nfserr_mlink, -EMLINK },
-		{ nfserr_nodev, -ENODEV },
-		{ nfserr_notdir, -ENOTDIR },
-		{ nfserr_isdir, -EISDIR },
-		{ nfserr_inval, -EINVAL },
-		{ nfserr_fbig, -EFBIG },
-		{ nfserr_nospc, -ENOSPC },
-		{ nfserr_rofs, -EROFS },
-		{ nfserr_mlink, -EMLINK },
-		{ nfserr_nametoolong, -ENAMETOOLONG },
-		{ nfserr_notempty, -ENOTEMPTY },
-#ifdef EDQUOT
-		{ nfserr_dquot, -EDQUOT },
-#endif
-		{ nfserr_stale, -ESTALE },
-		{ nfserr_jukebox, -ETIMEDOUT },
-		{ nfserr_jukebox, -ERESTARTSYS },
-		{ nfserr_jukebox, -EAGAIN },
-		{ nfserr_jukebox, -EWOULDBLOCK },
-		{ nfserr_jukebox, -ENOMEM },
-		{ nfserr_io, -ETXTBSY },
-		{ nfserr_notsupp, -EOPNOTSUPP },
-		{ nfserr_toosmall, -ETOOSMALL },
-		{ nfserr_serverfault, -ESERVERFAULT },
-		{ nfserr_serverfault, -ENFILE },
-		{ nfserr_io, -EREMOTEIO },
-		{ nfserr_stale, -EOPENSTALE },
-		{ nfserr_io, -EUCLEAN },
-		{ nfserr_perm, -ENOKEY },
-		{ nfserr_no_grace, -ENOGRACE},
-	};
-	int	i;
-
-	for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) {
-		if (nfs_errtbl[i].syserr == errno)
-			return nfs_errtbl[i].nfserr;
-	}
-	WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno);
-	return nfserr_io;
-}
-

fs/nfsd/nfssvc.c

@@ -91,8 +91,12 @@ unsigned long	nfsd_drc_mem_used;
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat	nfsd_acl_svcstats;
 static const struct svc_version *nfsd_acl_version[] = {
+# if defined(CONFIG_NFSD_V2_ACL)
 	[2] = &nfsd_acl_version2,
+# endif
+# if defined(CONFIG_NFSD_V3_ACL)
 	[3] = &nfsd_acl_version3,
+# endif
 };
 
 #define NFSD_ACL_MINVERS            2
@@ -116,7 +120,9 @@ static struct svc_stat	nfsd_acl_svcstats = {
 #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
 
 static const struct svc_version *nfsd_version[] = {
+#if defined(CONFIG_NFSD_V2)
 	[2] = &nfsd_version2,
+#endif
 	[3] = &nfsd_version3,
 #if defined(CONFIG_NFSD_V4)
 	[4] = &nfsd_version4,
@@ -1054,7 +1060,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	svcxdr_init_encode(rqstp);
 
 	*statp = proc->pc_func(rqstp);
-	if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags))
+	if (test_bit(RQ_DROPME, &rqstp->rq_flags))
 		goto out_update_drop;
 
 	if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream))

fs/nfsd/state.h

@@ -368,6 +368,7 @@ struct nfs4_client {
 #define NFSD4_CLIENT_UPCALL_LOCK	(5)	/* upcall serialization */
 #define NFSD4_CLIENT_CB_FLAG_MASK	(1 << NFSD4_CLIENT_CB_UPDATE | \
 					 1 << NFSD4_CLIENT_CB_KILL)
+#define NFSD4_CLIENT_CB_RECALL_ANY	(6)
 	unsigned long		cl_flags;
 	const struct cred	*cl_cb_cred;
 	struct rpc_clnt		*cl_cb_client;
@@ -411,6 +412,10 @@ struct nfs4_client {
 
 	unsigned int		cl_state;
 	atomic_t		cl_delegs_in_recall;
+
+	struct nfsd4_cb_recall_any	*cl_ra;
+	time64_t		cl_ra_time;
+	struct list_head	cl_ra_cblist;
 };
 
 /* struct nfs4_client_reset
@@ -536,16 +541,13 @@ struct nfs4_clnt_odstate {
  * inode can have multiple filehandles associated with it, so there is
  * (potentially) a many to one relationship between this struct and struct
  * inode.
- *
- * These are hashed by filehandle in the file_hashtbl, which is protected by
- * the global state_lock spinlock.
  */
 struct nfs4_file {
 	refcount_t		fi_ref;
 	struct inode *		fi_inode;
 	bool			fi_aliased;
 	spinlock_t		fi_lock;
-	struct hlist_node       fi_hash;	/* hash on fi_fhandle */
+	struct rhlist_head	fi_rlist;
 	struct list_head        fi_stateids;
 	union {
 		struct list_head	fi_delegations;
@@ -639,6 +641,7 @@ enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_OFFLOAD,
 	NFSPROC4_CLNT_CB_SEQUENCE,
 	NFSPROC4_CLNT_CB_NOTIFY_LOCK,
+	NFSPROC4_CLNT_CB_RECALL_ANY,
 };
 
 /* Returns true iff a is later than b: */

fs/nfsd/trace.h

@@ -9,9 +9,12 @@
 #define _NFSD_TRACE_H
 
 #include <linux/tracepoint.h>
+#include <linux/sunrpc/xprt.h>
+#include <trace/misc/nfs.h>
 
 #include "export.h"
 #include "nfsfh.h"
+#include "xdr4.h"
 
 #define NFSD_TRACE_PROC_RES_FIELDS \
 		__field(unsigned int, netns_ino) \
@@ -604,6 +607,7 @@ DEFINE_STATEID_EVENT(layout_recall_release);
 
 DEFINE_STATEID_EVENT(open);
 DEFINE_STATEID_EVENT(deleg_read);
+DEFINE_STATEID_EVENT(deleg_return);
 DEFINE_STATEID_EVENT(deleg_recall);
 
 DECLARE_EVENT_CLASS(nfsd_stateseqid_class,
@@ -636,6 +640,61 @@ DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \
 DEFINE_STATESEQID_EVENT(preprocess);
 DEFINE_STATESEQID_EVENT(open_confirm);
 
+TRACE_DEFINE_ENUM(NFS4_OPEN_STID);
+TRACE_DEFINE_ENUM(NFS4_LOCK_STID);
+TRACE_DEFINE_ENUM(NFS4_DELEG_STID);
+TRACE_DEFINE_ENUM(NFS4_CLOSED_STID);
+TRACE_DEFINE_ENUM(NFS4_REVOKED_DELEG_STID);
+TRACE_DEFINE_ENUM(NFS4_CLOSED_DELEG_STID);
+TRACE_DEFINE_ENUM(NFS4_LAYOUT_STID);
+
+#define show_stid_type(x)						\
+	__print_flags(x, "|",						\
+		{ NFS4_OPEN_STID,		"OPEN" },		\
+		{ NFS4_LOCK_STID,		"LOCK" },		\
+		{ NFS4_DELEG_STID,		"DELEG" },		\
+		{ NFS4_CLOSED_STID,		"CLOSED" },		\
+		{ NFS4_REVOKED_DELEG_STID,	"REVOKED" },		\
+		{ NFS4_CLOSED_DELEG_STID,	"CLOSED_DELEG" },	\
+		{ NFS4_LAYOUT_STID,		"LAYOUT" })
+
+DECLARE_EVENT_CLASS(nfsd_stid_class,
+	TP_PROTO(
+		const struct nfs4_stid *stid
+	),
+	TP_ARGS(stid),
+	TP_STRUCT__entry(
+		__field(unsigned long, sc_type)
+		__field(int, sc_count)
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, si_id)
+		__field(u32, si_generation)
+	),
+	TP_fast_assign(
+		const stateid_t *stp = &stid->sc_stateid;
+
+		__entry->sc_type = stid->sc_type;
+		__entry->sc_count = refcount_read(&stid->sc_count);
+		__entry->cl_boot = stp->si_opaque.so_clid.cl_boot;
+		__entry->cl_id = stp->si_opaque.so_clid.cl_id;
+		__entry->si_id = stp->si_opaque.so_id;
+		__entry->si_generation = stp->si_generation;
+	),
+	TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s",
+		__entry->cl_boot, __entry->cl_id,
+		__entry->si_id, __entry->si_generation,
+		__entry->sc_count, show_stid_type(__entry->sc_type)
+	)
+);
+
+#define DEFINE_STID_EVENT(name)					\
+DEFINE_EVENT(nfsd_stid_class, nfsd_stid_##name,			\
+	TP_PROTO(const struct nfs4_stid *stid),			\
+	TP_ARGS(stid))
+
+DEFINE_STID_EVENT(revoke);
+
 DECLARE_EVENT_CLASS(nfsd_clientid_class,
 	TP_PROTO(const clientid_t *clid),
 	TP_ARGS(clid),
@@ -817,7 +876,8 @@ DEFINE_CLID_EVENT(confirmed_r);
 	__print_flags(val, "|",						\
 		{ 1 << NFSD_FILE_HASHED,	"HASHED" },		\
 		{ 1 << NFSD_FILE_PENDING,	"PENDING" },		\
-		{ 1 << NFSD_FILE_REFERENCED,	"REFERENCED"})
+		{ 1 << NFSD_FILE_REFERENCED,	"REFERENCED"},		\
+		{ 1 << NFSD_FILE_GC,		"GC"})
 
 DECLARE_EVENT_CLASS(nfsd_file_class,
 	TP_PROTO(struct nfsd_file *nf),
@@ -849,10 +909,10 @@ DEFINE_EVENT(nfsd_file_class, name, \
 	TP_PROTO(struct nfsd_file *nf), \
 	TP_ARGS(nf))
 
-DEFINE_NFSD_FILE_EVENT(nfsd_file_put_final);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_free);
 DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash);
 DEFINE_NFSD_FILE_EVENT(nfsd_file_put);
-DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_dispose);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_queue);
 
 TRACE_EVENT(nfsd_file_alloc,
 	TP_PROTO(
@@ -1181,6 +1241,37 @@ DEFINE_EVENT(nfsd_file_lruwalk_class, name,				\
 DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed);
 DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed);
 
+TRACE_EVENT(nfsd_file_fsync,
+	TP_PROTO(
+		const struct nfsd_file *nf,
+		int ret
+	),
+	TP_ARGS(nf, ret),
+	TP_STRUCT__entry(
+		__field(void *, nf_inode)
+		__field(int, nf_ref)
+		__field(int, ret)
+		__field(unsigned long, nf_flags)
+		__field(unsigned char, nf_may)
+		__field(struct file *, nf_file)
+	),
+	TP_fast_assign(
+		__entry->nf_inode = nf->nf_inode;
+		__entry->nf_ref = refcount_read(&nf->nf_ref);
+		__entry->ret = ret;
+		__entry->nf_flags = nf->nf_flags;
+		__entry->nf_may = nf->nf_may;
+		__entry->nf_file = nf->nf_file;
+	),
+	TP_printk("inode=%p ref=%d flags=%s may=%s nf_file=%p ret=%d",
+		__entry->nf_inode,
+		__entry->nf_ref,
+		show_nf_flags(__entry->nf_flags),
+		show_nfsd_may_flags(__entry->nf_may),
+		__entry->nf_file, __entry->ret
+	)
+);
+
 #include "cache.h"
 
 TRACE_DEFINE_ENUM(RC_DROPIT);
@@ -1474,6 +1565,32 @@ TRACE_EVENT(nfsd_cb_offload,
 		__entry->fh_hash, __entry->count, __entry->status)
 );
 
+TRACE_EVENT(nfsd_cb_recall_any,
+	TP_PROTO(
+		const struct nfsd4_cb_recall_any *ra
+	),
+	TP_ARGS(ra),
+	TP_STRUCT__entry(
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(u32, keep)
+		__field(unsigned long, bmval0)
+		__sockaddr(addr, ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen)
+	),
+	TP_fast_assign(
+		__entry->cl_boot = ra->ra_cb.cb_clp->cl_clientid.cl_boot;
+		__entry->cl_id = ra->ra_cb.cb_clp->cl_clientid.cl_id;
+		__entry->keep = ra->ra_keep;
+		__entry->bmval0 = ra->ra_bmval[0];
+		__assign_sockaddr(addr, &ra->ra_cb.cb_clp->cl_addr,
+				  ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen);
+	),
+	TP_printk("addr=%pISpc client %08x:%08x keep=%u bmval0=%s",
+		__get_sockaddr(addr), __entry->cl_boot, __entry->cl_id,
+		__entry->keep, show_rca_mask(__entry->bmval0)
+	)
+);
+
 DECLARE_EVENT_CLASS(nfsd_cb_done_class,
 	TP_PROTO(
 		const stateid_t *stp,
@@ -1513,6 +1630,27 @@ DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_notify_lock_done);
 DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_layout_done);
 DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_offload_done);
 
+TRACE_EVENT(nfsd_cb_recall_any_done,
+	TP_PROTO(
+		const struct nfsd4_callback *cb,
+		const struct rpc_task *task
+	),
+	TP_ARGS(cb, task),
+	TP_STRUCT__entry(
+		__field(u32, cl_boot)
+		__field(u32, cl_id)
+		__field(int, status)
+	),
+	TP_fast_assign(
+		__entry->status = task->tk_status;
+		__entry->cl_boot = cb->cb_clp->cl_clientid.cl_boot;
+		__entry->cl_id = cb->cb_clp->cl_clientid.cl_id;
+	),
+	TP_printk("client %08x:%08x status=%d",
+		__entry->cl_boot, __entry->cl_id, __entry->status
+	)
+);
+
 #endif /* _NFSD_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH

fs/nfsd/vfs.c

@@ -49,6 +49,69 @@
 
 #define NFSDDBG_FACILITY		NFSDDBG_FILEOP
 
+/**
+ * nfserrno - Map Linux errnos to NFS errnos
+ * @errno: POSIX(-ish) error code to be mapped
+ *
+ * Returns the appropriate (net-endian) nfserr_* (or nfs_ok if errno is 0). If
+ * it's an error we don't expect, log it once and return nfserr_io.
+ */
+__be32
+nfserrno (int errno)
+{
+	static struct {
+		__be32	nfserr;
+		int	syserr;
+	} nfs_errtbl[] = {
+		{ nfs_ok, 0 },
+		{ nfserr_perm, -EPERM },
+		{ nfserr_noent, -ENOENT },
+		{ nfserr_io, -EIO },
+		{ nfserr_nxio, -ENXIO },
+		{ nfserr_fbig, -E2BIG },
+		{ nfserr_stale, -EBADF },
+		{ nfserr_acces, -EACCES },
+		{ nfserr_exist, -EEXIST },
+		{ nfserr_xdev, -EXDEV },
+		{ nfserr_mlink, -EMLINK },
+		{ nfserr_nodev, -ENODEV },
+		{ nfserr_notdir, -ENOTDIR },
+		{ nfserr_isdir, -EISDIR },
+		{ nfserr_inval, -EINVAL },
+		{ nfserr_fbig, -EFBIG },
+		{ nfserr_nospc, -ENOSPC },
+		{ nfserr_rofs, -EROFS },
+		{ nfserr_mlink, -EMLINK },
+		{ nfserr_nametoolong, -ENAMETOOLONG },
+		{ nfserr_notempty, -ENOTEMPTY },
+		{ nfserr_dquot, -EDQUOT },
+		{ nfserr_stale, -ESTALE },
+		{ nfserr_jukebox, -ETIMEDOUT },
+		{ nfserr_jukebox, -ERESTARTSYS },
+		{ nfserr_jukebox, -EAGAIN },
+		{ nfserr_jukebox, -EWOULDBLOCK },
+		{ nfserr_jukebox, -ENOMEM },
+		{ nfserr_io, -ETXTBSY },
+		{ nfserr_notsupp, -EOPNOTSUPP },
+		{ nfserr_toosmall, -ETOOSMALL },
+		{ nfserr_serverfault, -ESERVERFAULT },
+		{ nfserr_serverfault, -ENFILE },
+		{ nfserr_io, -EREMOTEIO },
+		{ nfserr_stale, -EOPENSTALE },
+		{ nfserr_io, -EUCLEAN },
+		{ nfserr_perm, -ENOKEY },
+		{ nfserr_no_grace, -ENOGRACE},
+	};
+	int	i;
+
+	for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) {
+		if (nfs_errtbl[i].syserr == errno)
+			return nfs_errtbl[i].nfserr;
+	}
+	WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno);
+	return nfserr_io;
+}
+
 /* 
  * Called from nfsd_lookup and encode_dirent. Check if we have crossed 
  * a mount point.
@@ -1085,7 +1148,7 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	__be32 err;
 
 	trace_nfsd_read_start(rqstp, fhp, offset, *count);
-	err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf);
+	err = nfsd_file_acquire_gc(rqstp, fhp, NFSD_MAY_READ, &nf);
 	if (err)
 		return err;
 
@@ -1117,7 +1180,7 @@ nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
 
 	trace_nfsd_write_start(rqstp, fhp, offset, *cnt);
 
-	err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_WRITE, &nf);
+	err = nfsd_file_acquire_gc(rqstp, fhp, NFSD_MAY_WRITE, &nf);
 	if (err)
 		goto out;
 
@@ -1133,6 +1196,7 @@ out:
  * nfsd_commit - Commit pending writes to stable storage
  * @rqstp: RPC request being processed
  * @fhp: NFS filehandle
+ * @nf: target file
  * @offset: raw offset from beginning of file
  * @count: raw count of bytes to sync
  * @verf: filled in with the server's current write verifier
@@ -1149,19 +1213,13 @@ out:
  *   An nfsstat value in network byte order.
  */
 __be32
-nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset,
+nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf,
-	    u32 count, __be32 *verf)
+	    u64 offset, u32 count, __be32 *verf)
 {
+	__be32			err = nfs_ok;
 	u64			maxbytes;
 	loff_t			start, end;
 	struct nfsd_net		*nn;
-	struct nfsd_file	*nf;
-	__be32			err;
-
-	err = nfsd_file_acquire(rqstp, fhp,
-			NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf);
-	if (err)
-		goto out;
 
 	/*
 	 * Convert the client-provided (offset, count) range to a
@@ -1202,8 +1260,6 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset,
 	} else
 		nfsd_copy_write_verifier(verf, nn);
 
-	nfsd_file_put(nf);
-out:
 	return err;
 }
 
@@ -1305,7 +1361,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		iap->ia_mode &= ~current_umask();
 
 	err = 0;
-	host_err = 0;
 	switch (type) {
 	case S_IFREG:
 		host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true);

fs/nfsd/vfs.h

@@ -60,6 +60,7 @@ static inline void nfsd_attrs_free(struct nfsd_attrs *attrs)
 	posix_acl_release(attrs->na_dpacl);
 }
 
+__be32		nfserrno (int errno);
 int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 		                struct svc_export **expp);
 __be32		nfsd_lookup(struct svc_rqst *, struct svc_fh *,
@@ -88,7 +89,8 @@ __be32		nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
 __be32		nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct svc_fh *resfhp, struct nfsd_attrs *iap);
 __be32		nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp,
-				u64 offset, u32 count, __be32 *verf);
+				struct nfsd_file *nf, u64 offset, u32 count,
+				__be32 *verf);
 #ifdef CONFIG_NFSD_V4
 __be32		nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			    char *name, void **bufp, int *lenp);

fs/nfsd/xdr4.h

@@ -896,5 +896,10 @@ struct nfsd4_operation {
 			union nfsd4_op_u *);
 };
 
+struct nfsd4_cb_recall_any {
+	struct nfsd4_callback	ra_cb;
+	u32			ra_keep;
+	u32			ra_bmval[1];
+};
 
 #endif

fs/nfsd/xdr4cb.h

@@ -48,3 +48,9 @@
 #define NFS4_dec_cb_offload_sz		(cb_compound_dec_hdr_sz  +      \
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
+#define NFS4_enc_cb_recall_any_sz	(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + 1 + 1)
+#define NFS4_dec_cb_recall_any_sz	(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)

include/linux/nfs4.h

@@ -732,4 +732,17 @@ enum nfs4_setxattr_options {
 	SETXATTR4_CREATE	= 1,
 	SETXATTR4_REPLACE	= 2,
 };
+
+enum {
+	RCA4_TYPE_MASK_RDATA_DLG	= 0,
+	RCA4_TYPE_MASK_WDATA_DLG	= 1,
+	RCA4_TYPE_MASK_DIR_DLG		= 2,
+	RCA4_TYPE_MASK_FILE_LAYOUT	= 3,
+	RCA4_TYPE_MASK_BLK_LAYOUT	= 4,
+	RCA4_TYPE_MASK_OBJ_LAYOUT_MIN	= 8,
+	RCA4_TYPE_MASK_OBJ_LAYOUT_MAX	= 9,
+	RCA4_TYPE_MASK_OTHER_LAYOUT_MIN	= 12,
+	RCA4_TYPE_MASK_OTHER_LAYOUT_MAX	= 15,
+};
+
 #endif

include/linux/sunrpc/svc.h

@@ -220,13 +220,6 @@ static inline __be32 svc_getu32(struct kvec *iov)
 	return val;
 }
 
-static inline void svc_ungetu32(struct kvec *iov)
-{
-	__be32 *vp = (__be32 *)iov->iov_base;
-	iov->iov_base = (void *)(vp - 1);
-	iov->iov_len += sizeof(*vp);
-}
-
 static inline void svc_putu32(struct kvec *iov, __be32 val)
 {
 	__be32 *vp = iov->iov_base + iov->iov_len;
@@ -311,7 +304,6 @@ struct svc_rqst {
 	struct auth_domain *	rq_gssclient;	/* "gss/"-style peer info */
 	struct svc_cacherep *	rq_cacherep;	/* cache info */
 	struct task_struct	*rq_task;	/* service thread */
-	spinlock_t		rq_lock;	/* per-request lock */
 	struct net		*rq_bc_net;	/* pointer to backchannel's
 						 * net namespace
 						 */

include/trace/events/rpcgss.h

@@ -13,7 +13,7 @@
 
 #include <linux/tracepoint.h>
 
-#include <trace/events/sunrpc_base.h>
+#include <trace/misc/sunrpc.h>
 
 /**
  ** GSS-API related trace events

include/trace/events/rpcrdma.h

@@ -15,8 +15,8 @@
 #include <linux/tracepoint.h>
 #include <rdma/ib_cm.h>
 
-#include <trace/events/rdma.h>
+#include <trace/misc/rdma.h>
-#include <trace/events/sunrpc_base.h>
+#include <trace/misc/sunrpc.h>
 
 /**
  ** Event classes

include/trace/events/sunrpc.h

@@ -14,7 +14,7 @@
 #include <linux/net.h>
 #include <linux/tracepoint.h>
 
-#include <trace/events/sunrpc_base.h>
+#include <trace/misc/sunrpc.h>
 
 TRACE_DEFINE_ENUM(SOCK_STREAM);
 TRACE_DEFINE_ENUM(SOCK_DGRAM);
@@ -1666,11 +1666,13 @@ TRACE_DEFINE_ENUM(SVC_COMPLETE);
 #define SVC_RQST_ENDPOINT_VARARGS \
 		__entry->xid, __get_sockaddr(server), __get_sockaddr(client)
 
-TRACE_EVENT(svc_authenticate,
+TRACE_EVENT_CONDITION(svc_authenticate,
 	TP_PROTO(const struct svc_rqst *rqst, int auth_res),
 
 	TP_ARGS(rqst, auth_res),
 
+	TP_CONDITION(auth_res != SVC_OK && auth_res != SVC_COMPLETE),
+
 	TP_STRUCT__entry(
 		SVC_RQST_ENDPOINT_FIELDS(rqst)
 

include/trace/misc/nfs.h

@@ -360,6 +360,18 @@ TRACE_DEFINE_ENUM(IOMODE_ANY);
 		{ IOMODE_RW,			"RW" }, \
 		{ IOMODE_ANY,			"ANY" })
 
+#define show_rca_mask(x) \
+	__print_flags(x, "|", \
+		{ BIT(RCA4_TYPE_MASK_RDATA_DLG),	"RDATA_DLG" }, \
+		{ BIT(RCA4_TYPE_MASK_WDATA_DLG),	"WDATA_DLG" }, \
+		{ BIT(RCA4_TYPE_MASK_DIR_DLG),		"DIR_DLG" }, \
+		{ BIT(RCA4_TYPE_MASK_FILE_LAYOUT),	"FILE_LAYOUT" }, \
+		{ BIT(RCA4_TYPE_MASK_BLK_LAYOUT),	"BLK_LAYOUT" }, \
+		{ BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MIN),	"OBJ_LAYOUT_MIN" }, \
+		{ BIT(RCA4_TYPE_MASK_OBJ_LAYOUT_MAX),	"OBJ_LAYOUT_MAX" }, \
+		{ BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MIN),	"OTHER_LAYOUT_MIN" }, \
+		{ BIT(RCA4_TYPE_MASK_OTHER_LAYOUT_MAX),	"OTHER_LAYOUT_MAX" })
+
 #define show_nfs4_seq4_status(x) \
 	__print_flags(x, "|", \
 		{ SEQ4_STATUS_CB_PATH_DOWN,		"CB_PATH_DOWN" }, \

net/sunrpc/auth_gss/svcauth_gss.c

@@ -49,11 +49,36 @@
 #include <linux/sunrpc/svcauth.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/cache.h>
+#include <linux/sunrpc/gss_krb5.h>
 
 #include <trace/events/rpcgss.h>
 
 #include "gss_rpc_upcall.h"
 
+/*
+ * Unfortunately there isn't a maximum checksum size exported via the
+ * GSS API. Manufacture one based on GSS mechanisms supported by this
+ * implementation.
+ */
+#define GSS_MAX_CKSUMSIZE (GSS_KRB5_TOK_HDR_LEN + GSS_KRB5_MAX_CKSUM_LEN)
+
+/*
+ * This value may be increased in the future to accommodate other
+ * usage of the scratch buffer.
+ */
+#define GSS_SCRATCH_SIZE GSS_MAX_CKSUMSIZE
+
+struct gss_svc_data {
+	/* decoded gss client cred: */
+	struct rpc_gss_wire_cred	clcred;
+	/* save a pointer to the beginning of the encoded verifier,
+	 * for use in encryption/checksumming in svcauth_gss_release: */
+	__be32				*verf_start;
+	struct rsc			*rsci;
+
+	/* for temporary results */
+	u8				gsd_scratch[GSS_SCRATCH_SIZE];
+};
 
 /* The rpcsec_init cache is used for mapping RPCSEC_GSS_{,CONT_}INIT requests
  * into replies.
@@ -887,13 +912,11 @@ read_u32_from_xdr_buf(struct xdr_buf *buf, int base, u32 *obj)
 static int
 unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx)
 {
+	struct gss_svc_data *gsd = rqstp->rq_auth_data;
 	u32 integ_len, rseqno, maj_stat;
-	int stat = -EINVAL;
 	struct xdr_netobj mic;
 	struct xdr_buf integ_buf;
 
-	mic.data = NULL;
-
 	/* NFS READ normally uses splice to send data in-place. However
 	 * the data in cache can change after the reply's MIC is computed
 	 * but before the RPC reply is sent. To prevent the client from
@@ -917,11 +940,9 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g
 	/* copy out mic... */
 	if (read_u32_from_xdr_buf(buf, integ_len, &mic.len))
 		goto unwrap_failed;
-	if (mic.len > RPC_MAX_AUTH_SIZE)
+	if (mic.len > sizeof(gsd->gsd_scratch))
-		goto unwrap_failed;
-	mic.data = kmalloc(mic.len, GFP_KERNEL);
-	if (!mic.data)
 		goto unwrap_failed;
+	mic.data = gsd->gsd_scratch;
 	if (read_bytes_from_xdr_buf(buf, integ_len + 4, mic.data, mic.len))
 		goto unwrap_failed;
 	maj_stat = gss_verify_mic(ctx, &integ_buf, &mic);
@@ -932,20 +953,17 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g
 		goto bad_seqno;
 	/* trim off the mic and padding at the end before returning */
 	xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4);
-	stat = 0;
+	return 0;
-out:
-	kfree(mic.data);
-	return stat;
 
 unwrap_failed:
 	trace_rpcgss_svc_unwrap_failed(rqstp);
-	goto out;
+	return -EINVAL;
 bad_seqno:
 	trace_rpcgss_svc_seqno_bad(rqstp, seq, rseqno);
-	goto out;
+	return -EINVAL;
 bad_mic:
 	trace_rpcgss_svc_mic(rqstp, maj_stat);
-	goto out;
+	return -EINVAL;
 }
 
 static inline int
@@ -1023,15 +1041,6 @@ bad_unwrap:
 	return -EINVAL;
 }
 
-struct gss_svc_data {
-	/* decoded gss client cred: */
-	struct rpc_gss_wire_cred	clcred;
-	/* save a pointer to the beginning of the encoded verifier,
-	 * for use in encryption/checksumming in svcauth_gss_release: */
-	__be32				*verf_start;
-	struct rsc			*rsci;
-};
-
 static int
 svcauth_gss_set_client(struct svc_rqst *rqstp)
 {
@@ -1162,18 +1171,23 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp,
 		return res;
 
 	inlen = svc_getnl(argv);
-	if (inlen > (argv->iov_len + rqstp->rq_arg.page_len))
+	if (inlen > (argv->iov_len + rqstp->rq_arg.page_len)) {
+		kfree(in_handle->data);
 		return SVC_DENIED;
+	}
 
 	pages = DIV_ROUND_UP(inlen, PAGE_SIZE);
 	in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL);
-	if (!in_token->pages)
+	if (!in_token->pages) {
+		kfree(in_handle->data);
 		return SVC_DENIED;
+	}
 	in_token->page_base = 0;
 	in_token->page_len = inlen;
 	for (i = 0; i < pages; i++) {
 		in_token->pages[i] = alloc_page(GFP_KERNEL);
 		if (!in_token->pages[i]) {
+			kfree(in_handle->data);
 			gss_free_in_token_pages(in_token);
 			return SVC_DENIED;
 		}

net/sunrpc/svc.c

@@ -638,7 +638,6 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
 		return rqstp;
 
 	__set_bit(RQ_BUSY, &rqstp->rq_flags);
-	spin_lock_init(&rqstp->rq_lock);
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
 
@@ -1281,8 +1280,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 	/* Also give the program a chance to reject this call: */
 	if (auth_res == SVC_OK && progp)
 		auth_res = progp->pg_authenticate(rqstp);
-	if (auth_res != SVC_OK)
+	trace_svc_authenticate(rqstp, auth_res);
-		trace_svc_authenticate(rqstp, auth_res);
 	switch (auth_res) {
 	case SVC_OK:
 		break;

net/sunrpc/xdr.c

@@ -1224,30 +1224,34 @@ EXPORT_SYMBOL(xdr_restrict_buflen);
 /**
  * xdr_write_pages - Insert a list of pages into an XDR buffer for sending
  * @xdr: pointer to xdr_stream
- * @pages: list of pages
+ * @pages: array of pages to insert
- * @base: offset of first byte
+ * @base: starting offset of first data byte in @pages
- * @len: length of data in bytes
+ * @len: number of data bytes in @pages to insert
  *
+ * After the @pages are added, the tail iovec is instantiated pointing to
+ * end of the head buffer, and the stream is set up to encode subsequent
+ * items into the tail.
  */
 void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base,
 		 unsigned int len)
 {
 	struct xdr_buf *buf = xdr->buf;
-	struct kvec *iov = buf->tail;
+	struct kvec *tail = buf->tail;
+
 	buf->pages = pages;
 	buf->page_base = base;
 	buf->page_len = len;
 
-	iov->iov_base = (char *)xdr->p;
+	tail->iov_base = xdr->p;
-	iov->iov_len  = 0;
+	tail->iov_len = 0;
-	xdr->iov = iov;
+	xdr->iov = tail;
 
 	if (len & 3) {
 		unsigned int pad = 4 - (len & 3);
 
 		BUG_ON(xdr->p >= xdr->end);
-		iov->iov_base = (char *)xdr->p + (len & 3);
+		tail->iov_base = (char *)xdr->p + (len & 3);
-		iov->iov_len  += pad;
+		tail->iov_len += pad;
 		len += pad;
 		*xdr->p++ = 0;
 	}