Merge branch 'for-3.18' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Highlights:

   - support the NFSv4.2 SEEK operation (allowing clients to support
     SEEK_HOLE/SEEK_DATA), thanks to Anna.
   - end the grace period early in a number of cases, mitigating a
     long-standing annoyance, thanks to Jeff
   - improve SMP scalability, thanks to Trond"

* 'for-3.18' of git://linux-nfs.org/~bfields/linux: (55 commits)
  nfsd: eliminate "to_delegation" define
  NFSD: Implement SEEK
  NFSD: Add generic v4.2 infrastructure
  svcrdma: advertise the correct max payload
  nfsd: introduce nfsd4_callback_ops
  nfsd: split nfsd4_callback initialization and use
  nfsd: introduce a generic nfsd4_cb
  nfsd: remove nfsd4_callback.cb_op
  nfsd: do not clear rpc_resp in nfsd4_cb_done_sequence
  nfsd: fix nfsd4_cb_recall_done error handling
  nfsd4: clarify how grace period ends
  nfsd4: stop grace_time update at end of grace period
  nfsd: skip subsequent UMH "create" operations after the first one for v4.0 clients
  nfsd: set and test NFSD4_CLIENT_STABLE bit to reduce nfsdcltrack upcalls
  nfsd: serialize nfsdcltrack upcalls for a particular client
  nfsd: pass extra info in env vars to upcalls to allow for early grace period end
  nfsd: add a v4_end_grace file to /proc/fs/nfsd
  lockd: add a /proc/fs/lockd/nlm_end_grace file
  nfsd: reject reclaim request when client has already sent RECLAIM_COMPLETE
  nfsd: remove redundant boot_time parm from grace_done client tracking op
  ...

fs/Kconfig

@@ -233,9 +233,13 @@ if NETWORK_FILESYSTEMS
 source "fs/nfs/Kconfig"
 source "fs/nfsd/Kconfig"
 
+config GRACE_PERIOD
+	tristate
+
 config LOCKD
 	tristate
 	depends on FILE_LOCKING
+	select GRACE_PERIOD
 
 config LOCKD_V4
 	bool
@@ -249,7 +253,7 @@ config NFS_ACL_SUPPORT
 
 config NFS_COMMON
 	bool
-	depends on NFSD || NFS_FS
+	depends on NFSD || NFS_FS || LOCKD
 	default y
 
 source "net/sunrpc/Kconfig"

fs/lockd/Makefile

@@ -5,6 +5,7 @@
 obj-$(CONFIG_LOCKD) += lockd.o
 
 lockd-objs-y := clntlock.o clntproc.o clntxdr.o host.o svc.o svclock.o \
-	        svcshare.o svcproc.o svcsubs.o mon.o xdr.o grace.o
+	        svcshare.o svcproc.o svcsubs.o mon.o xdr.o
 lockd-objs-$(CONFIG_LOCKD_V4) += clnt4xdr.o xdr4.o svc4proc.o
+lockd-objs-$(CONFIG_PROC_FS) += procfs.o
 lockd-objs		      := $(lockd-objs-y)

fs/lockd/netns.h

@@ -11,7 +11,6 @@ struct lockd_net {
 
 	struct delayed_work grace_period_end;
 	struct lock_manager lockd_manager;
-	struct list_head grace_list;
 
 	spinlock_t nsm_clnt_lock;
 	unsigned int nsm_users;

fs/lockd/procfs.c

+/*
+ * Procfs support for lockd
+ *
+ * Copyright (c) 2014 Jeff Layton <jlayton@primarydata.com>
+ */
+
+#include <linux/fs.h>
+#include <linux/proc_fs.h>
+#include <linux/module.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+
+#include "netns.h"
+#include "procfs.h"
+
+/*
+ * We only allow strings that start with 'Y', 'y', or '1'.
+ */
+static ssize_t
+nlm_end_grace_write(struct file *file, const char __user *buf, size_t size,
+		    loff_t *pos)
+{
+	char *data;
+	struct lockd_net *ln = net_generic(current->nsproxy->net_ns,
+					   lockd_net_id);
+
+	if (size < 1)
+		return -EINVAL;
+
+	data = simple_transaction_get(file, buf, size);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	switch(data[0]) {
+	case 'Y':
+	case 'y':
+	case '1':
+		locks_end_grace(&ln->lockd_manager);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return size;
+}
+
+static ssize_t
+nlm_end_grace_read(struct file *file, char __user *buf, size_t size,
+		   loff_t *pos)
+{
+	struct lockd_net *ln = net_generic(current->nsproxy->net_ns,
+					   lockd_net_id);
+	char resp[3];
+
+	resp[0] = list_empty(&ln->lockd_manager.list) ? 'Y' : 'N';
+	resp[1] = '\n';
+	resp[2] = '\0';
+
+	return simple_read_from_buffer(buf, size, pos, resp, sizeof(resp));
+}
+
+static const struct file_operations lockd_end_grace_operations = {
+	.write		= nlm_end_grace_write,
+	.read		= nlm_end_grace_read,
+	.llseek		= default_llseek,
+	.release	= simple_transaction_release,
+	.owner		= THIS_MODULE,
+};
+
+int __init
+lockd_create_procfs(void)
+{
+	struct proc_dir_entry *entry;
+
+	entry = proc_mkdir("fs/lockd", NULL);
+	if (!entry)
+		return -ENOMEM;
+	entry = proc_create("nlm_end_grace", S_IRUGO|S_IWUSR, entry,
+				 &lockd_end_grace_operations);
+	if (!entry) {
+		remove_proc_entry("fs/lockd", NULL);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void __exit
+lockd_remove_procfs(void)
+{
+	remove_proc_entry("fs/lockd/nlm_end_grace", NULL);
+	remove_proc_entry("fs/lockd", NULL);
+}

fs/lockd/procfs.h

+/*
+ * Procfs support for lockd
+ *
+ * Copyright (c) 2014 Jeff Layton <jlayton@primarydata.com>
+ */
+#ifndef _LOCKD_PROCFS_H
+#define _LOCKD_PROCFS_H
+
+#include <linux/kconfig.h>
+
+#if IS_ENABLED(CONFIG_PROC_FS)
+int lockd_create_procfs(void);
+void lockd_remove_procfs(void);
+#else
+static inline int
+lockd_create_procfs(void)
+{
+	return 0;
+}
+
+static inline void
+lockd_remove_procfs(void)
+{
+	return;
+}
+#endif /* IS_ENABLED(CONFIG_PROC_FS) */
+
+#endif /* _LOCKD_PROCFS_H */

fs/lockd/svc.c

@@ -36,6 +36,7 @@
 #include <linux/nfs.h>
 
 #include "netns.h"
+#include "procfs.h"
 
 #define NLMDBG_FACILITY		NLMDBG_SVC
 #define LOCKD_BUFSIZE		(1024 + NLMSVC_XDRSIZE)
@@ -304,13 +305,16 @@ static int lockd_start_svc(struct svc_serv *serv)
 	svc_sock_update_bufs(serv);
 	serv->sv_maxconn = nlm_max_connections;
 
-	nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, "%s", serv->sv_name);
+	nlmsvc_task = kthread_create(lockd, nlmsvc_rqst, "%s", serv->sv_name);
 	if (IS_ERR(nlmsvc_task)) {
 		error = PTR_ERR(nlmsvc_task);
 		printk(KERN_WARNING
 			"lockd_up: kthread_run failed, error=%d\n", error);
 		goto out_task;
 	}
+	nlmsvc_rqst->rq_task = nlmsvc_task;
+	wake_up_process(nlmsvc_task);
+
 	dprintk("lockd_up: service started\n");
 	return 0;
 
@@ -581,7 +585,7 @@ static int lockd_init_net(struct net *net)
 	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
 	INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
-	INIT_LIST_HEAD(&ln->grace_list);
+	INIT_LIST_HEAD(&ln->lockd_manager.list);
 	spin_lock_init(&ln->nsm_clnt_lock);
 	return 0;
 }
@@ -615,8 +619,15 @@ static int __init init_nlm(void)
 	err = register_pernet_subsys(&lockd_net_ops);
 	if (err)
 		goto err_pernet;
+
+	err = lockd_create_procfs();
+	if (err)
+		goto err_procfs;
+
 	return 0;
 
+err_procfs:
+	unregister_pernet_subsys(&lockd_net_ops);
 err_pernet:
 #ifdef CONFIG_SYSCTL
 	unregister_sysctl_table(nlm_sysctl_table);
@@ -629,6 +640,7 @@ static void __exit exit_nlm(void)
 {
 	/* FIXME: delete all NLM clients */
 	nlm_shutdown_hosts();
+	lockd_remove_procfs();
 	unregister_pernet_subsys(&lockd_net_ops);
 #ifdef CONFIG_SYSCTL
 	unregister_sysctl_table(nlm_sysctl_table);

fs/nfs/callback.c

@@ -235,7 +235,7 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
 
 	cb_info->serv = serv;
 	cb_info->rqst = rqstp;
-	cb_info->task = kthread_run(callback_svc, cb_info->rqst,
+	cb_info->task = kthread_create(callback_svc, cb_info->rqst,
 				    "nfsv4.%u-svc", minorversion);
 	if (IS_ERR(cb_info->task)) {
 		ret = PTR_ERR(cb_info->task);
@@ -244,6 +244,8 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
 		cb_info->task = NULL;
 		return ret;
 	}
+	rqstp->rq_task = cb_info->task;
+	wake_up_process(cb_info->task);
 	dprintk("nfs_callback_up: service started\n");
 	return 0;
 }

fs/nfs_common/Makefile

@@ -3,5 +3,6 @@
 #
 
 obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
-
 nfs_acl-objs := nfsacl.o
+
+obj-$(CONFIG_GRACE_PERIOD) += grace.o

fs/lockd/grace.c → fs/nfs_common/grace.c

 /*
  * Common code for control of lockd and nfsv4 grace periods.
+ *
+ * Transplanted from lockd code
  */
 
 #include <linux/module.h>
-#include <linux/lockd/bind.h>
 #include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <linux/fs.h>
 
-#include "netns.h"
-
+static int grace_net_id;
 static DEFINE_SPINLOCK(grace_lock);
 
 /**
  * locks_start_grace
+ * @net: net namespace that this lock manager belongs to
  * @lm: who this grace period is for
  *
  * A grace period is a period during which locks should not be given
@@ -21,18 +24,20 @@ static DEFINE_SPINLOCK(grace_lock);
  *
  * This function is called to start a grace period.
  */
-void locks_start_grace(struct net *net, struct lock_manager *lm)
+void
+locks_start_grace(struct net *net, struct lock_manager *lm)
 {
-	struct lockd_net *ln = net_generic(net, lockd_net_id);
+	struct list_head *grace_list = net_generic(net, grace_net_id);
 
 	spin_lock(&grace_lock);
-	list_add(&lm->list, &ln->grace_list);
+	list_add(&lm->list, grace_list);
 	spin_unlock(&grace_lock);
 }
 EXPORT_SYMBOL_GPL(locks_start_grace);
 
 /**
  * locks_end_grace
+ * @net: net namespace that this lock manager belongs to
  * @lm: who this grace period is for
  *
  * Call this function to state that the given lock manager is ready to
@@ -41,7 +46,8 @@ EXPORT_SYMBOL_GPL(locks_start_grace);
  * Note that callers count on it being safe to call this more than once,
  * and the second call should be a no-op.
  */
-void locks_end_grace(struct lock_manager *lm)
+void
+locks_end_grace(struct lock_manager *lm)
 {
 	spin_lock(&grace_lock);
 	list_del_init(&lm->list);
@@ -56,10 +62,52 @@ EXPORT_SYMBOL_GPL(locks_end_grace);
  * to answer ordinary lock requests, and when they should accept only
  * lock reclaims.
  */
-int locks_in_grace(struct net *net)
+int
+locks_in_grace(struct net *net)
 {
-	struct lockd_net *ln = net_generic(net, lockd_net_id);
+	struct list_head *grace_list = net_generic(net, grace_net_id);
 
-	return !list_empty(&ln->grace_list);
+	return !list_empty(grace_list);
 }
 EXPORT_SYMBOL_GPL(locks_in_grace);
+
+static int __net_init
+grace_init_net(struct net *net)
+{
+	struct list_head *grace_list = net_generic(net, grace_net_id);
+
+	INIT_LIST_HEAD(grace_list);
+	return 0;
+}
+
+static void __net_exit
+grace_exit_net(struct net *net)
+{
+	struct list_head *grace_list = net_generic(net, grace_net_id);
+
+	BUG_ON(!list_empty(grace_list));
+}
+
+static struct pernet_operations grace_net_ops = {
+	.init = grace_init_net,
+	.exit = grace_exit_net,
+	.id   = &grace_net_id,
+	.size = sizeof(struct list_head),
+};
+
+static int __init
+init_grace(void)
+{
+	return register_pernet_subsys(&grace_net_ops);
+}
+
+static void __exit
+exit_grace(void)
+{
+	unregister_pernet_subsys(&grace_net_ops);
+}
+
+MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>");
+MODULE_LICENSE("GPL");
+module_init(init_grace)
+module_exit(exit_grace)

fs/nfsd/Kconfig

@@ -71,6 +71,7 @@ config NFSD_V4
 	select FS_POSIX_ACL
 	select SUNRPC_GSS
 	select CRYPTO
+	select GRACE_PERIOD
 	help
 	  This option enables support in your system's NFS server for
 	  version 4 of the NFS protocol (RFC 3530).
@@ -94,9 +95,6 @@ config NFSD_V4_SECURITY_LABEL
 	If you do not wish to enable fine-grained security labels SELinux or
 	Smack policies on NFSv4 files, say N.
 
-	WARNING: there is still a chance of backwards-incompatible protocol changes.
-	For now we recommend "Y" only for developers and testers.
-
 config NFSD_FAULT_INJECTION
 	bool "NFS server manual fault injection"
 	depends on NFSD_V4 && DEBUG_KERNEL

fs/nfsd/cache.h

@@ -18,7 +18,6 @@
  * is much larger than a sockaddr_in6.
  */
 struct svc_cacherep {
-	struct hlist_node	c_hash;
 	struct list_head	c_lru;
 
 	unsigned char		c_state,	/* unused, inprog, done */

fs/nfsd/export.c

@@ -1145,6 +1145,7 @@ static struct flags {
 	{ NFSEXP_ALLSQUASH, {"all_squash", ""}},
 	{ NFSEXP_ASYNC, {"async", "sync"}},
 	{ NFSEXP_GATHERED_WRITES, {"wdelay", "no_wdelay"}},
+	{ NFSEXP_NOREADDIRPLUS, {"nordirplus", ""}},
 	{ NFSEXP_NOHIDE, {"nohide", ""}},
 	{ NFSEXP_CROSSMOUNT, {"crossmnt", ""}},
 	{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},

fs/nfsd/nfs3proc.c

@@ -223,11 +223,6 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
 	newfhp = fh_init(&resp->fh, NFS3_FHSIZE);
 	attr   = &argp->attrs;
 
-	/* Get the directory inode */
-	nfserr = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_CREATE);
-	if (nfserr)
-		RETURN_STATUS(nfserr);
-
 	/* Unfudge the mode bits */
 	attr->ia_mode &= ~S_IFMT;
 	if (!(attr->ia_valid & ATTR_MODE)) { 
@@ -471,6 +466,14 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 	resp->buflen = resp->count;
 	resp->rqstp = rqstp;
 	offset = argp->cookie;
+
+	nfserr = fh_verify(rqstp, &resp->fh, S_IFDIR, NFSD_MAY_NOP);
+	if (nfserr)
+		RETURN_STATUS(nfserr);
+
+	if (resp->fh.fh_export->ex_flags & NFSEXP_NOREADDIRPLUS)
+		RETURN_STATUS(nfserr_notsupp);
+
 	nfserr = nfsd_readdir(rqstp, &resp->fh,
 				     &offset,
 				     &resp->common,

fs/nfsd/nfs4callback.c

@@ -49,12 +49,6 @@ static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
 
 /* Index of predefined Linux callback client operations */
 
-enum {
-	NFSPROC4_CLNT_CB_NULL = 0,
-	NFSPROC4_CLNT_CB_RECALL,
-	NFSPROC4_CLNT_CB_SEQUENCE,
-};
-
 struct nfs4_cb_compound_hdr {
 	/* args */
 	u32		ident;	/* minorversion 0 only */
@@ -494,7 +488,7 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
 static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
 				   const struct nfsd4_callback *cb)
 {
-	const struct nfs4_delegation *args = cb->cb_op;
+	const struct nfs4_delegation *dp = cb_to_delegation(cb);
 	struct nfs4_cb_compound_hdr hdr = {
 		.ident = cb->cb_clp->cl_cb_ident,
 		.minorversion = cb->cb_minorversion,
@@ -502,7 +496,7 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
 
 	encode_cb_compound4args(xdr, &hdr);
 	encode_cb_sequence4args(xdr, cb, &hdr);
-	encode_cb_recall4args(xdr, args, &hdr);
+	encode_cb_recall4args(xdr, dp, &hdr);
 	encode_cb_nops(&hdr);
 }
 
@@ -746,27 +740,6 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
 
 static struct workqueue_struct *callback_wq;
 
-static void run_nfsd4_cb(struct nfsd4_callback *cb)
-{
-	queue_work(callback_wq, &cb->cb_work);
-}
-
-static void do_probe_callback(struct nfs4_client *clp)
-{
-	struct nfsd4_callback *cb = &clp->cl_cb_null;
-
-	cb->cb_op = NULL;
-	cb->cb_clp = clp;
-
-	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL];
-	cb->cb_msg.rpc_argp = NULL;
-	cb->cb_msg.rpc_resp = NULL;
-
-	cb->cb_ops = &nfsd4_cb_probe_ops;
-
-	run_nfsd4_cb(cb);
-}
-
 /*
  * Poke the callback thread to process any updates to the callback
  * parameters, and send a null probe.
@@ -775,7 +748,7 @@ void nfsd4_probe_callback(struct nfs4_client *clp)
 {
 	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
 	set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags);
-	do_probe_callback(clp);
+	nfsd4_run_cb(&clp->cl_cb_null);
 }
 
 void nfsd4_probe_callback_sync(struct nfs4_client *clp)
@@ -847,23 +820,9 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
 		rpc_wake_up_next(&clp->cl_cb_waitq);
 		dprintk("%s: freed slot, new seqid=%d\n", __func__,
 			clp->cl_cb_session->se_cb_seq_nr);
-
-		/* We're done looking into the sequence information */
-		task->tk_msg.rpc_resp = NULL;
 	}
-}
-
-
-static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
-{
-	struct nfsd4_callback *cb = calldata;
-	struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
-	struct nfs4_client *clp = cb->cb_clp;
-	struct rpc_clnt *current_rpc_client = clp->cl_cb_client;
-
-	nfsd4_cb_done(task, calldata);
 
-	if (current_rpc_client != task->tk_client) {
+	if (clp->cl_cb_client != task->tk_client) {
 		/* We're shutting down or changing cl_cb_client; leave
 		 * it to nfsd4_process_cb_update to restart the call if
 		 * necessary. */
@@ -872,47 +831,42 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata)
 
 	if (cb->cb_done)
 		return;
-	switch (task->tk_status) {
+
+	switch (cb->cb_ops->done(cb, task)) {
 	case 0:
-		cb->cb_done = true;
+		task->tk_status = 0;
+		rpc_restart_call_prepare(task);
 		return;
-	case -EBADHANDLE:
-	case -NFS4ERR_BAD_STATEID:
-		/* Race: client probably got cb_recall
-		 * before open reply granting delegation */
+	case 1:
 		break;
-	default:
+	case -1:
 		/* Network partition? */
 		nfsd4_mark_cb_down(clp, task->tk_status);
+		break;
+	default:
+		BUG();
 	}
-	if (dp->dl_retries--) {
-		rpc_delay(task, 2*HZ);
-		task->tk_status = 0;
-		rpc_restart_call_prepare(task);
-		return;
-	}
-	nfsd4_mark_cb_down(clp, task->tk_status);
 	cb->cb_done = true;
 }
 
-static void nfsd4_cb_recall_release(void *calldata)
+static void nfsd4_cb_release(void *calldata)
 {
 	struct nfsd4_callback *cb = calldata;
 	struct nfs4_client *clp = cb->cb_clp;
-	struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall);
 
 	if (cb->cb_done) {
 		spin_lock(&clp->cl_lock);
 		list_del(&cb->cb_per_client);
 		spin_unlock(&clp->cl_lock);
-		nfs4_put_stid(&dp->dl_stid);
+
+		cb->cb_ops->release(cb);
 	}
 }
 
-static const struct rpc_call_ops nfsd4_cb_recall_ops = {
+static const struct rpc_call_ops nfsd4_cb_ops = {
 	.rpc_call_prepare = nfsd4_cb_prepare,
-	.rpc_call_done = nfsd4_cb_recall_done,
-	.rpc_release = nfsd4_cb_recall_release,
+	.rpc_call_done = nfsd4_cb_done,
+	.rpc_release = nfsd4_cb_release,
 };
 
 int nfsd4_create_callback_queue(void)
@@ -937,16 +891,10 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
 	 * instead, nfsd4_run_cb_null() will detect the killed
 	 * client, destroy the rpc client, and stop:
 	 */
-	do_probe_callback(clp);
+	nfsd4_run_cb(&clp->cl_cb_null);
 	flush_workqueue(callback_wq);
 }
 
-static void nfsd4_release_cb(struct nfsd4_callback *cb)
-{
-	if (cb->cb_ops->rpc_release)
-		cb->cb_ops->rpc_release(cb);
-}
-
 /* requires cl_lock: */
 static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp)
 {
@@ -1009,63 +957,49 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	}
 	/* Yay, the callback channel's back! Restart any callbacks: */
 	list_for_each_entry(cb, &clp->cl_callbacks, cb_per_client)
-		run_nfsd4_cb(cb);
+		queue_work(callback_wq, &cb->cb_work);
 }
 
 static void
-nfsd4_run_callback_rpc(struct nfsd4_callback *cb)
+nfsd4_run_cb_work(struct work_struct *work)
 {
+	struct nfsd4_callback *cb =
+		container_of(work, struct nfsd4_callback, cb_work);
 	struct nfs4_client *clp = cb->cb_clp;
 	struct rpc_clnt *clnt;
 
+	if (cb->cb_ops && cb->cb_ops->prepare)
+		cb->cb_ops->prepare(cb);
+
 	if (clp->cl_flags & NFSD4_CLIENT_CB_FLAG_MASK)
 		nfsd4_process_cb_update(cb);
 
 	clnt = clp->cl_cb_client;
 	if (!clnt) {
 		/* Callback channel broken, or client killed; give up: */
-		nfsd4_release_cb(cb);
+		if (cb->cb_ops && cb->cb_ops->release)
+			cb->cb_ops->release(cb);
 		return;
 	}
 	cb->cb_msg.rpc_cred = clp->cl_cb_cred;
 	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
-			cb->cb_ops, cb);
+			cb->cb_ops ? &nfsd4_cb_ops : &nfsd4_cb_probe_ops, cb);
 }
 
-void
-nfsd4_run_cb_null(struct work_struct *w)
+void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
+		struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op)
 {
-	struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
-							cb_work);
-	nfsd4_run_callback_rpc(cb);
-}
-
-void
-nfsd4_run_cb_recall(struct work_struct *w)
-{
-	struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
-							cb_work);
-
-	nfsd4_prepare_cb_recall(cb->cb_op);
-	nfsd4_run_callback_rpc(cb);
-}
-
-void nfsd4_cb_recall(struct nfs4_delegation *dp)
-{
-	struct nfsd4_callback *cb = &dp->dl_recall;
-	struct nfs4_client *clp = dp->dl_stid.sc_client;
-
-	dp->dl_retries = 1;
-	cb->cb_op = dp;
 	cb->cb_clp = clp;
-	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL];
+	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[op];
 	cb->cb_msg.rpc_argp = cb;
 	cb->cb_msg.rpc_resp = cb;
-
-	cb->cb_ops = &nfsd4_cb_recall_ops;
-
+	cb->cb_ops = ops;
+	INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
 	INIT_LIST_HEAD(&cb->cb_per_client);
 	cb->cb_done = true;
+}
 
-	run_nfsd4_cb(&dp->dl_recall);
+void nfsd4_run_cb(struct nfsd4_callback *cb)
+{
+	queue_work(callback_wq, &cb->cb_work);
 }

fs/nfsd/nfs4idmap.c

@@ -215,7 +215,8 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
 	memset(&ent, 0, sizeof(ent));
 
 	/* Authentication name */
-	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
 		goto out;
 	memcpy(ent.authname, buf1, sizeof(ent.authname));
 
@@ -245,12 +246,10 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
 	/* Name */
 	error = -EINVAL;
 	len = qword_get(&buf, buf1, PAGE_SIZE);
-	if (len < 0)
+	if (len < 0 || len >= IDMAP_NAMESZ)
 		goto out;
 	if (len == 0)
 		set_bit(CACHE_NEGATIVE, &ent.h.flags);
-	else if (len >= IDMAP_NAMESZ)
-		goto out;
 	else
 		memcpy(ent.name, buf1, sizeof(ent.name));
 	error = -ENOMEM;
@@ -259,15 +258,12 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
 		goto out;
 
 	cache_put(&res->h, cd);
-
 	error = 0;
 out:
 	kfree(buf1);
-
 	return error;
 }
 
-
 static struct ent *
 idtoname_lookup(struct cache_detail *cd, struct ent *item)
 {
@@ -368,7 +364,7 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
 {
 	struct ent ent, *res;
 	char *buf1;
-	int error = -EINVAL;
+	int len, error = -EINVAL;
 
 	if (buf[buflen - 1] != '\n')
 		return (-EINVAL);
@@ -381,7 +377,8 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
 	memset(&ent, 0, sizeof(ent));
 
 	/* Authentication name */
-	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
 		goto out;
 	memcpy(ent.authname, buf1, sizeof(ent.authname));
 
@@ -392,8 +389,8 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
 		IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
 
 	/* Name */
-	error = qword_get(&buf, buf1, PAGE_SIZE);
-	if (error <= 0 || error >= IDMAP_NAMESZ)
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
 		goto out;
 	memcpy(ent.name, buf1, sizeof(ent.name));
 
@@ -421,7 +418,6 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
 	error = 0;
 out:
 	kfree(buf1);
-
 	return (error);
 }
 

fs/nfsd/nfs4proc.c

@@ -1013,6 +1013,49 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
+static __be32
+nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		struct nfsd4_seek *seek)
+{
+	int whence;
+	__be32 status;
+	struct file *file;
+
+	status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
+					    &seek->seek_stateid,
+					    RD_STATE, &file);
+	if (status) {
+		dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n");
+		return status;
+	}
+
+	switch (seek->seek_whence) {
+	case NFS4_CONTENT_DATA:
+		whence = SEEK_DATA;
+		break;
+	case NFS4_CONTENT_HOLE:
+		whence = SEEK_HOLE;
+		break;
+	default:
+		status = nfserr_union_notsupp;
+		goto out;
+	}
+
+	/*
+	 * Note:  This call does change file->f_pos, but nothing in NFSD
+	 *        should ever file->f_pos.
+	 */
+	seek->seek_pos = vfs_llseek(file, seek->seek_offset, whence);
+	if (seek->seek_pos < 0)
+		status = nfserrno(seek->seek_pos);
+	else if (seek->seek_pos >= i_size_read(file_inode(file)))
+		seek->seek_eof = true;
+
+out:
+	fput(file);
+	return status;
+}
+
 /* This routine never returns NFS_OK!  If there are no other errors, it
  * will return NFSERR_SAME or NFSERR_NOT_SAME depending on whether the
  * attributes matched.  VERIFY is implemented by mapping NFSERR_SAME
@@ -1881,6 +1924,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+
+	/* NFSv4.2 operations */
+	[OP_SEEK] = {
+		.op_func = (nfsd4op_func)nfsd4_seek,
+		.op_name = "OP_SEEK",
+	},
 };
 
 int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)

fs/nfsd/nfs4recover.c

@@ -58,7 +58,7 @@ struct nfsd4_client_tracking_ops {
 	void (*create)(struct nfs4_client *);
 	void (*remove)(struct nfs4_client *);
 	int (*check)(struct nfs4_client *);
-	void (*grace_done)(struct nfsd_net *, time_t);
+	void (*grace_done)(struct nfsd_net *);
 };
 
 /* Globals */
@@ -188,7 +188,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 
 	status = mnt_want_write_file(nn->rec_file);
 	if (status)
-		return;
+		goto out_creds;
 
 	dir = nn->rec_file->f_path.dentry;
 	/* lock the parent */
@@ -228,6 +228,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 				user_recovery_dirname);
 	}
 	mnt_drop_write_file(nn->rec_file);
+out_creds:
 	nfs4_reset_creds(original_cred);
 }
 
@@ -392,7 +393,7 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
 }
 
 static void
-nfsd4_recdir_purge_old(struct nfsd_net *nn, time_t boot_time)
+nfsd4_recdir_purge_old(struct nfsd_net *nn)
 {
 	int status;
 
@@ -479,6 +480,16 @@ nfsd4_init_recdir(struct net *net)
 	return status;
 }
 
+static void
+nfsd4_shutdown_recdir(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (!nn->rec_file)
+		return;
+	fput(nn->rec_file);
+	nn->rec_file = NULL;
+}
 
 static int
 nfs4_legacy_state_init(struct net *net)
@@ -512,10 +523,13 @@ nfsd4_load_reboot_recovery_data(struct net *net)
 	int status;
 
 	status = nfsd4_init_recdir(net);
-	if (!status)
-		status = nfsd4_recdir_load(net);
 	if (status)
-		printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
+		return status;
+
+	status = nfsd4_recdir_load(net);
+	if (status)
+		nfsd4_shutdown_recdir(net);
+
 	return status;
 }
 
@@ -545,22 +559,13 @@ nfsd4_legacy_tracking_init(struct net *net)
 	return status;
 }
 
-static void
-nfsd4_shutdown_recdir(struct nfsd_net *nn)
-{
-	if (!nn->rec_file)
-		return;
-	fput(nn->rec_file);
-	nn->rec_file = NULL;
-}
-
 static void
 nfsd4_legacy_tracking_exit(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	nfs4_release_reclaim(nn);
-	nfsd4_shutdown_recdir(nn);
+	nfsd4_shutdown_recdir(net);
 	nfs4_legacy_state_shutdown(net);
 }
 
@@ -1016,7 +1021,7 @@ nfsd4_cld_check(struct nfs4_client *clp)
 }
 
 static void
-nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time)
+nfsd4_cld_grace_done(struct nfsd_net *nn)
 {
 	int ret;
 	struct cld_upcall *cup;
@@ -1029,7 +1034,7 @@ nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time)
 	}
 
 	cup->cu_msg.cm_cmd = Cld_GraceDone;
-	cup->cu_msg.cm_u.cm_gracetime = (int64_t)boot_time;
+	cup->cu_msg.cm_u.cm_gracetime = (int64_t)nn->boot_time;
 	ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
 	if (!ret)
 		ret = cup->cu_msg.cm_status;
@@ -1062,6 +1067,8 @@ MODULE_PARM_DESC(cltrack_legacy_disable,
 
 #define LEGACY_TOPDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_TOPDIR="
 #define LEGACY_RECDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_RECDIR="
+#define HAS_SESSION_ENV_PREFIX "NFSDCLTRACK_CLIENT_HAS_SESSION="
+#define GRACE_START_ENV_PREFIX "NFSDCLTRACK_GRACE_START="
 
 static char *
 nfsd4_cltrack_legacy_topdir(void)
@@ -1126,10 +1133,60 @@ nfsd4_cltrack_legacy_recdir(const struct xdr_netobj *name)
 	return result;
 }
 
+static char *
+nfsd4_cltrack_client_has_session(struct nfs4_client *clp)
+{
+	int copied;
+	size_t len;
+	char *result;
+
+	/* prefix + Y/N character + terminating NULL */
+	len = strlen(HAS_SESSION_ENV_PREFIX) + 1 + 1;
+
+	result = kmalloc(len, GFP_KERNEL);
+	if (!result)
+		return result;
+
+	copied = snprintf(result, len, HAS_SESSION_ENV_PREFIX "%c",
+				clp->cl_minorversion ? 'Y' : 'N');
+	if (copied >= len) {
+		/* just return nothing if output was truncated */
+		kfree(result);
+		return NULL;
+	}
+
+	return result;
+}
+
+static char *
+nfsd4_cltrack_grace_start(time_t grace_start)
+{
+	int copied;
+	size_t len;
+	char *result;
+
+	/* prefix + max width of int64_t string + terminating NULL */
+	len = strlen(GRACE_START_ENV_PREFIX) + 22 + 1;
+
+	result = kmalloc(len, GFP_KERNEL);
+	if (!result)
+		return result;
+
+	copied = snprintf(result, len, GRACE_START_ENV_PREFIX "%ld",
+				grace_start);
+	if (copied >= len) {
+		/* just return nothing if output was truncated */
+		kfree(result);
+		return NULL;
+	}
+
+	return result;
+}
+
 static int
-nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy)
+nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *env0, char *env1)
 {
-	char *envp[2];
+	char *envp[3];
 	char *argv[4];
 	int ret;
 
@@ -1140,10 +1197,12 @@ nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy)
 
 	dprintk("%s: cmd: %s\n", __func__, cmd);
 	dprintk("%s: arg: %s\n", __func__, arg ? arg : "(null)");
-	dprintk("%s: legacy: %s\n", __func__, legacy ? legacy : "(null)");
+	dprintk("%s: env0: %s\n", __func__, env0 ? env0 : "(null)");
+	dprintk("%s: env1: %s\n", __func__, env1 ? env1 : "(null)");
 
-	envp[0] = legacy;
-	envp[1] = NULL;
+	envp[0] = env0;
+	envp[1] = env1;
+	envp[2] = NULL;
 
 	argv[0] = (char *)cltrack_prog;
 	argv[1] = cmd;
@@ -1187,28 +1246,78 @@ bin_to_hex_dup(const unsigned char *src, int srclen)
 }
 
 static int
-nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net)
+nfsd4_umh_cltrack_init(struct net *net)
 {
+	int ret;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	char *grace_start = nfsd4_cltrack_grace_start(nn->boot_time);
+
 	/* XXX: The usermode helper s not working in container yet. */
 	if (net != &init_net) {
 		WARN(1, KERN_ERR "NFSD: attempt to initialize umh client "
 			"tracking in a container!\n");
 		return -EINVAL;
 	}
-	return nfsd4_umh_cltrack_upcall("init", NULL, NULL);
+
+	ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL);
+	kfree(grace_start);
+	return ret;
+}
+
+static void
+nfsd4_cltrack_upcall_lock(struct nfs4_client *clp)
+{
+	wait_on_bit_lock(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK,
+			 TASK_UNINTERRUPTIBLE);
+}
+
+static void
+nfsd4_cltrack_upcall_unlock(struct nfs4_client *clp)
+{
+	smp_mb__before_atomic();
+	clear_bit(NFSD4_CLIENT_UPCALL_LOCK, &clp->cl_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&clp->cl_flags, NFSD4_CLIENT_UPCALL_LOCK);
 }
 
 static void
 nfsd4_umh_cltrack_create(struct nfs4_client *clp)
 {
-	char *hexid;
+	char *hexid, *has_session, *grace_start;
+	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+	/*
+	 * With v4.0 clients, there's little difference in outcome between a
+	 * create and check operation, and we can end up calling into this
+	 * function multiple times per client (once for each openowner). So,
+	 * for v4.0 clients skip upcalling once the client has been recorded
+	 * on stable storage.
+	 *
+	 * For v4.1+ clients, the outcome of the two operations is different,
+	 * so we must ensure that we upcall for the create operation. v4.1+
+	 * clients call this on RECLAIM_COMPLETE though, so we should only end
+	 * up doing a single create upcall per client.
+	 */
+	if (clp->cl_minorversion == 0 &&
+	    test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
 
 	hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
 	if (!hexid) {
 		dprintk("%s: can't allocate memory for upcall!\n", __func__);
 		return;
 	}
-	nfsd4_umh_cltrack_upcall("create", hexid, NULL);
+
+	has_session = nfsd4_cltrack_client_has_session(clp);
+	grace_start = nfsd4_cltrack_grace_start(nn->boot_time);
+
+	nfsd4_cltrack_upcall_lock(clp);
+	if (!nfsd4_umh_cltrack_upcall("create", hexid, has_session, grace_start))
+		set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	nfsd4_cltrack_upcall_unlock(clp);
+
+	kfree(has_session);
+	kfree(grace_start);
 	kfree(hexid);
 }
 
@@ -1217,12 +1326,21 @@ nfsd4_umh_cltrack_remove(struct nfs4_client *clp)
 {
 	char *hexid;
 
+	if (!test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return;
+
 	hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
 	if (!hexid) {
 		dprintk("%s: can't allocate memory for upcall!\n", __func__);
 		return;
 	}
-	nfsd4_umh_cltrack_upcall("remove", hexid, NULL);
+
+	nfsd4_cltrack_upcall_lock(clp);
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags) &&
+	    nfsd4_umh_cltrack_upcall("remove", hexid, NULL, NULL) == 0)
+		clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	nfsd4_cltrack_upcall_unlock(clp);
+
 	kfree(hexid);
 }
 
@@ -1230,30 +1348,45 @@ static int
 nfsd4_umh_cltrack_check(struct nfs4_client *clp)
 {
 	int ret;
-	char *hexid, *legacy;
+	char *hexid, *has_session, *legacy;
+
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
+		return 0;
 
 	hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len);
 	if (!hexid) {
 		dprintk("%s: can't allocate memory for upcall!\n", __func__);
 		return -ENOMEM;
 	}
+
+	has_session = nfsd4_cltrack_client_has_session(clp);
 	legacy = nfsd4_cltrack_legacy_recdir(&clp->cl_name);
-	ret = nfsd4_umh_cltrack_upcall("check", hexid, legacy);
+
+	nfsd4_cltrack_upcall_lock(clp);
+	if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) {
+		ret = 0;
+	} else {
+		ret = nfsd4_umh_cltrack_upcall("check", hexid, has_session, legacy);
+		if (ret == 0)
+			set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
+	}
+	nfsd4_cltrack_upcall_unlock(clp);
+	kfree(has_session);
 	kfree(legacy);
 	kfree(hexid);
+
 	return ret;
 }
 
 static void
-nfsd4_umh_cltrack_grace_done(struct nfsd_net __attribute__((unused)) *nn,
-				time_t boot_time)
+nfsd4_umh_cltrack_grace_done(struct nfsd_net *nn)
 {
 	char *legacy;
 	char timestr[22]; /* FIXME: better way to determine max size? */
 
-	sprintf(timestr, "%ld", boot_time);
+	sprintf(timestr, "%ld", nn->boot_time);
 	legacy = nfsd4_cltrack_legacy_topdir();
-	nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy);
+	nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy, NULL);
 	kfree(legacy);
 }
 
@@ -1356,10 +1489,10 @@ nfsd4_client_record_check(struct nfs4_client *clp)
 }
 
 void
-nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time)
+nfsd4_record_grace_done(struct nfsd_net *nn)
 {
 	if (nn->client_tracking_ops)
-		nn->client_tracking_ops->grace_done(nn, boot_time);
+		nn->client_tracking_ops->grace_done(nn);
 }
 
 static int

fs/nfsd/nfs4state.c

@@ -96,6 +96,8 @@ static struct kmem_cache *deleg_slab;
 
 static void free_session(struct nfsd4_session *);
 
+static struct nfsd4_callback_ops nfsd4_cb_recall_ops;
+
 static bool is_session_dead(struct nfsd4_session *ses)
 {
 	return ses->se_flags & NFS4_SESSION_DEAD;
@@ -645,7 +647,9 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh)
 	INIT_LIST_HEAD(&dp->dl_perclnt);
 	INIT_LIST_HEAD(&dp->dl_recall_lru);
 	dp->dl_type = NFS4_OPEN_DELEGATE_READ;
-	INIT_WORK(&dp->dl_recall.cb_work, nfsd4_run_cb_recall);
+	dp->dl_retries = 1;
+	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
+		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
 	return dp;
 out_dec:
 	atomic_long_dec(&num_delegations);
@@ -673,15 +677,20 @@ nfs4_put_stid(struct nfs4_stid *s)
 
 static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 {
-	lockdep_assert_held(&state_lock);
+	struct file *filp = NULL;
+	struct file_lock *fl;
 
-	if (!fp->fi_lease)
-		return;
-	if (atomic_dec_and_test(&fp->fi_delegees)) {
-		vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
+	spin_lock(&fp->fi_lock);
+	if (fp->fi_lease && atomic_dec_and_test(&fp->fi_delegees)) {
+		swap(filp, fp->fi_deleg_file);
+		fl = fp->fi_lease;
 		fp->fi_lease = NULL;
-		fput(fp->fi_deleg_file);
-		fp->fi_deleg_file = NULL;
+	}
+	spin_unlock(&fp->fi_lock);
+
+	if (filp) {
+		vfs_setlease(filp, F_UNLCK, &fl);
+		fput(filp);
 	}
 }
 
@@ -717,8 +726,6 @@ unhash_delegation_locked(struct nfs4_delegation *dp)
 	list_del_init(&dp->dl_recall_lru);
 	list_del_init(&dp->dl_perfile);
 	spin_unlock(&fp->fi_lock);
-	if (fp)
-		nfs4_put_deleg_lease(fp);
 }
 
 static void destroy_delegation(struct nfs4_delegation *dp)
@@ -726,6 +733,7 @@ static void destroy_delegation(struct nfs4_delegation *dp)
 	spin_lock(&state_lock);
 	unhash_delegation_locked(dp);
 	spin_unlock(&state_lock);
+	nfs4_put_deleg_lease(dp->dl_stid.sc_file);
 	nfs4_put_stid(&dp->dl_stid);
 }
 
@@ -735,6 +743,8 @@ static void revoke_delegation(struct nfs4_delegation *dp)
 
 	WARN_ON(!list_empty(&dp->dl_recall_lru));
 
+	nfs4_put_deleg_lease(dp->dl_stid.sc_file);
+
 	if (clp->cl_minorversion == 0)
 		nfs4_put_stid(&dp->dl_stid);
 	else {
@@ -1635,6 +1645,7 @@ __destroy_client(struct nfs4_client *clp)
 	while (!list_empty(&reaplist)) {
 		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
 		list_del_init(&dp->dl_recall_lru);
+		nfs4_put_deleg_lease(dp->dl_stid.sc_file);
 		nfs4_put_stid(&dp->dl_stid);
 	}
 	while (!list_empty(&clp->cl_revoked)) {
@@ -1862,7 +1873,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 		free_client(clp);
 		return NULL;
 	}
-	INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_run_cb_null);
+	nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL);
 	clp->cl_time = get_seconds();
 	clear_bit(0, &clp->cl_cb_slot_busy);
 	copy_verf(clp, verf);
@@ -3349,8 +3360,9 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
 	return ret;
 }
 
-void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
+static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
 {
+	struct nfs4_delegation *dp = cb_to_delegation(cb);
 	struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net,
 					  nfsd_net_id);
 
@@ -3371,6 +3383,43 @@ void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
 	spin_unlock(&state_lock);
 }
 
+static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
+		struct rpc_task *task)
+{
+	struct nfs4_delegation *dp = cb_to_delegation(cb);
+
+	switch (task->tk_status) {
+	case 0:
+		return 1;
+	case -EBADHANDLE:
+	case -NFS4ERR_BAD_STATEID:
+		/*
+		 * Race: client probably got cb_recall before open reply
+		 * granting delegation.
+		 */
+		if (dp->dl_retries--) {
+			rpc_delay(task, 2 * HZ);
+			return 0;
+		}
+		/*FALLTHRU*/
+	default:
+		return -1;
+	}
+}
+
+static void nfsd4_cb_recall_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_delegation *dp = cb_to_delegation(cb);
+
+	nfs4_put_stid(&dp->dl_stid);
+}
+
+static struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
+	.prepare	= nfsd4_cb_recall_prepare,
+	.done		= nfsd4_cb_recall_done,
+	.release	= nfsd4_cb_recall_release,
+};
+
 static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 {
 	/*
@@ -3381,7 +3430,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	 * it's safe to take a reference.
 	 */
 	atomic_inc(&dp->dl_stid.sc_count);
-	nfsd4_cb_recall(dp);
+	nfsd4_run_cb(&dp->dl_recall);
 }
 
 /* Called from break_lease() with i_lock held. */
@@ -3759,7 +3808,6 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag)
 	fl = locks_alloc_lock();
 	if (!fl)
 		return NULL;
-	locks_init_lock(fl);
 	fl->fl_lmops = &nfsd_lease_mng_ops;
 	fl->fl_flags = FL_DELEG;
 	fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
@@ -4107,7 +4155,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status;
 }
 
-static void
+void
 nfsd4_end_grace(struct nfsd_net *nn)
 {
 	/* do nothing if grace period already ended */
@@ -4116,14 +4164,28 @@ nfsd4_end_grace(struct nfsd_net *nn)
 
 	dprintk("NFSD: end of grace period\n");
 	nn->grace_ended = true;
-	nfsd4_record_grace_done(nn, nn->boot_time);
+	/*
+	 * If the server goes down again right now, an NFSv4
+	 * client will still be allowed to reclaim after it comes back up,
+	 * even if it hasn't yet had a chance to reclaim state this time.
+	 *
+	 */
+	nfsd4_record_grace_done(nn);
+	/*
+	 * At this point, NFSv4 clients can still reclaim.  But if the
+	 * server crashes, any that have not yet reclaimed will be out
+	 * of luck on the next boot.
+	 *
+	 * (NFSv4.1+ clients are considered to have reclaimed once they
+	 * call RECLAIM_COMPLETE.  NFSv4.0 clients are considered to
+	 * have reclaimed after their first OPEN.)
+	 */
 	locks_end_grace(&nn->nfsd4_manager);
 	/*
-	 * Now that every NFSv4 client has had the chance to recover and
-	 * to see the (possibly new, possibly shorter) lease time, we
-	 * can safely set the next grace time to the current lease time:
+	 * At this point, and once lockd and/or any other containers
+	 * exit their grace period, further reclaims will fail and
+	 * regular locking can resume.
 	 */
-	nn->nfsd4_grace = nn->nfsd4_lease;
 }
 
 static time_t
@@ -5210,7 +5272,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 	fp = lock_stp->st_stid.sc_file;
-	locks_init_lock(file_lock);
 	switch (lock->lk_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
@@ -5354,7 +5415,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_jukebox;
 		goto out;
 	}
-	locks_init_lock(file_lock);
+
 	switch (lockt->lt_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
@@ -5432,7 +5493,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_jukebox;
 		goto fput;
 	}
-	locks_init_lock(file_lock);
+
 	file_lock->fl_type = F_UNLCK;
 	file_lock->fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
 	file_lock->fl_pid = current->tgid;
@@ -5645,6 +5706,9 @@ nfs4_check_open_reclaim(clientid_t *clid,
 	if (status)
 		return nfserr_reclaim_bad;
 
+	if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags))
+		return nfserr_no_grace;
+
 	if (nfsd4_client_record_check(cstate->clp))
 		return nfserr_reclaim_bad;
 
@@ -6342,10 +6406,10 @@ nfs4_state_start_net(struct net *net)
 	ret = nfs4_state_create_net(net);
 	if (ret)
 		return ret;
-	nfsd4_client_tracking_init(net);
 	nn->boot_time = get_seconds();
-	locks_start_grace(net, &nn->nfsd4_manager);
 	nn->grace_ended = false;
+	locks_start_grace(net, &nn->nfsd4_manager);
+	nfsd4_client_tracking_init(net);
 	printk(KERN_INFO "NFSD: starting %ld-second grace period (net %p)\n",
 	       nn->nfsd4_grace, net);
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ);
@@ -6402,6 +6466,7 @@ nfs4_state_shutdown_net(struct net *net)
 	list_for_each_safe(pos, next, &reaplist) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		list_del_init(&dp->dl_recall_lru);
+		nfs4_put_deleg_lease(dp->dl_stid.sc_file);
 		nfs4_put_stid(&dp->dl_stid);
 	}
 

fs/nfsd/nfs4xdr.c

@@ -31,13 +31,6 @@
  *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
  *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * TODO: Neil Brown made the following observation:  We currently
- * initially reserve NFSD_BUFSIZE space on the transmit queue and
- * never release any of that until the request is complete.
- * It would be good to calculate a new maximum response size while
- * decoding the COMPOUND, and call svc_reserve with this number
- * at the end of nfs4svc_decode_compoundargs.
  */
 
 #include <linux/slab.h>
@@ -1520,6 +1513,22 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+static __be32
+nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek)
+{
+	DECODE_HEAD;
+
+	status = nfsd4_decode_stateid(argp, &seek->seek_stateid);
+	if (status)
+		return status;
+
+	READ_BUF(8 + 4);
+	p = xdr_decode_hyper(p, &seek->seek_offset);
+	seek->seek_whence = be32_to_cpup(p);
+
+	DECODE_TAIL;
+}
+
 static __be32
 nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p)
 {
@@ -1593,6 +1602,20 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_WANT_DELEGATION]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_DESTROY_CLIENTID]	= (nfsd4_dec)nfsd4_decode_destroy_clientid,
 	[OP_RECLAIM_COMPLETE]	= (nfsd4_dec)nfsd4_decode_reclaim_complete,
+
+	/* new operations for NFSv4.2 */
+	[OP_ALLOCATE]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_COPY]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_COPY_NOTIFY]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_DEALLOCATE]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_IO_ADVISE]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTERROR]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTSTATS]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_OFFLOAD_CANCEL]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_OFFLOAD_STATUS]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_READ_PLUS]		= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_SEEK]		= (nfsd4_dec)nfsd4_decode_seek,
+	[OP_WRITE_SAME]		= (nfsd4_dec)nfsd4_decode_notsupp,
 };
 
 static inline bool
@@ -1670,6 +1693,14 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 			readbytes += nfsd4_max_reply(argp->rqstp, op);
 		} else
 			max_reply += nfsd4_max_reply(argp->rqstp, op);
+		/*
+		 * OP_LOCK may return a conflicting lock.  (Special case
+		 * because it will just skip encoding this if it runs
+		 * out of xdr buffer space, and it is the only operation
+		 * that behaves this way.)
+		 */
+		if (op->opnum == OP_LOCK)
+			max_reply += NFS4_OPAQUE_LIMIT;
 
 		if (op->status) {
 			argp->opcnt = i+1;
@@ -3763,6 +3794,22 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	return nfserr;
 }
 
+static __be32
+nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
+		  struct nfsd4_seek *seek)
+{
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(&resp->xdr, 4 + 8);
+	*p++ = cpu_to_be32(seek->seek_eof);
+	p = xdr_encode_hyper(p, seek->seek_pos);
+
+	return nfserr;
+}
+
 static __be32
 nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p)
 {
@@ -3835,6 +3882,20 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_WANT_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_DESTROY_CLIENTID]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_RECLAIM_COMPLETE]	= (nfsd4_enc)nfsd4_encode_noop,
+
+	/* NFSv4.2 operations */
+	[OP_ALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_COPY]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_COPY_NOTIFY]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_DEALLOCATE]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_IO_ADVISE]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTERROR]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTSTATS]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_OFFLOAD_CANCEL]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_OFFLOAD_STATUS]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_READ_PLUS]		= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_SEEK]		= (nfsd4_enc)nfsd4_encode_seek,
+	[OP_WRITE_SAME]		= (nfsd4_enc)nfsd4_encode_noop,
 };
 
 /*

fs/nfsd/nfscache.c

@@ -27,8 +27,12 @@
  */
 #define TARGET_BUCKET_SIZE	64
 
-static struct hlist_head *	cache_hash;
-static struct list_head 	lru_head;
+struct nfsd_drc_bucket {
+	struct list_head lru_head;
+	spinlock_t cache_lock;
+};
+
+static struct nfsd_drc_bucket	*drc_hashtbl;
 static struct kmem_cache	*drc_slab;
 
 /* max number of entries allowed in the cache */
@@ -36,6 +40,7 @@ static unsigned int		max_drc_entries;
 
 /* number of significant bits in the hash value */
 static unsigned int		maskbits;
+static unsigned int		drc_hashsize;
 
 /*
  * Stats and other tracking of on the duplicate reply cache. All of these and
@@ -43,7 +48,7 @@ static unsigned int		maskbits;
  */
 
 /* total number of entries */
-static unsigned int		num_drc_entries;
+static atomic_t			num_drc_entries;
 
 /* cache misses due only to checksum comparison failures */
 static unsigned int		payload_misses;
@@ -75,7 +80,6 @@ static struct shrinker nfsd_reply_cache_shrinker = {
  * A cache entry is "single use" if c_state == RC_INPROG
  * Otherwise, it when accessing _prev or _next, the lock must be held.
  */
-static DEFINE_SPINLOCK(cache_lock);
 static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
 
 /*
@@ -116,6 +120,12 @@ nfsd_hashsize(unsigned int limit)
 	return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE);
 }
 
+static u32
+nfsd_cache_hash(__be32 xid)
+{
+	return hash_32(be32_to_cpu(xid), maskbits);
+}
+
 static struct svc_cacherep *
 nfsd_reply_cache_alloc(void)
 {
@@ -126,7 +136,6 @@ nfsd_reply_cache_alloc(void)
 		rp->c_state = RC_UNUSED;
 		rp->c_type = RC_NOCACHE;
 		INIT_LIST_HEAD(&rp->c_lru);
-		INIT_HLIST_NODE(&rp->c_hash);
 	}
 	return rp;
 }
@@ -138,29 +147,27 @@ nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
 		drc_mem_usage -= rp->c_replvec.iov_len;
 		kfree(rp->c_replvec.iov_base);
 	}
-	if (!hlist_unhashed(&rp->c_hash))
-		hlist_del(&rp->c_hash);
 	list_del(&rp->c_lru);
-	--num_drc_entries;
+	atomic_dec(&num_drc_entries);
 	drc_mem_usage -= sizeof(*rp);
 	kmem_cache_free(drc_slab, rp);
 }
 
 static void
-nfsd_reply_cache_free(struct svc_cacherep *rp)
+nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
 {
-	spin_lock(&cache_lock);
+	spin_lock(&b->cache_lock);
 	nfsd_reply_cache_free_locked(rp);
-	spin_unlock(&cache_lock);
+	spin_unlock(&b->cache_lock);
 }
 
 int nfsd_reply_cache_init(void)
 {
 	unsigned int hashsize;
+	unsigned int i;
 
-	INIT_LIST_HEAD(&lru_head);
 	max_drc_entries = nfsd_cache_size_limit();
-	num_drc_entries = 0;
+	atomic_set(&num_drc_entries, 0);
 	hashsize = nfsd_hashsize(max_drc_entries);
 	maskbits = ilog2(hashsize);
 
@@ -170,9 +177,14 @@ int nfsd_reply_cache_init(void)
 	if (!drc_slab)
 		goto out_nomem;
 
-	cache_hash = kcalloc(hashsize, sizeof(struct hlist_head), GFP_KERNEL);
-	if (!cache_hash)
+	drc_hashtbl = kcalloc(hashsize, sizeof(*drc_hashtbl), GFP_KERNEL);
+	if (!drc_hashtbl)
 		goto out_nomem;
+	for (i = 0; i < hashsize; i++) {
+		INIT_LIST_HEAD(&drc_hashtbl[i].lru_head);
+		spin_lock_init(&drc_hashtbl[i].cache_lock);
+	}
+	drc_hashsize = hashsize;
 
 	return 0;
 out_nomem:
@@ -184,17 +196,22 @@ int nfsd_reply_cache_init(void)
 void nfsd_reply_cache_shutdown(void)
 {
 	struct svc_cacherep	*rp;
+	unsigned int i;
 
 	unregister_shrinker(&nfsd_reply_cache_shrinker);
 	cancel_delayed_work_sync(&cache_cleaner);
 
-	while (!list_empty(&lru_head)) {
-		rp = list_entry(lru_head.next, struct svc_cacherep, c_lru);
-		nfsd_reply_cache_free_locked(rp);
+	for (i = 0; i < drc_hashsize; i++) {
+		struct list_head *head = &drc_hashtbl[i].lru_head;
+		while (!list_empty(head)) {
+			rp = list_first_entry(head, struct svc_cacherep, c_lru);
+			nfsd_reply_cache_free_locked(rp);
+		}
 	}
 
-	kfree (cache_hash);
-	cache_hash = NULL;
+	kfree (drc_hashtbl);
+	drc_hashtbl = NULL;
+	drc_hashsize = 0;
 
 	if (drc_slab) {
 		kmem_cache_destroy(drc_slab);
@@ -207,61 +224,63 @@ void nfsd_reply_cache_shutdown(void)
  * not already scheduled.
  */
 static void
-lru_put_end(struct svc_cacherep *rp)
+lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp)
 {
 	rp->c_timestamp = jiffies;
-	list_move_tail(&rp->c_lru, &lru_head);
+	list_move_tail(&rp->c_lru, &b->lru_head);
 	schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
 }
 
-/*
- * Move a cache entry from one hash list to another
- */
-static void
-hash_refile(struct svc_cacherep *rp)
-{
-	hlist_del_init(&rp->c_hash);
-	/*
-	 * No point in byte swapping c_xid since we're just using it to pick
-	 * a hash bucket.
-	 */
-	hlist_add_head(&rp->c_hash, cache_hash +
-			hash_32((__force u32)rp->c_xid, maskbits));
-}
-
-/*
- * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
- * Also prune the oldest ones when the total exceeds the max number of entries.
- */
 static long
-prune_cache_entries(void)
+prune_bucket(struct nfsd_drc_bucket *b)
 {
 	struct svc_cacherep *rp, *tmp;
 	long freed = 0;
 
-	list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
+	list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) {
 		/*
 		 * Don't free entries attached to calls that are still
 		 * in-progress, but do keep scanning the list.
 		 */
 		if (rp->c_state == RC_INPROG)
 			continue;
-		if (num_drc_entries <= max_drc_entries &&
+		if (atomic_read(&num_drc_entries) <= max_drc_entries &&
 		    time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
 			break;
 		nfsd_reply_cache_free_locked(rp);
 		freed++;
 	}
+	return freed;
+}
+
+/*
+ * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
+ * Also prune the oldest ones when the total exceeds the max number of entries.
+ */
+static long
+prune_cache_entries(void)
+{
+	unsigned int i;
+	long freed = 0;
+	bool cancel = true;
+
+	for (i = 0; i < drc_hashsize; i++) {
+		struct nfsd_drc_bucket *b = &drc_hashtbl[i];
+
+		if (list_empty(&b->lru_head))
+			continue;
+		spin_lock(&b->cache_lock);
+		freed += prune_bucket(b);
+		if (!list_empty(&b->lru_head))
+			cancel = false;
+		spin_unlock(&b->cache_lock);
+	}
 
 	/*
-	 * Conditionally rearm the job. If we cleaned out the list, then
-	 * cancel any pending run (since there won't be any work to do).
-	 * Otherwise, we rearm the job or modify the existing one to run in
-	 * RC_EXPIRE since we just ran the pruner.
+	 * Conditionally rearm the job to run in RC_EXPIRE since we just
+	 * ran the pruner.
 	 */
-	if (list_empty(&lru_head))
-		cancel_delayed_work(&cache_cleaner);
-	else
+	if (!cancel)
 		mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
 	return freed;
 }
@@ -269,32 +288,19 @@ prune_cache_entries(void)
 static void
 cache_cleaner_func(struct work_struct *unused)
 {
-	spin_lock(&cache_lock);
 	prune_cache_entries();
-	spin_unlock(&cache_lock);
 }
 
 static unsigned long
 nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
 {
-	unsigned long num;
-
-	spin_lock(&cache_lock);
-	num = num_drc_entries;
-	spin_unlock(&cache_lock);
-
-	return num;
+	return atomic_read(&num_drc_entries);
 }
 
 static unsigned long
 nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
 {
-	unsigned long freed;
-
-	spin_lock(&cache_lock);
-	freed = prune_cache_entries();
-	spin_unlock(&cache_lock);
-	return freed;
+	return prune_cache_entries();
 }
 /*
  * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
@@ -332,20 +338,24 @@ nfsd_cache_csum(struct svc_rqst *rqstp)
 static bool
 nfsd_cache_match(struct svc_rqst *rqstp, __wsum csum, struct svc_cacherep *rp)
 {
-	/* Check RPC header info first */
-	if (rqstp->rq_xid != rp->c_xid || rqstp->rq_proc != rp->c_proc ||
-	    rqstp->rq_prot != rp->c_prot || rqstp->rq_vers != rp->c_vers ||
-	    rqstp->rq_arg.len != rp->c_len ||
-	    !rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) ||
-	    rpc_get_port(svc_addr(rqstp)) != rpc_get_port((struct sockaddr *)&rp->c_addr))
+	/* Check RPC XID first */
+	if (rqstp->rq_xid != rp->c_xid)
 		return false;
-
 	/* compare checksum of NFS data */
 	if (csum != rp->c_csum) {
 		++payload_misses;
 		return false;
 	}
 
+	/* Other discriminators */
+	if (rqstp->rq_proc != rp->c_proc ||
+	    rqstp->rq_prot != rp->c_prot ||
+	    rqstp->rq_vers != rp->c_vers ||
+	    rqstp->rq_arg.len != rp->c_len ||
+	    !rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) ||
+	    rpc_get_port(svc_addr(rqstp)) != rpc_get_port((struct sockaddr *)&rp->c_addr))
+		return false;
+
 	return true;
 }
 
@@ -355,18 +365,14 @@ nfsd_cache_match(struct svc_rqst *rqstp, __wsum csum, struct svc_cacherep *rp)
  * NULL on failure.
  */
 static struct svc_cacherep *
-nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
+nfsd_cache_search(struct nfsd_drc_bucket *b, struct svc_rqst *rqstp,
+		__wsum csum)
 {
 	struct svc_cacherep	*rp, *ret = NULL;
-	struct hlist_head 	*rh;
+	struct list_head 	*rh = &b->lru_head;
 	unsigned int		entries = 0;
 
-	/*
-	 * No point in byte swapping rq_xid since we're just using it to pick
-	 * a hash bucket.
-	 */
-	rh = &cache_hash[hash_32((__force u32)rqstp->rq_xid, maskbits)];
-	hlist_for_each_entry(rp, rh, c_hash) {
+	list_for_each_entry(rp, rh, c_lru) {
 		++entries;
 		if (nfsd_cache_match(rqstp, csum, rp)) {
 			ret = rp;
@@ -377,11 +383,12 @@ nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
 	/* tally hash chain length stats */
 	if (entries > longest_chain) {
 		longest_chain = entries;
-		longest_chain_cachesize = num_drc_entries;
+		longest_chain_cachesize = atomic_read(&num_drc_entries);
 	} else if (entries == longest_chain) {
 		/* prefer to keep the smallest cachesize possible here */
-		longest_chain_cachesize = min(longest_chain_cachesize,
-						num_drc_entries);
+		longest_chain_cachesize = min_t(unsigned int,
+				longest_chain_cachesize,
+				atomic_read(&num_drc_entries));
 	}
 
 	return ret;
@@ -403,6 +410,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 				vers = rqstp->rq_vers,
 				proc = rqstp->rq_proc;
 	__wsum			csum;
+	u32 hash = nfsd_cache_hash(xid);
+	struct nfsd_drc_bucket *b = &drc_hashtbl[hash];
 	unsigned long		age;
 	int type = rqstp->rq_cachetype;
 	int rtn = RC_DOIT;
@@ -420,16 +429,16 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 	 * preallocate an entry.
 	 */
 	rp = nfsd_reply_cache_alloc();
-	spin_lock(&cache_lock);
+	spin_lock(&b->cache_lock);
 	if (likely(rp)) {
-		++num_drc_entries;
+		atomic_inc(&num_drc_entries);
 		drc_mem_usage += sizeof(*rp);
 	}
 
 	/* go ahead and prune the cache */
-	prune_cache_entries();
+	prune_bucket(b);
 
-	found = nfsd_cache_search(rqstp, csum);
+	found = nfsd_cache_search(b, rqstp, csum);
 	if (found) {
 		if (likely(rp))
 			nfsd_reply_cache_free_locked(rp);
@@ -454,8 +463,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 	rp->c_len = rqstp->rq_arg.len;
 	rp->c_csum = csum;
 
-	hash_refile(rp);
-	lru_put_end(rp);
+	lru_put_end(b, rp);
 
 	/* release any buffer */
 	if (rp->c_type == RC_REPLBUFF) {
@@ -465,14 +473,14 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
 	}
 	rp->c_type = RC_NOCACHE;
  out:
-	spin_unlock(&cache_lock);
+	spin_unlock(&b->cache_lock);
 	return rtn;
 
 found_entry:
 	nfsdstats.rchits++;
 	/* We found a matching entry which is either in progress or done. */
 	age = jiffies - rp->c_timestamp;
-	lru_put_end(rp);
+	lru_put_end(b, rp);
 
 	rtn = RC_DROPIT;
 	/* Request being processed or excessive rexmits */
@@ -527,18 +535,23 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
 {
 	struct svc_cacherep *rp = rqstp->rq_cacherep;
 	struct kvec	*resv = &rqstp->rq_res.head[0], *cachv;
+	u32		hash;
+	struct nfsd_drc_bucket *b;
 	int		len;
 	size_t		bufsize = 0;
 
 	if (!rp)
 		return;
 
+	hash = nfsd_cache_hash(rp->c_xid);
+	b = &drc_hashtbl[hash];
+
 	len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
 	len >>= 2;
 
 	/* Don't cache excessive amounts of data and XDR failures */
 	if (!statp || len > (256 >> 2)) {
-		nfsd_reply_cache_free(rp);
+		nfsd_reply_cache_free(b, rp);
 		return;
 	}
 
@@ -553,23 +566,23 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
 		bufsize = len << 2;
 		cachv->iov_base = kmalloc(bufsize, GFP_KERNEL);
 		if (!cachv->iov_base) {
-			nfsd_reply_cache_free(rp);
+			nfsd_reply_cache_free(b, rp);
 			return;
 		}
 		cachv->iov_len = bufsize;
 		memcpy(cachv->iov_base, statp, bufsize);
 		break;
 	case RC_NOCACHE:
-		nfsd_reply_cache_free(rp);
+		nfsd_reply_cache_free(b, rp);
 		return;
 	}
-	spin_lock(&cache_lock);
+	spin_lock(&b->cache_lock);
 	drc_mem_usage += bufsize;
-	lru_put_end(rp);
+	lru_put_end(b, rp);
 	rp->c_secure = rqstp->rq_secure;
 	rp->c_type = cachetype;
 	rp->c_state = RC_DONE;
-	spin_unlock(&cache_lock);
+	spin_unlock(&b->cache_lock);
 	return;
 }
 
@@ -600,9 +613,9 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
  */
 static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
 {
-	spin_lock(&cache_lock);
 	seq_printf(m, "max entries:           %u\n", max_drc_entries);
-	seq_printf(m, "num entries:           %u\n", num_drc_entries);
+	seq_printf(m, "num entries:           %u\n",
+			atomic_read(&num_drc_entries));
 	seq_printf(m, "hash buckets:          %u\n", 1 << maskbits);
 	seq_printf(m, "mem usage:             %u\n", drc_mem_usage);
 	seq_printf(m, "cache hits:            %u\n", nfsdstats.rchits);
@@ -611,7 +624,6 @@ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "payload misses:        %u\n", payload_misses);
 	seq_printf(m, "longest chain len:     %u\n", longest_chain);
 	seq_printf(m, "cachesize at longest:  %u\n", longest_chain_cachesize);
-	spin_unlock(&cache_lock);
 	return 0;
 }
 

fs/nfsd/nfsctl.c

@@ -49,6 +49,7 @@ enum {
 	NFSD_Leasetime,
 	NFSD_Gracetime,
 	NFSD_RecoveryDir,
+	NFSD_V4EndGrace,
 #endif
 };
 
@@ -68,6 +69,7 @@ static ssize_t write_maxconn(struct file *file, char *buf, size_t size);
 static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
 static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
 static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
+static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size);
 #endif
 
 static ssize_t (*write_op[])(struct file *, char *, size_t) = {
@@ -84,6 +86,7 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = {
 	[NFSD_Leasetime] = write_leasetime,
 	[NFSD_Gracetime] = write_gracetime,
 	[NFSD_RecoveryDir] = write_recoverydir,
+	[NFSD_V4EndGrace] = write_v4_end_grace,
 #endif
 };
 
@@ -1077,6 +1080,47 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
 	return rv;
 }
 
+/**
+ * write_v4_end_grace - release grace period for nfsd's v4.x lock manager
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ * OR
+ *
+ * Input:
+ * 			buf:		any value
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *			passed-in buffer filled with "Y" or "N" with a newline
+ *			and NULL-terminated C string. This indicates whether
+ *			the grace period has ended in the current net
+ *			namespace. Return code is the size in bytes of the
+ *			string. Writing a string that starts with 'Y', 'y', or
+ *			'1' to the file will end the grace period for nfsd's v4
+ *			lock manager.
+ */
+static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size)
+{
+	struct net *net = file->f_dentry->d_sb->s_fs_info;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	if (size > 0) {
+		switch(buf[0]) {
+		case 'Y':
+		case 'y':
+		case '1':
+			nfsd4_end_grace(nn);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%c\n",
+			 nn->grace_ended ? 'Y' : 'N');
+}
+
 #endif
 
 /*----------------------------------------------------------------------------*/
@@ -1110,6 +1154,7 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 		[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR},
+		[NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO},
 #endif
 		/* last one */ {""}
 	};

fs/nfsd/nfsd.h

@@ -251,7 +251,7 @@ void		nfsd_lockd_shutdown(void);
 #define nfserr_deleg_revoked		cpu_to_be32(NFS4ERR_DELEG_REVOKED)
 #define nfserr_partner_notsupp		cpu_to_be32(NFS4ERR_PARTNER_NOTSUPP)
 #define nfserr_partner_no_auth		cpu_to_be32(NFS4ERR_PARTNER_NO_AUTH)
-#define nfserr_metadata_notsupp		cpu_to_be32(NFS4ERR_METADATA_NOTSUPP)
+#define nfserr_union_notsupp		cpu_to_be32(NFS4ERR_UNION_NOTSUPP)
 #define nfserr_offload_denied		cpu_to_be32(NFS4ERR_OFFLOAD_DENIED)
 #define nfserr_wrong_lfs		cpu_to_be32(NFS4ERR_WRONG_LFS)
 #define nfserr_badlabel		cpu_to_be32(NFS4ERR_BADLABEL)

fs/nfsd/nfsfh.c

@@ -209,8 +209,10 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 		 * fix that case easily.
 		 */
 		struct cred *new = prepare_creds();
-		if (!new)
-			return nfserrno(-ENOMEM);
+		if (!new) {
+			error =  nfserrno(-ENOMEM);
+			goto out;
+		}
 		new->cap_effective =
 			cap_raise_nfsd_set(new->cap_effective,
 					   new->cap_permitted);

fs/nfsd/state.h

@@ -62,16 +62,21 @@ typedef struct {
 	(s)->si_generation
 
 struct nfsd4_callback {
-	void *cb_op;
 	struct nfs4_client *cb_clp;
 	struct list_head cb_per_client;
 	u32 cb_minorversion;
 	struct rpc_message cb_msg;
-	const struct rpc_call_ops *cb_ops;
+	struct nfsd4_callback_ops *cb_ops;
 	struct work_struct cb_work;
 	bool cb_done;
 };
 
+struct nfsd4_callback_ops {
+	void (*prepare)(struct nfsd4_callback *);
+	int (*done)(struct nfsd4_callback *, struct rpc_task *);
+	void (*release)(struct nfsd4_callback *);
+};
+
 /*
  * A core object that represents a "common" stateid. These are generally
  * embedded within the different (more specific) stateid objects and contain
@@ -127,6 +132,9 @@ struct nfs4_delegation {
 	struct nfsd4_callback	dl_recall;
 };
 
+#define cb_to_delegation(cb) \
+	container_of(cb, struct nfs4_delegation, dl_recall)
+
 /* client delegation callback info */
 struct nfs4_cb_conn {
 	/* SETCLIENTID info */
@@ -306,6 +314,7 @@ struct nfs4_client {
 #define NFSD4_CLIENT_STABLE		(2)	/* client on stable storage */
 #define NFSD4_CLIENT_RECLAIM_COMPLETE	(3)	/* reclaim_complete done */
 #define NFSD4_CLIENT_CONFIRMED		(4)	/* client is confirmed */
+#define NFSD4_CLIENT_UPCALL_LOCK	(5)	/* upcall serialization */
 #define NFSD4_CLIENT_CB_FLAG_MASK	(1 << NFSD4_CLIENT_CB_UPDATE | \
 					 1 << NFSD4_CLIENT_CB_KILL)
 	unsigned long		cl_flags;
@@ -517,6 +526,13 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 #define RD_STATE	        0x00000010
 #define WR_STATE	        0x00000020
 
+enum nfsd4_cb_op {
+	NFSPROC4_CLNT_CB_NULL = 0,
+	NFSPROC4_CLNT_CB_RECALL,
+	NFSPROC4_CLNT_CB_SEQUENCE,
+};
+
+
 struct nfsd4_compound_state;
 struct nfsd_net;
 
@@ -531,12 +547,12 @@ extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid,
 		struct nfsd4_compound_state *cstate, struct nfsd_net *nn);
 extern int set_callback_cred(void);
-void nfsd4_run_cb_null(struct work_struct *w);
-void nfsd4_run_cb_recall(struct work_struct *w);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
 extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
-extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
+extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
+		struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
+extern void nfsd4_run_cb(struct nfsd4_callback *cb);
 extern int nfsd4_create_callback_queue(void);
 extern void nfsd4_destroy_callback_queue(void);
 extern void nfsd4_shutdown_callback(struct nfs4_client *);
@@ -545,13 +561,16 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
 							struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
 
+/* grace period management */
+void nfsd4_end_grace(struct nfsd_net *nn);
+
 /* nfs4recover operations */
 extern int nfsd4_client_tracking_init(struct net *net);
 extern void nfsd4_client_tracking_exit(struct net *net);
 extern void nfsd4_client_record_create(struct nfs4_client *clp);
 extern void nfsd4_client_record_remove(struct nfs4_client *clp);
 extern int nfsd4_client_record_check(struct nfs4_client *clp);
-extern void nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time);
+extern void nfsd4_record_grace_done(struct nfsd_net *nn);
 
 /* nfs fault injection functions */
 #ifdef CONFIG_NFSD_FAULT_INJECTION

fs/nfsd/vfs.c

@@ -445,6 +445,16 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 		if (err)
 			goto out;
 		size_change = 1;
+
+		/*
+		 * RFC5661, Section 18.30.4:
+		 *   Changing the size of a file with SETATTR indirectly
+		 *   changes the time_modify and change attributes.
+		 *
+		 * (and similar for the older RFCs)
+		 */
+		if (iap->ia_size != i_size_read(inode))
+			iap->ia_valid |= ATTR_MTIME;
 	}
 
 	iap->ia_valid |= ATTR_CTIME;
@@ -649,6 +659,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 {
 	struct path	path;
 	struct inode	*inode;
+	struct file	*file;
 	int		flags = O_RDONLY|O_LARGEFILE;
 	__be32		err;
 	int		host_err = 0;
@@ -703,19 +714,25 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 		else
 			flags = O_WRONLY|O_LARGEFILE;
 	}
-	*filp = dentry_open(&path, flags, current_cred());
-	if (IS_ERR(*filp)) {
-		host_err = PTR_ERR(*filp);
-		*filp = NULL;
-	} else {
-		host_err = ima_file_check(*filp, may_flags);
 
-		if (may_flags & NFSD_MAY_64BIT_COOKIE)
-			(*filp)->f_mode |= FMODE_64BITHASH;
-		else
-			(*filp)->f_mode |= FMODE_32BITHASH;
+	file = dentry_open(&path, flags, current_cred());
+	if (IS_ERR(file)) {
+		host_err = PTR_ERR(file);
+		goto out_nfserr;
 	}
 
+	host_err = ima_file_check(file, may_flags);
+	if (host_err) {
+		nfsd_close(file);
+		goto out_nfserr;
+	}
+
+	if (may_flags & NFSD_MAY_64BIT_COOKIE)
+		file->f_mode |= FMODE_64BITHASH;
+	else
+		file->f_mode |= FMODE_32BITHASH;
+
+	*filp = file;
 out_nfserr:
 	err = nfserrno(host_err);
 out:

fs/nfsd/xdr4.h

@@ -428,6 +428,17 @@ struct nfsd4_reclaim_complete {
 	u32 rca_one_fs;
 };
 
+struct nfsd4_seek {
+	/* request */
+	stateid_t	seek_stateid;
+	loff_t		seek_offset;
+	u32		seek_whence;
+
+	/* response */
+	u32		seek_eof;
+	loff_t		seek_pos;
+};
+
 struct nfsd4_op {
 	int					opnum;
 	__be32					status;
@@ -473,6 +484,9 @@ struct nfsd4_op {
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
 		struct nfsd4_free_stateid	free_stateid;
+
+		/* NFSv4.2 */
+		struct nfsd4_seek		seek;
 	} u;
 	struct nfs4_replay *			replay;
 };

include/linux/nfs4.h

@@ -110,6 +110,20 @@ enum nfs_opnum4 {
 	OP_DESTROY_CLIENTID = 57,
 	OP_RECLAIM_COMPLETE = 58,
 
+	/* nfs42 */
+	OP_ALLOCATE = 59,
+	OP_COPY = 60,
+	OP_COPY_NOTIFY = 61,
+	OP_DEALLOCATE = 62,
+	OP_IO_ADVISE = 63,
+	OP_LAYOUTERROR = 64,
+	OP_LAYOUTSTATS = 65,
+	OP_OFFLOAD_CANCEL = 66,
+	OP_OFFLOAD_STATUS = 67,
+	OP_READ_PLUS = 68,
+	OP_SEEK = 69,
+	OP_WRITE_SAME = 70,
+
 	OP_ILLEGAL = 10044,
 };
 
@@ -117,10 +131,10 @@ enum nfs_opnum4 {
 Needs to be updated if more operations are defined in future.*/
 
 #define FIRST_NFS4_OP	OP_ACCESS
-#define LAST_NFS4_OP 	OP_RECLAIM_COMPLETE
+#define LAST_NFS4_OP 	OP_WRITE_SAME
 #define LAST_NFS40_OP	OP_RELEASE_LOCKOWNER
 #define LAST_NFS41_OP	OP_RECLAIM_COMPLETE
-#define LAST_NFS42_OP	OP_RECLAIM_COMPLETE
+#define LAST_NFS42_OP	OP_WRITE_SAME
 
 enum nfsstat4 {
 	NFS4_OK = 0,
@@ -235,10 +249,11 @@ enum nfsstat4 {
 	/* nfs42 */
 	NFS4ERR_PARTNER_NOTSUPP	= 10088,
 	NFS4ERR_PARTNER_NO_AUTH	= 10089,
-	NFS4ERR_METADATA_NOTSUPP = 10090,
+	NFS4ERR_UNION_NOTSUPP = 10090,
 	NFS4ERR_OFFLOAD_DENIED = 10091,
 	NFS4ERR_WRONG_LFS = 10092,
 	NFS4ERR_BADLABEL = 10093,
+	NFS4ERR_OFFLOAD_NO_REQS = 10094,
 };
 
 static inline bool seqid_mutating_err(u32 err)
@@ -535,4 +550,9 @@ struct nfs4_deviceid {
 	char data[NFS4_DEVICEID4_SIZE];
 };
 
+enum data_content4 {
+	NFS4_CONTENT_DATA		= 0,
+	NFS4_CONTENT_HOLE		= 1,
+};
+
 #endif

include/linux/proc_fs.h

@@ -74,6 +74,8 @@ static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *p
 
 #endif /* CONFIG_PROC_FS */
 
+struct net;
+
 static inline struct proc_dir_entry *proc_net_mkdir(
 	struct net *net, const char *name, struct proc_dir_entry *parent)
 {

include/linux/sunrpc/svc.h

@@ -280,7 +280,6 @@ struct svc_rqst {
 	bool			rq_splice_ok;   /* turned off in gss privacy
 						 * to prevent encrypting page
 						 * cache pages */
-	wait_queue_head_t	rq_wait;	/* synchronization */
 	struct task_struct	*rq_task;	/* service thread */
 };
 

include/uapi/linux/nfsd/export.h

@@ -28,7 +28,8 @@
 #define NFSEXP_ALLSQUASH	0x0008
 #define NFSEXP_ASYNC		0x0010
 #define NFSEXP_GATHERED_WRITES	0x0020
-/* 40 80 100 currently unused */
+#define NFSEXP_NOREADDIRPLUS    0x0040
+/* 80 100 currently unused */
 #define NFSEXP_NOHIDE		0x0200
 #define NFSEXP_NOSUBTREECHECK	0x0400
 #define	NFSEXP_NOAUTHNLM	0x0800		/* Don't authenticate NLM requests - just trust */
@@ -47,7 +48,7 @@
  */
 #define	NFSEXP_V4ROOT		0x10000
 /* All flags that we claim to support.  (Note we don't support NOACL.) */
-#define NFSEXP_ALLFLAGS		0x17E3F
+#define NFSEXP_ALLFLAGS		0x1FE7F
 
 /* The flags that may vary depending on security flavor: */
 #define NFSEXP_SECINFO_FLAGS	(NFSEXP_READONLY | NFSEXP_ROOTSQUASH \

net/sunrpc/svc.c

@@ -612,8 +612,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	if (!rqstp)
 		goto out_enomem;
 
-	init_waitqueue_head(&rqstp->rq_wait);
-
 	serv->sv_nrthreads++;
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;

net/sunrpc/svc_xprt.c

@@ -346,20 +346,6 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	if (!svc_xprt_has_something_to_do(xprt))
 		return;
 
-	cpu = get_cpu();
-	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	put_cpu();
-
-	spin_lock_bh(&pool->sp_lock);
-
-	if (!list_empty(&pool->sp_threads) &&
-	    !list_empty(&pool->sp_sockets))
-		printk(KERN_ERR
-		       "svc_xprt_enqueue: "
-		       "threads and transports both waiting??\n");
-
-	pool->sp_stats.packets++;
-
 	/* Mark transport as busy. It will remain in this state until
 	 * the provider calls svc_xprt_received. We update XPT_BUSY
 	 * atomically because it also guards against trying to enqueue
@@ -368,9 +354,15 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 	if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) {
 		/* Don't enqueue transport while already enqueued */
 		dprintk("svc: transport %p busy, not enqueued\n", xprt);
-		goto out_unlock;
+		return;
 	}
 
+	cpu = get_cpu();
+	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
+	spin_lock_bh(&pool->sp_lock);
+
+	pool->sp_stats.packets++;
+
 	if (!list_empty(&pool->sp_threads)) {
 		rqstp = list_entry(pool->sp_threads.next,
 				   struct svc_rqst,
@@ -382,18 +374,23 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 			printk(KERN_ERR
 				"svc_xprt_enqueue: server %p, rq_xprt=%p!\n",
 				rqstp, rqstp->rq_xprt);
-		rqstp->rq_xprt = xprt;
+		/* Note the order of the following 3 lines:
+		 * We want to assign xprt to rqstp->rq_xprt only _after_
+		 * we've woken up the process, so that we don't race with
+		 * the lockless check in svc_get_next_xprt().
+		 */
 		svc_xprt_get(xprt);
+		wake_up_process(rqstp->rq_task);
+		rqstp->rq_xprt = xprt;
 		pool->sp_stats.threads_woken++;
-		wake_up(&rqstp->rq_wait);
 	} else {
 		dprintk("svc: transport %p put into queue\n", xprt);
 		list_add_tail(&xprt->xpt_ready, &pool->sp_sockets);
 		pool->sp_stats.sockets_queued++;
 	}
 
-out_unlock:
 	spin_unlock_bh(&pool->sp_lock);
+	put_cpu();
 }
 
 /*
@@ -509,7 +506,7 @@ void svc_wake_up(struct svc_serv *serv)
 			svc_thread_dequeue(pool, rqstp);
 			rqstp->rq_xprt = NULL;
 			 */
-			wake_up(&rqstp->rq_wait);
+			wake_up_process(rqstp->rq_task);
 		} else
 			pool->sp_task_pending = 1;
 		spin_unlock_bh(&pool->sp_lock);
@@ -628,8 +625,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 {
 	struct svc_xprt *xprt;
 	struct svc_pool		*pool = rqstp->rq_pool;
-	DECLARE_WAITQUEUE(wait, current);
-	long			time_left;
+	long			time_left = 0;
 
 	/* Normally we will wait up to 5 seconds for any required
 	 * cache information to be provided.
@@ -651,40 +647,32 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 	} else {
 		if (pool->sp_task_pending) {
 			pool->sp_task_pending = 0;
-			spin_unlock_bh(&pool->sp_lock);
-			return ERR_PTR(-EAGAIN);
+			xprt = ERR_PTR(-EAGAIN);
+			goto out;
 		}
-		/* No data pending. Go to sleep */
-		svc_thread_enqueue(pool, rqstp);
-
 		/*
 		 * We have to be able to interrupt this wait
 		 * to bring down the daemons ...
 		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 
-		/*
-		 * checking kthread_should_stop() here allows us to avoid
-		 * locking and signalling when stopping kthreads that call
-		 * svc_recv. If the thread has already been woken up, then
-		 * we can exit here without sleeping. If not, then it
-		 * it'll be woken up quickly during the schedule_timeout
-		 */
-		if (kthread_should_stop()) {
-			set_current_state(TASK_RUNNING);
-			spin_unlock_bh(&pool->sp_lock);
-			return ERR_PTR(-EINTR);
-		}
-
-		add_wait_queue(&rqstp->rq_wait, &wait);
+		/* No data pending. Go to sleep */
+		svc_thread_enqueue(pool, rqstp);
 		spin_unlock_bh(&pool->sp_lock);
 
-		time_left = schedule_timeout(timeout);
+		if (!(signalled() || kthread_should_stop())) {
+			time_left = schedule_timeout(timeout);
+			__set_current_state(TASK_RUNNING);
 
-		try_to_freeze();
+			try_to_freeze();
+
+			xprt = rqstp->rq_xprt;
+			if (xprt != NULL)
+				return xprt;
+		} else
+			__set_current_state(TASK_RUNNING);
 
 		spin_lock_bh(&pool->sp_lock);
-		remove_wait_queue(&rqstp->rq_wait, &wait);
 		if (!time_left)
 			pool->sp_stats.threads_timedout++;
 
@@ -699,6 +687,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 				return ERR_PTR(-EAGAIN);
 		}
 	}
+out:
 	spin_unlock_bh(&pool->sp_lock);
 	return xprt;
 }
@@ -744,7 +733,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 			svc_add_new_temp_xprt(serv, newxpt);
 		else
 			module_put(xprt->xpt_class->xcl_owner);
-	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
+	} else {
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
 			rqstp, rqstp->rq_pool->sp_id, xprt,
@@ -781,10 +770,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		printk(KERN_ERR
 			"svc_recv: service %p, transport not NULL!\n",
 			 rqstp);
-	if (waitqueue_active(&rqstp->rq_wait))
-		printk(KERN_ERR
-			"svc_recv: service %p, wait queue active!\n",
-			 rqstp);
 
 	err = svc_alloc_arg(rqstp);
 	if (err)

net/sunrpc/svcsock.c

@@ -311,19 +311,6 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 	return len;
 }
 
-/*
- * Check input queue length
- */
-static int svc_recv_available(struct svc_sock *svsk)
-{
-	struct socket	*sock = svsk->sk_sock;
-	int		avail, err;
-
-	err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail);
-
-	return (err >= 0)? avail : err;
-}
-
 /*
  * Generic recvfrom routine.
  */
@@ -339,8 +326,14 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
 
 	rqstp->rq_xprt_hlen = 0;
 
+	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
 				msg.msg_flags);
+	/* If we read a full record, then assume there may be more
+	 * data to read (stream based sockets only!)
+	 */
+	if (len == buflen)
+		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
 	dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
 		svsk, iov[0].iov_base, iov[0].iov_len, len);
@@ -980,8 +973,6 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 	unsigned int want;
 	int len;
 
-	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-
 	if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
 		struct kvec	iov;
 
@@ -1036,7 +1027,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 			"%s: Got unrecognized reply: "
 			"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
 			__func__, ntohl(calldir),
-			bc_xprt, xid);
+			bc_xprt, ntohl(xid));
 		return -EAGAIN;
 	}
 
@@ -1073,8 +1064,6 @@ static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
 static void svc_tcp_fragment_received(struct svc_sock *svsk)
 {
 	/* If we have more data, signal svc_xprt_enqueue() to try again */
-	if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
-		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 	dprintk("svc: TCP %s record (%d bytes)\n",
 		svc_sock_final_rec(svsk) ? "final" : "nonfinal",
 		svc_sock_reclen(svsk));

net/sunrpc/xprtrdma/svc_rdma_transport.c

@@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = {
 	.xcl_name = "rdma",
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_rdma_ops,
-	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA,
 	.xcl_ident = XPRT_TRANSPORT_RDMA,
 };
 

net/sunrpc/xprtrdma/xprt_rdma.h

@@ -51,6 +51,7 @@
 #include <linux/sunrpc/clnt.h> 		/* rpc_xprt */
 #include <linux/sunrpc/rpc_rdma.h> 	/* RPC/RDMA protocol */
 #include <linux/sunrpc/xprtrdma.h> 	/* xprt parameters */
+#include <linux/sunrpc/svc.h>		/* RPCSVC_MAXPAYLOAD */
 
 #define RDMA_RESOLVE_TIMEOUT	(5000)	/* 5 seconds */
 #define RDMA_CONNECT_RETRY_MAX	(2)	/* retries if no listener backlog */
@@ -392,4 +393,10 @@ extern struct kmem_cache *svc_rdma_ctxt_cachep;
 /* Workqueue created in svc_rdma.c */
 extern struct workqueue_struct *svc_rdma_wq;
 
+#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
+#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD
+#else
+#define RPCSVC_MAXPAYLOAD_RDMA (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT)
+#endif
+
 #endif				/* _LINUX_SUNRPC_XPRT_RDMA_H */